Text Generation
Transformers
Safetensors
MLX
gpt_bigcode
code
granite
conversational
Eval Results (legacy)
text-generation-inference
Instructions to use mlx-community/granite-34b-code-instruct-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mlx-community/granite-34b-code-instruct-8bit with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="mlx-community/granite-34b-code-instruct-8bit") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("mlx-community/granite-34b-code-instruct-8bit") model = AutoModelForCausalLM.from_pretrained("mlx-community/granite-34b-code-instruct-8bit") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - MLX
How to use mlx-community/granite-34b-code-instruct-8bit with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("mlx-community/granite-34b-code-instruct-8bit") prompt = "Write a story about Einstein" messages = [{"role": "user", "content": prompt}] prompt = tokenizer.apply_chat_template( messages, add_generation_prompt=True ) text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- vLLM
How to use mlx-community/granite-34b-code-instruct-8bit with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "mlx-community/granite-34b-code-instruct-8bit" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "mlx-community/granite-34b-code-instruct-8bit", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/mlx-community/granite-34b-code-instruct-8bit
- SGLang
How to use mlx-community/granite-34b-code-instruct-8bit with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "mlx-community/granite-34b-code-instruct-8bit" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "mlx-community/granite-34b-code-instruct-8bit", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "mlx-community/granite-34b-code-instruct-8bit" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "mlx-community/granite-34b-code-instruct-8bit", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - MLX LM
How to use mlx-community/granite-34b-code-instruct-8bit with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "mlx-community/granite-34b-code-instruct-8bit"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "mlx-community/granite-34b-code-instruct-8bit" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "mlx-community/granite-34b-code-instruct-8bit", "messages": [ {"role": "user", "content": "Hello"} ] }' - Docker Model Runner
How to use mlx-community/granite-34b-code-instruct-8bit with Docker Model Runner:
docker model run hf.co/mlx-community/granite-34b-code-instruct-8bit
| { | |
| "metadata": { | |
| "total_size": 35828436992 | |
| }, | |
| "weight_map": { | |
| "transformer.h.0.attn.c_attn.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.0.attn.c_attn.biases": "model-00001-of-00007.safetensors", | |
| "transformer.h.0.attn.c_attn.scales": "model-00001-of-00007.safetensors", | |
| "transformer.h.0.attn.c_attn.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.0.attn.c_proj.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.0.attn.c_proj.biases": "model-00001-of-00007.safetensors", | |
| "transformer.h.0.attn.c_proj.scales": "model-00001-of-00007.safetensors", | |
| "transformer.h.0.attn.c_proj.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.0.ln_1.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.0.ln_1.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.0.ln_2.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.0.ln_2.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.0.mlp.c_fc.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.0.mlp.c_fc.biases": "model-00001-of-00007.safetensors", | |
| "transformer.h.0.mlp.c_fc.scales": "model-00001-of-00007.safetensors", | |
| "transformer.h.0.mlp.c_fc.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.0.mlp.c_proj.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.0.mlp.c_proj.biases": "model-00001-of-00007.safetensors", | |
| "transformer.h.0.mlp.c_proj.scales": "model-00001-of-00007.safetensors", | |
| "transformer.h.0.mlp.c_proj.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.1.attn.c_attn.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.1.attn.c_attn.biases": "model-00001-of-00007.safetensors", | |
| "transformer.h.1.attn.c_attn.scales": "model-00001-of-00007.safetensors", | |
| "transformer.h.1.attn.c_attn.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.1.attn.c_proj.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.1.attn.c_proj.biases": "model-00001-of-00007.safetensors", | |
| "transformer.h.1.attn.c_proj.scales": "model-00001-of-00007.safetensors", | |
| "transformer.h.1.attn.c_proj.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.1.ln_1.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.1.ln_1.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.1.ln_2.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.1.ln_2.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.1.mlp.c_fc.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.1.mlp.c_fc.biases": "model-00001-of-00007.safetensors", | |
| "transformer.h.1.mlp.c_fc.scales": "model-00001-of-00007.safetensors", | |
| "transformer.h.1.mlp.c_fc.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.1.mlp.c_proj.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.1.mlp.c_proj.biases": "model-00001-of-00007.safetensors", | |
| "transformer.h.1.mlp.c_proj.scales": "model-00001-of-00007.safetensors", | |
| "transformer.h.1.mlp.c_proj.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.10.attn.c_attn.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.10.attn.c_attn.biases": "model-00001-of-00007.safetensors", | |
| "transformer.h.10.attn.c_attn.scales": "model-00001-of-00007.safetensors", | |
| "transformer.h.10.attn.c_attn.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.10.attn.c_proj.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.10.attn.c_proj.biases": "model-00001-of-00007.safetensors", | |
| "transformer.h.10.attn.c_proj.scales": "model-00001-of-00007.safetensors", | |
| "transformer.h.10.attn.c_proj.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.10.ln_1.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.10.ln_1.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.10.ln_2.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.10.ln_2.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.10.mlp.c_fc.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.10.mlp.c_fc.biases": "model-00001-of-00007.safetensors", | |
| "transformer.h.10.mlp.c_fc.scales": "model-00001-of-00007.safetensors", | |
| "transformer.h.10.mlp.c_fc.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.10.mlp.c_proj.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.10.mlp.c_proj.biases": "model-00001-of-00007.safetensors", | |
| "transformer.h.10.mlp.c_proj.scales": "model-00001-of-00007.safetensors", | |
| "transformer.h.10.mlp.c_proj.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.11.attn.c_attn.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.11.attn.c_attn.biases": "model-00001-of-00007.safetensors", | |
| "transformer.h.11.attn.c_attn.scales": "model-00001-of-00007.safetensors", | |
| "transformer.h.11.attn.c_attn.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.11.attn.c_proj.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.11.attn.c_proj.biases": "model-00001-of-00007.safetensors", | |
| "transformer.h.11.attn.c_proj.scales": "model-00001-of-00007.safetensors", | |
| "transformer.h.11.attn.c_proj.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.11.ln_1.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.11.ln_1.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.11.ln_2.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.11.ln_2.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.11.mlp.c_fc.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.11.mlp.c_fc.biases": "model-00001-of-00007.safetensors", | |
| "transformer.h.11.mlp.c_fc.scales": "model-00001-of-00007.safetensors", | |
| "transformer.h.11.mlp.c_fc.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.11.mlp.c_proj.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.11.mlp.c_proj.biases": "model-00001-of-00007.safetensors", | |
| "transformer.h.11.mlp.c_proj.scales": "model-00001-of-00007.safetensors", | |
| "transformer.h.11.mlp.c_proj.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.12.attn.c_attn.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.12.attn.c_attn.biases": "model-00001-of-00007.safetensors", | |
| "transformer.h.12.attn.c_attn.scales": "model-00001-of-00007.safetensors", | |
| "transformer.h.12.attn.c_attn.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.12.attn.c_proj.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.12.attn.c_proj.biases": "model-00001-of-00007.safetensors", | |
| "transformer.h.12.attn.c_proj.scales": "model-00001-of-00007.safetensors", | |
| "transformer.h.12.attn.c_proj.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.12.ln_1.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.12.ln_1.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.12.ln_2.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.12.ln_2.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.12.mlp.c_fc.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.12.mlp.c_fc.biases": "model-00002-of-00007.safetensors", | |
| "transformer.h.12.mlp.c_fc.scales": "model-00002-of-00007.safetensors", | |
| "transformer.h.12.mlp.c_fc.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.12.mlp.c_proj.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.12.mlp.c_proj.biases": "model-00002-of-00007.safetensors", | |
| "transformer.h.12.mlp.c_proj.scales": "model-00002-of-00007.safetensors", | |
| "transformer.h.12.mlp.c_proj.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.13.attn.c_attn.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.13.attn.c_attn.biases": "model-00002-of-00007.safetensors", | |
| "transformer.h.13.attn.c_attn.scales": "model-00002-of-00007.safetensors", | |
| "transformer.h.13.attn.c_attn.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.13.attn.c_proj.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.13.attn.c_proj.biases": "model-00002-of-00007.safetensors", | |
| "transformer.h.13.attn.c_proj.scales": "model-00002-of-00007.safetensors", | |
| "transformer.h.13.attn.c_proj.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.13.ln_1.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.13.ln_1.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.13.ln_2.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.13.ln_2.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.13.mlp.c_fc.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.13.mlp.c_fc.biases": "model-00002-of-00007.safetensors", | |
| "transformer.h.13.mlp.c_fc.scales": "model-00002-of-00007.safetensors", | |
| "transformer.h.13.mlp.c_fc.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.13.mlp.c_proj.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.13.mlp.c_proj.biases": "model-00002-of-00007.safetensors", | |
| "transformer.h.13.mlp.c_proj.scales": "model-00002-of-00007.safetensors", | |
| "transformer.h.13.mlp.c_proj.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.14.attn.c_attn.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.14.attn.c_attn.biases": "model-00002-of-00007.safetensors", | |
| "transformer.h.14.attn.c_attn.scales": "model-00002-of-00007.safetensors", | |
| "transformer.h.14.attn.c_attn.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.14.attn.c_proj.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.14.attn.c_proj.biases": "model-00002-of-00007.safetensors", | |
| "transformer.h.14.attn.c_proj.scales": "model-00002-of-00007.safetensors", | |
| "transformer.h.14.attn.c_proj.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.14.ln_1.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.14.ln_1.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.14.ln_2.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.14.ln_2.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.14.mlp.c_fc.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.14.mlp.c_fc.biases": "model-00002-of-00007.safetensors", | |
| "transformer.h.14.mlp.c_fc.scales": "model-00002-of-00007.safetensors", | |
| "transformer.h.14.mlp.c_fc.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.14.mlp.c_proj.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.14.mlp.c_proj.biases": "model-00002-of-00007.safetensors", | |
| "transformer.h.14.mlp.c_proj.scales": "model-00002-of-00007.safetensors", | |
| "transformer.h.14.mlp.c_proj.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.15.attn.c_attn.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.15.attn.c_attn.biases": "model-00002-of-00007.safetensors", | |
| "transformer.h.15.attn.c_attn.scales": "model-00002-of-00007.safetensors", | |
| "transformer.h.15.attn.c_attn.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.15.attn.c_proj.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.15.attn.c_proj.biases": "model-00002-of-00007.safetensors", | |
| "transformer.h.15.attn.c_proj.scales": "model-00002-of-00007.safetensors", | |
| "transformer.h.15.attn.c_proj.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.15.ln_1.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.15.ln_1.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.15.ln_2.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.15.ln_2.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.15.mlp.c_fc.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.15.mlp.c_fc.biases": "model-00002-of-00007.safetensors", | |
| "transformer.h.15.mlp.c_fc.scales": "model-00002-of-00007.safetensors", | |
| "transformer.h.15.mlp.c_fc.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.15.mlp.c_proj.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.15.mlp.c_proj.biases": "model-00002-of-00007.safetensors", | |
| "transformer.h.15.mlp.c_proj.scales": "model-00002-of-00007.safetensors", | |
| "transformer.h.15.mlp.c_proj.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.16.attn.c_attn.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.16.attn.c_attn.biases": "model-00002-of-00007.safetensors", | |
| "transformer.h.16.attn.c_attn.scales": "model-00002-of-00007.safetensors", | |
| "transformer.h.16.attn.c_attn.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.16.attn.c_proj.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.16.attn.c_proj.biases": "model-00002-of-00007.safetensors", | |
| "transformer.h.16.attn.c_proj.scales": "model-00002-of-00007.safetensors", | |
| "transformer.h.16.attn.c_proj.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.16.ln_1.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.16.ln_1.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.16.ln_2.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.16.ln_2.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.16.mlp.c_fc.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.16.mlp.c_fc.biases": "model-00002-of-00007.safetensors", | |
| "transformer.h.16.mlp.c_fc.scales": "model-00002-of-00007.safetensors", | |
| "transformer.h.16.mlp.c_fc.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.16.mlp.c_proj.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.16.mlp.c_proj.biases": "model-00002-of-00007.safetensors", | |
| "transformer.h.16.mlp.c_proj.scales": "model-00002-of-00007.safetensors", | |
| "transformer.h.16.mlp.c_proj.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.17.attn.c_attn.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.17.attn.c_attn.biases": "model-00002-of-00007.safetensors", | |
| "transformer.h.17.attn.c_attn.scales": "model-00002-of-00007.safetensors", | |
| "transformer.h.17.attn.c_attn.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.17.attn.c_proj.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.17.attn.c_proj.biases": "model-00002-of-00007.safetensors", | |
| "transformer.h.17.attn.c_proj.scales": "model-00002-of-00007.safetensors", | |
| "transformer.h.17.attn.c_proj.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.17.ln_1.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.17.ln_1.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.17.ln_2.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.17.ln_2.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.17.mlp.c_fc.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.17.mlp.c_fc.biases": "model-00002-of-00007.safetensors", | |
| "transformer.h.17.mlp.c_fc.scales": "model-00002-of-00007.safetensors", | |
| "transformer.h.17.mlp.c_fc.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.17.mlp.c_proj.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.17.mlp.c_proj.biases": "model-00002-of-00007.safetensors", | |
| "transformer.h.17.mlp.c_proj.scales": "model-00002-of-00007.safetensors", | |
| "transformer.h.17.mlp.c_proj.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.18.attn.c_attn.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.18.attn.c_attn.biases": "model-00002-of-00007.safetensors", | |
| "transformer.h.18.attn.c_attn.scales": "model-00002-of-00007.safetensors", | |
| "transformer.h.18.attn.c_attn.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.18.attn.c_proj.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.18.attn.c_proj.biases": "model-00002-of-00007.safetensors", | |
| "transformer.h.18.attn.c_proj.scales": "model-00002-of-00007.safetensors", | |
| "transformer.h.18.attn.c_proj.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.18.ln_1.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.18.ln_1.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.18.ln_2.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.18.ln_2.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.18.mlp.c_fc.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.18.mlp.c_fc.biases": "model-00002-of-00007.safetensors", | |
| "transformer.h.18.mlp.c_fc.scales": "model-00002-of-00007.safetensors", | |
| "transformer.h.18.mlp.c_fc.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.18.mlp.c_proj.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.18.mlp.c_proj.biases": "model-00002-of-00007.safetensors", | |
| "transformer.h.18.mlp.c_proj.scales": "model-00002-of-00007.safetensors", | |
| "transformer.h.18.mlp.c_proj.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.19.attn.c_attn.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.19.attn.c_attn.biases": "model-00002-of-00007.safetensors", | |
| "transformer.h.19.attn.c_attn.scales": "model-00002-of-00007.safetensors", | |
| "transformer.h.19.attn.c_attn.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.19.attn.c_proj.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.19.attn.c_proj.biases": "model-00002-of-00007.safetensors", | |
| "transformer.h.19.attn.c_proj.scales": "model-00002-of-00007.safetensors", | |
| "transformer.h.19.attn.c_proj.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.19.ln_1.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.19.ln_1.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.19.ln_2.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.19.ln_2.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.19.mlp.c_fc.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.19.mlp.c_fc.biases": "model-00002-of-00007.safetensors", | |
| "transformer.h.19.mlp.c_fc.scales": "model-00002-of-00007.safetensors", | |
| "transformer.h.19.mlp.c_fc.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.19.mlp.c_proj.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.19.mlp.c_proj.biases": "model-00002-of-00007.safetensors", | |
| "transformer.h.19.mlp.c_proj.scales": "model-00002-of-00007.safetensors", | |
| "transformer.h.19.mlp.c_proj.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.2.attn.c_attn.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.2.attn.c_attn.biases": "model-00001-of-00007.safetensors", | |
| "transformer.h.2.attn.c_attn.scales": "model-00001-of-00007.safetensors", | |
| "transformer.h.2.attn.c_attn.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.2.attn.c_proj.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.2.attn.c_proj.biases": "model-00001-of-00007.safetensors", | |
| "transformer.h.2.attn.c_proj.scales": "model-00001-of-00007.safetensors", | |
| "transformer.h.2.attn.c_proj.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.2.ln_1.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.2.ln_1.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.2.ln_2.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.2.ln_2.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.2.mlp.c_fc.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.2.mlp.c_fc.biases": "model-00001-of-00007.safetensors", | |
| "transformer.h.2.mlp.c_fc.scales": "model-00001-of-00007.safetensors", | |
| "transformer.h.2.mlp.c_fc.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.2.mlp.c_proj.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.2.mlp.c_proj.biases": "model-00001-of-00007.safetensors", | |
| "transformer.h.2.mlp.c_proj.scales": "model-00001-of-00007.safetensors", | |
| "transformer.h.2.mlp.c_proj.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.20.attn.c_attn.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.20.attn.c_attn.biases": "model-00002-of-00007.safetensors", | |
| "transformer.h.20.attn.c_attn.scales": "model-00002-of-00007.safetensors", | |
| "transformer.h.20.attn.c_attn.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.20.attn.c_proj.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.20.attn.c_proj.biases": "model-00002-of-00007.safetensors", | |
| "transformer.h.20.attn.c_proj.scales": "model-00002-of-00007.safetensors", | |
| "transformer.h.20.attn.c_proj.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.20.ln_1.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.20.ln_1.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.20.ln_2.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.20.ln_2.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.20.mlp.c_fc.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.20.mlp.c_fc.biases": "model-00002-of-00007.safetensors", | |
| "transformer.h.20.mlp.c_fc.scales": "model-00002-of-00007.safetensors", | |
| "transformer.h.20.mlp.c_fc.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.20.mlp.c_proj.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.20.mlp.c_proj.biases": "model-00002-of-00007.safetensors", | |
| "transformer.h.20.mlp.c_proj.scales": "model-00002-of-00007.safetensors", | |
| "transformer.h.20.mlp.c_proj.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.21.attn.c_attn.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.21.attn.c_attn.biases": "model-00002-of-00007.safetensors", | |
| "transformer.h.21.attn.c_attn.scales": "model-00002-of-00007.safetensors", | |
| "transformer.h.21.attn.c_attn.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.21.attn.c_proj.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.21.attn.c_proj.biases": "model-00002-of-00007.safetensors", | |
| "transformer.h.21.attn.c_proj.scales": "model-00002-of-00007.safetensors", | |
| "transformer.h.21.attn.c_proj.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.21.ln_1.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.21.ln_1.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.21.ln_2.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.21.ln_2.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.21.mlp.c_fc.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.21.mlp.c_fc.biases": "model-00002-of-00007.safetensors", | |
| "transformer.h.21.mlp.c_fc.scales": "model-00002-of-00007.safetensors", | |
| "transformer.h.21.mlp.c_fc.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.21.mlp.c_proj.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.21.mlp.c_proj.biases": "model-00002-of-00007.safetensors", | |
| "transformer.h.21.mlp.c_proj.scales": "model-00002-of-00007.safetensors", | |
| "transformer.h.21.mlp.c_proj.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.22.attn.c_attn.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.22.attn.c_attn.biases": "model-00002-of-00007.safetensors", | |
| "transformer.h.22.attn.c_attn.scales": "model-00002-of-00007.safetensors", | |
| "transformer.h.22.attn.c_attn.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.22.attn.c_proj.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.22.attn.c_proj.biases": "model-00002-of-00007.safetensors", | |
| "transformer.h.22.attn.c_proj.scales": "model-00002-of-00007.safetensors", | |
| "transformer.h.22.attn.c_proj.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.22.ln_1.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.22.ln_1.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.22.ln_2.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.22.ln_2.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.22.mlp.c_fc.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.22.mlp.c_fc.biases": "model-00002-of-00007.safetensors", | |
| "transformer.h.22.mlp.c_fc.scales": "model-00002-of-00007.safetensors", | |
| "transformer.h.22.mlp.c_fc.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.22.mlp.c_proj.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.22.mlp.c_proj.biases": "model-00002-of-00007.safetensors", | |
| "transformer.h.22.mlp.c_proj.scales": "model-00002-of-00007.safetensors", | |
| "transformer.h.22.mlp.c_proj.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.23.attn.c_attn.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.23.attn.c_attn.biases": "model-00002-of-00007.safetensors", | |
| "transformer.h.23.attn.c_attn.scales": "model-00002-of-00007.safetensors", | |
| "transformer.h.23.attn.c_attn.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.23.attn.c_proj.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.23.attn.c_proj.biases": "model-00002-of-00007.safetensors", | |
| "transformer.h.23.attn.c_proj.scales": "model-00002-of-00007.safetensors", | |
| "transformer.h.23.attn.c_proj.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.23.ln_1.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.23.ln_1.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.23.ln_2.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.23.ln_2.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.23.mlp.c_fc.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.23.mlp.c_fc.biases": "model-00002-of-00007.safetensors", | |
| "transformer.h.23.mlp.c_fc.scales": "model-00002-of-00007.safetensors", | |
| "transformer.h.23.mlp.c_fc.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.23.mlp.c_proj.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.23.mlp.c_proj.biases": "model-00002-of-00007.safetensors", | |
| "transformer.h.23.mlp.c_proj.scales": "model-00002-of-00007.safetensors", | |
| "transformer.h.23.mlp.c_proj.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.24.attn.c_attn.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.24.attn.c_attn.biases": "model-00002-of-00007.safetensors", | |
| "transformer.h.24.attn.c_attn.scales": "model-00002-of-00007.safetensors", | |
| "transformer.h.24.attn.c_attn.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.24.attn.c_proj.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.24.attn.c_proj.biases": "model-00002-of-00007.safetensors", | |
| "transformer.h.24.attn.c_proj.scales": "model-00002-of-00007.safetensors", | |
| "transformer.h.24.attn.c_proj.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.24.ln_1.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.24.ln_1.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.24.ln_2.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.24.ln_2.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.24.mlp.c_fc.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.24.mlp.c_fc.biases": "model-00002-of-00007.safetensors", | |
| "transformer.h.24.mlp.c_fc.scales": "model-00002-of-00007.safetensors", | |
| "transformer.h.24.mlp.c_fc.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.24.mlp.c_proj.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.24.mlp.c_proj.biases": "model-00002-of-00007.safetensors", | |
| "transformer.h.24.mlp.c_proj.scales": "model-00002-of-00007.safetensors", | |
| "transformer.h.24.mlp.c_proj.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.25.attn.c_attn.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.25.attn.c_attn.biases": "model-00002-of-00007.safetensors", | |
| "transformer.h.25.attn.c_attn.scales": "model-00002-of-00007.safetensors", | |
| "transformer.h.25.attn.c_attn.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.25.attn.c_proj.bias": "model-00002-of-00007.safetensors", | |
| "transformer.h.25.attn.c_proj.biases": "model-00002-of-00007.safetensors", | |
| "transformer.h.25.attn.c_proj.scales": "model-00002-of-00007.safetensors", | |
| "transformer.h.25.attn.c_proj.weight": "model-00002-of-00007.safetensors", | |
| "transformer.h.25.ln_1.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.25.ln_1.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.25.ln_2.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.25.ln_2.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.25.mlp.c_fc.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.25.mlp.c_fc.biases": "model-00003-of-00007.safetensors", | |
| "transformer.h.25.mlp.c_fc.scales": "model-00003-of-00007.safetensors", | |
| "transformer.h.25.mlp.c_fc.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.25.mlp.c_proj.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.25.mlp.c_proj.biases": "model-00003-of-00007.safetensors", | |
| "transformer.h.25.mlp.c_proj.scales": "model-00003-of-00007.safetensors", | |
| "transformer.h.25.mlp.c_proj.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.26.attn.c_attn.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.26.attn.c_attn.biases": "model-00003-of-00007.safetensors", | |
| "transformer.h.26.attn.c_attn.scales": "model-00003-of-00007.safetensors", | |
| "transformer.h.26.attn.c_attn.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.26.attn.c_proj.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.26.attn.c_proj.biases": "model-00003-of-00007.safetensors", | |
| "transformer.h.26.attn.c_proj.scales": "model-00003-of-00007.safetensors", | |
| "transformer.h.26.attn.c_proj.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.26.ln_1.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.26.ln_1.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.26.ln_2.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.26.ln_2.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.26.mlp.c_fc.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.26.mlp.c_fc.biases": "model-00003-of-00007.safetensors", | |
| "transformer.h.26.mlp.c_fc.scales": "model-00003-of-00007.safetensors", | |
| "transformer.h.26.mlp.c_fc.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.26.mlp.c_proj.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.26.mlp.c_proj.biases": "model-00003-of-00007.safetensors", | |
| "transformer.h.26.mlp.c_proj.scales": "model-00003-of-00007.safetensors", | |
| "transformer.h.26.mlp.c_proj.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.27.attn.c_attn.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.27.attn.c_attn.biases": "model-00003-of-00007.safetensors", | |
| "transformer.h.27.attn.c_attn.scales": "model-00003-of-00007.safetensors", | |
| "transformer.h.27.attn.c_attn.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.27.attn.c_proj.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.27.attn.c_proj.biases": "model-00003-of-00007.safetensors", | |
| "transformer.h.27.attn.c_proj.scales": "model-00003-of-00007.safetensors", | |
| "transformer.h.27.attn.c_proj.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.27.ln_1.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.27.ln_1.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.27.ln_2.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.27.ln_2.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.27.mlp.c_fc.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.27.mlp.c_fc.biases": "model-00003-of-00007.safetensors", | |
| "transformer.h.27.mlp.c_fc.scales": "model-00003-of-00007.safetensors", | |
| "transformer.h.27.mlp.c_fc.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.27.mlp.c_proj.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.27.mlp.c_proj.biases": "model-00003-of-00007.safetensors", | |
| "transformer.h.27.mlp.c_proj.scales": "model-00003-of-00007.safetensors", | |
| "transformer.h.27.mlp.c_proj.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.28.attn.c_attn.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.28.attn.c_attn.biases": "model-00003-of-00007.safetensors", | |
| "transformer.h.28.attn.c_attn.scales": "model-00003-of-00007.safetensors", | |
| "transformer.h.28.attn.c_attn.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.28.attn.c_proj.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.28.attn.c_proj.biases": "model-00003-of-00007.safetensors", | |
| "transformer.h.28.attn.c_proj.scales": "model-00003-of-00007.safetensors", | |
| "transformer.h.28.attn.c_proj.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.28.ln_1.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.28.ln_1.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.28.ln_2.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.28.ln_2.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.28.mlp.c_fc.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.28.mlp.c_fc.biases": "model-00003-of-00007.safetensors", | |
| "transformer.h.28.mlp.c_fc.scales": "model-00003-of-00007.safetensors", | |
| "transformer.h.28.mlp.c_fc.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.28.mlp.c_proj.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.28.mlp.c_proj.biases": "model-00003-of-00007.safetensors", | |
| "transformer.h.28.mlp.c_proj.scales": "model-00003-of-00007.safetensors", | |
| "transformer.h.28.mlp.c_proj.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.29.attn.c_attn.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.29.attn.c_attn.biases": "model-00003-of-00007.safetensors", | |
| "transformer.h.29.attn.c_attn.scales": "model-00003-of-00007.safetensors", | |
| "transformer.h.29.attn.c_attn.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.29.attn.c_proj.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.29.attn.c_proj.biases": "model-00003-of-00007.safetensors", | |
| "transformer.h.29.attn.c_proj.scales": "model-00003-of-00007.safetensors", | |
| "transformer.h.29.attn.c_proj.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.29.ln_1.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.29.ln_1.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.29.ln_2.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.29.ln_2.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.29.mlp.c_fc.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.29.mlp.c_fc.biases": "model-00003-of-00007.safetensors", | |
| "transformer.h.29.mlp.c_fc.scales": "model-00003-of-00007.safetensors", | |
| "transformer.h.29.mlp.c_fc.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.29.mlp.c_proj.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.29.mlp.c_proj.biases": "model-00003-of-00007.safetensors", | |
| "transformer.h.29.mlp.c_proj.scales": "model-00003-of-00007.safetensors", | |
| "transformer.h.29.mlp.c_proj.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.3.attn.c_attn.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.3.attn.c_attn.biases": "model-00001-of-00007.safetensors", | |
| "transformer.h.3.attn.c_attn.scales": "model-00001-of-00007.safetensors", | |
| "transformer.h.3.attn.c_attn.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.3.attn.c_proj.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.3.attn.c_proj.biases": "model-00001-of-00007.safetensors", | |
| "transformer.h.3.attn.c_proj.scales": "model-00001-of-00007.safetensors", | |
| "transformer.h.3.attn.c_proj.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.3.ln_1.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.3.ln_1.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.3.ln_2.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.3.ln_2.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.3.mlp.c_fc.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.3.mlp.c_fc.biases": "model-00001-of-00007.safetensors", | |
| "transformer.h.3.mlp.c_fc.scales": "model-00001-of-00007.safetensors", | |
| "transformer.h.3.mlp.c_fc.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.3.mlp.c_proj.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.3.mlp.c_proj.biases": "model-00001-of-00007.safetensors", | |
| "transformer.h.3.mlp.c_proj.scales": "model-00001-of-00007.safetensors", | |
| "transformer.h.3.mlp.c_proj.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.30.attn.c_attn.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.30.attn.c_attn.biases": "model-00003-of-00007.safetensors", | |
| "transformer.h.30.attn.c_attn.scales": "model-00003-of-00007.safetensors", | |
| "transformer.h.30.attn.c_attn.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.30.attn.c_proj.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.30.attn.c_proj.biases": "model-00003-of-00007.safetensors", | |
| "transformer.h.30.attn.c_proj.scales": "model-00003-of-00007.safetensors", | |
| "transformer.h.30.attn.c_proj.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.30.ln_1.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.30.ln_1.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.30.ln_2.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.30.ln_2.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.30.mlp.c_fc.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.30.mlp.c_fc.biases": "model-00003-of-00007.safetensors", | |
| "transformer.h.30.mlp.c_fc.scales": "model-00003-of-00007.safetensors", | |
| "transformer.h.30.mlp.c_fc.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.30.mlp.c_proj.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.30.mlp.c_proj.biases": "model-00003-of-00007.safetensors", | |
| "transformer.h.30.mlp.c_proj.scales": "model-00003-of-00007.safetensors", | |
| "transformer.h.30.mlp.c_proj.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.31.attn.c_attn.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.31.attn.c_attn.biases": "model-00003-of-00007.safetensors", | |
| "transformer.h.31.attn.c_attn.scales": "model-00003-of-00007.safetensors", | |
| "transformer.h.31.attn.c_attn.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.31.attn.c_proj.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.31.attn.c_proj.biases": "model-00003-of-00007.safetensors", | |
| "transformer.h.31.attn.c_proj.scales": "model-00003-of-00007.safetensors", | |
| "transformer.h.31.attn.c_proj.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.31.ln_1.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.31.ln_1.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.31.ln_2.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.31.ln_2.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.31.mlp.c_fc.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.31.mlp.c_fc.biases": "model-00003-of-00007.safetensors", | |
| "transformer.h.31.mlp.c_fc.scales": "model-00003-of-00007.safetensors", | |
| "transformer.h.31.mlp.c_fc.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.31.mlp.c_proj.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.31.mlp.c_proj.biases": "model-00003-of-00007.safetensors", | |
| "transformer.h.31.mlp.c_proj.scales": "model-00003-of-00007.safetensors", | |
| "transformer.h.31.mlp.c_proj.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.32.attn.c_attn.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.32.attn.c_attn.biases": "model-00003-of-00007.safetensors", | |
| "transformer.h.32.attn.c_attn.scales": "model-00003-of-00007.safetensors", | |
| "transformer.h.32.attn.c_attn.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.32.attn.c_proj.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.32.attn.c_proj.biases": "model-00003-of-00007.safetensors", | |
| "transformer.h.32.attn.c_proj.scales": "model-00003-of-00007.safetensors", | |
| "transformer.h.32.attn.c_proj.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.32.ln_1.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.32.ln_1.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.32.ln_2.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.32.ln_2.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.32.mlp.c_fc.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.32.mlp.c_fc.biases": "model-00003-of-00007.safetensors", | |
| "transformer.h.32.mlp.c_fc.scales": "model-00003-of-00007.safetensors", | |
| "transformer.h.32.mlp.c_fc.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.32.mlp.c_proj.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.32.mlp.c_proj.biases": "model-00003-of-00007.safetensors", | |
| "transformer.h.32.mlp.c_proj.scales": "model-00003-of-00007.safetensors", | |
| "transformer.h.32.mlp.c_proj.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.33.attn.c_attn.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.33.attn.c_attn.biases": "model-00003-of-00007.safetensors", | |
| "transformer.h.33.attn.c_attn.scales": "model-00003-of-00007.safetensors", | |
| "transformer.h.33.attn.c_attn.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.33.attn.c_proj.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.33.attn.c_proj.biases": "model-00003-of-00007.safetensors", | |
| "transformer.h.33.attn.c_proj.scales": "model-00003-of-00007.safetensors", | |
| "transformer.h.33.attn.c_proj.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.33.ln_1.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.33.ln_1.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.33.ln_2.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.33.ln_2.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.33.mlp.c_fc.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.33.mlp.c_fc.biases": "model-00003-of-00007.safetensors", | |
| "transformer.h.33.mlp.c_fc.scales": "model-00003-of-00007.safetensors", | |
| "transformer.h.33.mlp.c_fc.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.33.mlp.c_proj.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.33.mlp.c_proj.biases": "model-00003-of-00007.safetensors", | |
| "transformer.h.33.mlp.c_proj.scales": "model-00003-of-00007.safetensors", | |
| "transformer.h.33.mlp.c_proj.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.34.attn.c_attn.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.34.attn.c_attn.biases": "model-00003-of-00007.safetensors", | |
| "transformer.h.34.attn.c_attn.scales": "model-00003-of-00007.safetensors", | |
| "transformer.h.34.attn.c_attn.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.34.attn.c_proj.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.34.attn.c_proj.biases": "model-00003-of-00007.safetensors", | |
| "transformer.h.34.attn.c_proj.scales": "model-00003-of-00007.safetensors", | |
| "transformer.h.34.attn.c_proj.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.34.ln_1.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.34.ln_1.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.34.ln_2.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.34.ln_2.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.34.mlp.c_fc.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.34.mlp.c_fc.biases": "model-00003-of-00007.safetensors", | |
| "transformer.h.34.mlp.c_fc.scales": "model-00003-of-00007.safetensors", | |
| "transformer.h.34.mlp.c_fc.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.34.mlp.c_proj.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.34.mlp.c_proj.biases": "model-00003-of-00007.safetensors", | |
| "transformer.h.34.mlp.c_proj.scales": "model-00003-of-00007.safetensors", | |
| "transformer.h.34.mlp.c_proj.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.35.attn.c_attn.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.35.attn.c_attn.biases": "model-00003-of-00007.safetensors", | |
| "transformer.h.35.attn.c_attn.scales": "model-00003-of-00007.safetensors", | |
| "transformer.h.35.attn.c_attn.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.35.attn.c_proj.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.35.attn.c_proj.biases": "model-00003-of-00007.safetensors", | |
| "transformer.h.35.attn.c_proj.scales": "model-00003-of-00007.safetensors", | |
| "transformer.h.35.attn.c_proj.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.35.ln_1.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.35.ln_1.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.35.ln_2.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.35.ln_2.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.35.mlp.c_fc.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.35.mlp.c_fc.biases": "model-00003-of-00007.safetensors", | |
| "transformer.h.35.mlp.c_fc.scales": "model-00003-of-00007.safetensors", | |
| "transformer.h.35.mlp.c_fc.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.35.mlp.c_proj.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.35.mlp.c_proj.biases": "model-00003-of-00007.safetensors", | |
| "transformer.h.35.mlp.c_proj.scales": "model-00003-of-00007.safetensors", | |
| "transformer.h.35.mlp.c_proj.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.36.attn.c_attn.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.36.attn.c_attn.biases": "model-00003-of-00007.safetensors", | |
| "transformer.h.36.attn.c_attn.scales": "model-00003-of-00007.safetensors", | |
| "transformer.h.36.attn.c_attn.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.36.attn.c_proj.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.36.attn.c_proj.biases": "model-00003-of-00007.safetensors", | |
| "transformer.h.36.attn.c_proj.scales": "model-00003-of-00007.safetensors", | |
| "transformer.h.36.attn.c_proj.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.36.ln_1.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.36.ln_1.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.36.ln_2.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.36.ln_2.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.36.mlp.c_fc.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.36.mlp.c_fc.biases": "model-00003-of-00007.safetensors", | |
| "transformer.h.36.mlp.c_fc.scales": "model-00003-of-00007.safetensors", | |
| "transformer.h.36.mlp.c_fc.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.36.mlp.c_proj.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.36.mlp.c_proj.biases": "model-00003-of-00007.safetensors", | |
| "transformer.h.36.mlp.c_proj.scales": "model-00003-of-00007.safetensors", | |
| "transformer.h.36.mlp.c_proj.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.37.attn.c_attn.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.37.attn.c_attn.biases": "model-00003-of-00007.safetensors", | |
| "transformer.h.37.attn.c_attn.scales": "model-00003-of-00007.safetensors", | |
| "transformer.h.37.attn.c_attn.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.37.attn.c_proj.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.37.attn.c_proj.biases": "model-00003-of-00007.safetensors", | |
| "transformer.h.37.attn.c_proj.scales": "model-00003-of-00007.safetensors", | |
| "transformer.h.37.attn.c_proj.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.37.ln_1.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.37.ln_1.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.37.ln_2.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.37.ln_2.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.37.mlp.c_fc.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.37.mlp.c_fc.biases": "model-00003-of-00007.safetensors", | |
| "transformer.h.37.mlp.c_fc.scales": "model-00003-of-00007.safetensors", | |
| "transformer.h.37.mlp.c_fc.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.37.mlp.c_proj.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.37.mlp.c_proj.biases": "model-00003-of-00007.safetensors", | |
| "transformer.h.37.mlp.c_proj.scales": "model-00003-of-00007.safetensors", | |
| "transformer.h.37.mlp.c_proj.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.38.attn.c_attn.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.38.attn.c_attn.biases": "model-00003-of-00007.safetensors", | |
| "transformer.h.38.attn.c_attn.scales": "model-00003-of-00007.safetensors", | |
| "transformer.h.38.attn.c_attn.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.38.attn.c_proj.bias": "model-00003-of-00007.safetensors", | |
| "transformer.h.38.attn.c_proj.biases": "model-00003-of-00007.safetensors", | |
| "transformer.h.38.attn.c_proj.scales": "model-00003-of-00007.safetensors", | |
| "transformer.h.38.attn.c_proj.weight": "model-00003-of-00007.safetensors", | |
| "transformer.h.38.ln_1.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.38.ln_1.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.38.ln_2.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.38.ln_2.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.38.mlp.c_fc.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.38.mlp.c_fc.biases": "model-00004-of-00007.safetensors", | |
| "transformer.h.38.mlp.c_fc.scales": "model-00004-of-00007.safetensors", | |
| "transformer.h.38.mlp.c_fc.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.38.mlp.c_proj.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.38.mlp.c_proj.biases": "model-00004-of-00007.safetensors", | |
| "transformer.h.38.mlp.c_proj.scales": "model-00004-of-00007.safetensors", | |
| "transformer.h.38.mlp.c_proj.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.39.attn.c_attn.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.39.attn.c_attn.biases": "model-00004-of-00007.safetensors", | |
| "transformer.h.39.attn.c_attn.scales": "model-00004-of-00007.safetensors", | |
| "transformer.h.39.attn.c_attn.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.39.attn.c_proj.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.39.attn.c_proj.biases": "model-00004-of-00007.safetensors", | |
| "transformer.h.39.attn.c_proj.scales": "model-00004-of-00007.safetensors", | |
| "transformer.h.39.attn.c_proj.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.39.ln_1.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.39.ln_1.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.39.ln_2.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.39.ln_2.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.39.mlp.c_fc.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.39.mlp.c_fc.biases": "model-00004-of-00007.safetensors", | |
| "transformer.h.39.mlp.c_fc.scales": "model-00004-of-00007.safetensors", | |
| "transformer.h.39.mlp.c_fc.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.39.mlp.c_proj.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.39.mlp.c_proj.biases": "model-00004-of-00007.safetensors", | |
| "transformer.h.39.mlp.c_proj.scales": "model-00004-of-00007.safetensors", | |
| "transformer.h.39.mlp.c_proj.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.4.attn.c_attn.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.4.attn.c_attn.biases": "model-00001-of-00007.safetensors", | |
| "transformer.h.4.attn.c_attn.scales": "model-00001-of-00007.safetensors", | |
| "transformer.h.4.attn.c_attn.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.4.attn.c_proj.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.4.attn.c_proj.biases": "model-00001-of-00007.safetensors", | |
| "transformer.h.4.attn.c_proj.scales": "model-00001-of-00007.safetensors", | |
| "transformer.h.4.attn.c_proj.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.4.ln_1.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.4.ln_1.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.4.ln_2.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.4.ln_2.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.4.mlp.c_fc.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.4.mlp.c_fc.biases": "model-00001-of-00007.safetensors", | |
| "transformer.h.4.mlp.c_fc.scales": "model-00001-of-00007.safetensors", | |
| "transformer.h.4.mlp.c_fc.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.4.mlp.c_proj.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.4.mlp.c_proj.biases": "model-00001-of-00007.safetensors", | |
| "transformer.h.4.mlp.c_proj.scales": "model-00001-of-00007.safetensors", | |
| "transformer.h.4.mlp.c_proj.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.40.attn.c_attn.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.40.attn.c_attn.biases": "model-00004-of-00007.safetensors", | |
| "transformer.h.40.attn.c_attn.scales": "model-00004-of-00007.safetensors", | |
| "transformer.h.40.attn.c_attn.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.40.attn.c_proj.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.40.attn.c_proj.biases": "model-00004-of-00007.safetensors", | |
| "transformer.h.40.attn.c_proj.scales": "model-00004-of-00007.safetensors", | |
| "transformer.h.40.attn.c_proj.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.40.ln_1.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.40.ln_1.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.40.ln_2.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.40.ln_2.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.40.mlp.c_fc.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.40.mlp.c_fc.biases": "model-00004-of-00007.safetensors", | |
| "transformer.h.40.mlp.c_fc.scales": "model-00004-of-00007.safetensors", | |
| "transformer.h.40.mlp.c_fc.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.40.mlp.c_proj.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.40.mlp.c_proj.biases": "model-00004-of-00007.safetensors", | |
| "transformer.h.40.mlp.c_proj.scales": "model-00004-of-00007.safetensors", | |
| "transformer.h.40.mlp.c_proj.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.41.attn.c_attn.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.41.attn.c_attn.biases": "model-00004-of-00007.safetensors", | |
| "transformer.h.41.attn.c_attn.scales": "model-00004-of-00007.safetensors", | |
| "transformer.h.41.attn.c_attn.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.41.attn.c_proj.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.41.attn.c_proj.biases": "model-00004-of-00007.safetensors", | |
| "transformer.h.41.attn.c_proj.scales": "model-00004-of-00007.safetensors", | |
| "transformer.h.41.attn.c_proj.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.41.ln_1.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.41.ln_1.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.41.ln_2.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.41.ln_2.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.41.mlp.c_fc.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.41.mlp.c_fc.biases": "model-00004-of-00007.safetensors", | |
| "transformer.h.41.mlp.c_fc.scales": "model-00004-of-00007.safetensors", | |
| "transformer.h.41.mlp.c_fc.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.41.mlp.c_proj.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.41.mlp.c_proj.biases": "model-00004-of-00007.safetensors", | |
| "transformer.h.41.mlp.c_proj.scales": "model-00004-of-00007.safetensors", | |
| "transformer.h.41.mlp.c_proj.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.42.attn.c_attn.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.42.attn.c_attn.biases": "model-00004-of-00007.safetensors", | |
| "transformer.h.42.attn.c_attn.scales": "model-00004-of-00007.safetensors", | |
| "transformer.h.42.attn.c_attn.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.42.attn.c_proj.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.42.attn.c_proj.biases": "model-00004-of-00007.safetensors", | |
| "transformer.h.42.attn.c_proj.scales": "model-00004-of-00007.safetensors", | |
| "transformer.h.42.attn.c_proj.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.42.ln_1.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.42.ln_1.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.42.ln_2.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.42.ln_2.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.42.mlp.c_fc.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.42.mlp.c_fc.biases": "model-00004-of-00007.safetensors", | |
| "transformer.h.42.mlp.c_fc.scales": "model-00004-of-00007.safetensors", | |
| "transformer.h.42.mlp.c_fc.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.42.mlp.c_proj.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.42.mlp.c_proj.biases": "model-00004-of-00007.safetensors", | |
| "transformer.h.42.mlp.c_proj.scales": "model-00004-of-00007.safetensors", | |
| "transformer.h.42.mlp.c_proj.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.43.attn.c_attn.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.43.attn.c_attn.biases": "model-00004-of-00007.safetensors", | |
| "transformer.h.43.attn.c_attn.scales": "model-00004-of-00007.safetensors", | |
| "transformer.h.43.attn.c_attn.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.43.attn.c_proj.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.43.attn.c_proj.biases": "model-00004-of-00007.safetensors", | |
| "transformer.h.43.attn.c_proj.scales": "model-00004-of-00007.safetensors", | |
| "transformer.h.43.attn.c_proj.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.43.ln_1.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.43.ln_1.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.43.ln_2.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.43.ln_2.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.43.mlp.c_fc.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.43.mlp.c_fc.biases": "model-00004-of-00007.safetensors", | |
| "transformer.h.43.mlp.c_fc.scales": "model-00004-of-00007.safetensors", | |
| "transformer.h.43.mlp.c_fc.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.43.mlp.c_proj.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.43.mlp.c_proj.biases": "model-00004-of-00007.safetensors", | |
| "transformer.h.43.mlp.c_proj.scales": "model-00004-of-00007.safetensors", | |
| "transformer.h.43.mlp.c_proj.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.44.attn.c_attn.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.44.attn.c_attn.biases": "model-00004-of-00007.safetensors", | |
| "transformer.h.44.attn.c_attn.scales": "model-00004-of-00007.safetensors", | |
| "transformer.h.44.attn.c_attn.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.44.attn.c_proj.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.44.attn.c_proj.biases": "model-00004-of-00007.safetensors", | |
| "transformer.h.44.attn.c_proj.scales": "model-00004-of-00007.safetensors", | |
| "transformer.h.44.attn.c_proj.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.44.ln_1.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.44.ln_1.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.44.ln_2.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.44.ln_2.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.44.mlp.c_fc.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.44.mlp.c_fc.biases": "model-00004-of-00007.safetensors", | |
| "transformer.h.44.mlp.c_fc.scales": "model-00004-of-00007.safetensors", | |
| "transformer.h.44.mlp.c_fc.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.44.mlp.c_proj.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.44.mlp.c_proj.biases": "model-00004-of-00007.safetensors", | |
| "transformer.h.44.mlp.c_proj.scales": "model-00004-of-00007.safetensors", | |
| "transformer.h.44.mlp.c_proj.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.45.attn.c_attn.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.45.attn.c_attn.biases": "model-00004-of-00007.safetensors", | |
| "transformer.h.45.attn.c_attn.scales": "model-00004-of-00007.safetensors", | |
| "transformer.h.45.attn.c_attn.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.45.attn.c_proj.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.45.attn.c_proj.biases": "model-00004-of-00007.safetensors", | |
| "transformer.h.45.attn.c_proj.scales": "model-00004-of-00007.safetensors", | |
| "transformer.h.45.attn.c_proj.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.45.ln_1.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.45.ln_1.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.45.ln_2.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.45.ln_2.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.45.mlp.c_fc.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.45.mlp.c_fc.biases": "model-00004-of-00007.safetensors", | |
| "transformer.h.45.mlp.c_fc.scales": "model-00004-of-00007.safetensors", | |
| "transformer.h.45.mlp.c_fc.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.45.mlp.c_proj.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.45.mlp.c_proj.biases": "model-00004-of-00007.safetensors", | |
| "transformer.h.45.mlp.c_proj.scales": "model-00004-of-00007.safetensors", | |
| "transformer.h.45.mlp.c_proj.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.46.attn.c_attn.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.46.attn.c_attn.biases": "model-00004-of-00007.safetensors", | |
| "transformer.h.46.attn.c_attn.scales": "model-00004-of-00007.safetensors", | |
| "transformer.h.46.attn.c_attn.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.46.attn.c_proj.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.46.attn.c_proj.biases": "model-00004-of-00007.safetensors", | |
| "transformer.h.46.attn.c_proj.scales": "model-00004-of-00007.safetensors", | |
| "transformer.h.46.attn.c_proj.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.46.ln_1.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.46.ln_1.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.46.ln_2.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.46.ln_2.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.46.mlp.c_fc.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.46.mlp.c_fc.biases": "model-00004-of-00007.safetensors", | |
| "transformer.h.46.mlp.c_fc.scales": "model-00004-of-00007.safetensors", | |
| "transformer.h.46.mlp.c_fc.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.46.mlp.c_proj.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.46.mlp.c_proj.biases": "model-00004-of-00007.safetensors", | |
| "transformer.h.46.mlp.c_proj.scales": "model-00004-of-00007.safetensors", | |
| "transformer.h.46.mlp.c_proj.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.47.attn.c_attn.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.47.attn.c_attn.biases": "model-00004-of-00007.safetensors", | |
| "transformer.h.47.attn.c_attn.scales": "model-00004-of-00007.safetensors", | |
| "transformer.h.47.attn.c_attn.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.47.attn.c_proj.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.47.attn.c_proj.biases": "model-00004-of-00007.safetensors", | |
| "transformer.h.47.attn.c_proj.scales": "model-00004-of-00007.safetensors", | |
| "transformer.h.47.attn.c_proj.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.47.ln_1.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.47.ln_1.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.47.ln_2.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.47.ln_2.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.47.mlp.c_fc.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.47.mlp.c_fc.biases": "model-00004-of-00007.safetensors", | |
| "transformer.h.47.mlp.c_fc.scales": "model-00004-of-00007.safetensors", | |
| "transformer.h.47.mlp.c_fc.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.47.mlp.c_proj.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.47.mlp.c_proj.biases": "model-00004-of-00007.safetensors", | |
| "transformer.h.47.mlp.c_proj.scales": "model-00004-of-00007.safetensors", | |
| "transformer.h.47.mlp.c_proj.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.48.attn.c_attn.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.48.attn.c_attn.biases": "model-00004-of-00007.safetensors", | |
| "transformer.h.48.attn.c_attn.scales": "model-00004-of-00007.safetensors", | |
| "transformer.h.48.attn.c_attn.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.48.attn.c_proj.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.48.attn.c_proj.biases": "model-00004-of-00007.safetensors", | |
| "transformer.h.48.attn.c_proj.scales": "model-00004-of-00007.safetensors", | |
| "transformer.h.48.attn.c_proj.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.48.ln_1.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.48.ln_1.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.48.ln_2.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.48.ln_2.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.48.mlp.c_fc.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.48.mlp.c_fc.biases": "model-00004-of-00007.safetensors", | |
| "transformer.h.48.mlp.c_fc.scales": "model-00004-of-00007.safetensors", | |
| "transformer.h.48.mlp.c_fc.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.48.mlp.c_proj.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.48.mlp.c_proj.biases": "model-00004-of-00007.safetensors", | |
| "transformer.h.48.mlp.c_proj.scales": "model-00004-of-00007.safetensors", | |
| "transformer.h.48.mlp.c_proj.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.49.attn.c_attn.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.49.attn.c_attn.biases": "model-00004-of-00007.safetensors", | |
| "transformer.h.49.attn.c_attn.scales": "model-00004-of-00007.safetensors", | |
| "transformer.h.49.attn.c_attn.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.49.attn.c_proj.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.49.attn.c_proj.biases": "model-00004-of-00007.safetensors", | |
| "transformer.h.49.attn.c_proj.scales": "model-00004-of-00007.safetensors", | |
| "transformer.h.49.attn.c_proj.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.49.ln_1.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.49.ln_1.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.49.ln_2.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.49.ln_2.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.49.mlp.c_fc.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.49.mlp.c_fc.biases": "model-00004-of-00007.safetensors", | |
| "transformer.h.49.mlp.c_fc.scales": "model-00004-of-00007.safetensors", | |
| "transformer.h.49.mlp.c_fc.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.49.mlp.c_proj.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.49.mlp.c_proj.biases": "model-00004-of-00007.safetensors", | |
| "transformer.h.49.mlp.c_proj.scales": "model-00004-of-00007.safetensors", | |
| "transformer.h.49.mlp.c_proj.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.5.attn.c_attn.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.5.attn.c_attn.biases": "model-00001-of-00007.safetensors", | |
| "transformer.h.5.attn.c_attn.scales": "model-00001-of-00007.safetensors", | |
| "transformer.h.5.attn.c_attn.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.5.attn.c_proj.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.5.attn.c_proj.biases": "model-00001-of-00007.safetensors", | |
| "transformer.h.5.attn.c_proj.scales": "model-00001-of-00007.safetensors", | |
| "transformer.h.5.attn.c_proj.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.5.ln_1.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.5.ln_1.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.5.ln_2.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.5.ln_2.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.5.mlp.c_fc.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.5.mlp.c_fc.biases": "model-00001-of-00007.safetensors", | |
| "transformer.h.5.mlp.c_fc.scales": "model-00001-of-00007.safetensors", | |
| "transformer.h.5.mlp.c_fc.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.5.mlp.c_proj.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.5.mlp.c_proj.biases": "model-00001-of-00007.safetensors", | |
| "transformer.h.5.mlp.c_proj.scales": "model-00001-of-00007.safetensors", | |
| "transformer.h.5.mlp.c_proj.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.50.attn.c_attn.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.50.attn.c_attn.biases": "model-00004-of-00007.safetensors", | |
| "transformer.h.50.attn.c_attn.scales": "model-00004-of-00007.safetensors", | |
| "transformer.h.50.attn.c_attn.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.50.attn.c_proj.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.50.attn.c_proj.biases": "model-00004-of-00007.safetensors", | |
| "transformer.h.50.attn.c_proj.scales": "model-00004-of-00007.safetensors", | |
| "transformer.h.50.attn.c_proj.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.50.ln_1.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.50.ln_1.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.50.ln_2.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.50.ln_2.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.50.mlp.c_fc.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.50.mlp.c_fc.biases": "model-00004-of-00007.safetensors", | |
| "transformer.h.50.mlp.c_fc.scales": "model-00004-of-00007.safetensors", | |
| "transformer.h.50.mlp.c_fc.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.50.mlp.c_proj.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.50.mlp.c_proj.biases": "model-00004-of-00007.safetensors", | |
| "transformer.h.50.mlp.c_proj.scales": "model-00004-of-00007.safetensors", | |
| "transformer.h.50.mlp.c_proj.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.51.attn.c_attn.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.51.attn.c_attn.biases": "model-00004-of-00007.safetensors", | |
| "transformer.h.51.attn.c_attn.scales": "model-00004-of-00007.safetensors", | |
| "transformer.h.51.attn.c_attn.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.51.attn.c_proj.bias": "model-00004-of-00007.safetensors", | |
| "transformer.h.51.attn.c_proj.biases": "model-00004-of-00007.safetensors", | |
| "transformer.h.51.attn.c_proj.scales": "model-00004-of-00007.safetensors", | |
| "transformer.h.51.attn.c_proj.weight": "model-00004-of-00007.safetensors", | |
| "transformer.h.51.ln_1.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.51.ln_1.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.51.ln_2.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.51.ln_2.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.51.mlp.c_fc.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.51.mlp.c_fc.biases": "model-00005-of-00007.safetensors", | |
| "transformer.h.51.mlp.c_fc.scales": "model-00005-of-00007.safetensors", | |
| "transformer.h.51.mlp.c_fc.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.51.mlp.c_proj.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.51.mlp.c_proj.biases": "model-00005-of-00007.safetensors", | |
| "transformer.h.51.mlp.c_proj.scales": "model-00005-of-00007.safetensors", | |
| "transformer.h.51.mlp.c_proj.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.52.attn.c_attn.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.52.attn.c_attn.biases": "model-00005-of-00007.safetensors", | |
| "transformer.h.52.attn.c_attn.scales": "model-00005-of-00007.safetensors", | |
| "transformer.h.52.attn.c_attn.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.52.attn.c_proj.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.52.attn.c_proj.biases": "model-00005-of-00007.safetensors", | |
| "transformer.h.52.attn.c_proj.scales": "model-00005-of-00007.safetensors", | |
| "transformer.h.52.attn.c_proj.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.52.ln_1.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.52.ln_1.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.52.ln_2.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.52.ln_2.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.52.mlp.c_fc.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.52.mlp.c_fc.biases": "model-00005-of-00007.safetensors", | |
| "transformer.h.52.mlp.c_fc.scales": "model-00005-of-00007.safetensors", | |
| "transformer.h.52.mlp.c_fc.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.52.mlp.c_proj.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.52.mlp.c_proj.biases": "model-00005-of-00007.safetensors", | |
| "transformer.h.52.mlp.c_proj.scales": "model-00005-of-00007.safetensors", | |
| "transformer.h.52.mlp.c_proj.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.53.attn.c_attn.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.53.attn.c_attn.biases": "model-00005-of-00007.safetensors", | |
| "transformer.h.53.attn.c_attn.scales": "model-00005-of-00007.safetensors", | |
| "transformer.h.53.attn.c_attn.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.53.attn.c_proj.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.53.attn.c_proj.biases": "model-00005-of-00007.safetensors", | |
| "transformer.h.53.attn.c_proj.scales": "model-00005-of-00007.safetensors", | |
| "transformer.h.53.attn.c_proj.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.53.ln_1.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.53.ln_1.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.53.ln_2.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.53.ln_2.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.53.mlp.c_fc.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.53.mlp.c_fc.biases": "model-00005-of-00007.safetensors", | |
| "transformer.h.53.mlp.c_fc.scales": "model-00005-of-00007.safetensors", | |
| "transformer.h.53.mlp.c_fc.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.53.mlp.c_proj.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.53.mlp.c_proj.biases": "model-00005-of-00007.safetensors", | |
| "transformer.h.53.mlp.c_proj.scales": "model-00005-of-00007.safetensors", | |
| "transformer.h.53.mlp.c_proj.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.54.attn.c_attn.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.54.attn.c_attn.biases": "model-00005-of-00007.safetensors", | |
| "transformer.h.54.attn.c_attn.scales": "model-00005-of-00007.safetensors", | |
| "transformer.h.54.attn.c_attn.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.54.attn.c_proj.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.54.attn.c_proj.biases": "model-00005-of-00007.safetensors", | |
| "transformer.h.54.attn.c_proj.scales": "model-00005-of-00007.safetensors", | |
| "transformer.h.54.attn.c_proj.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.54.ln_1.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.54.ln_1.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.54.ln_2.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.54.ln_2.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.54.mlp.c_fc.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.54.mlp.c_fc.biases": "model-00005-of-00007.safetensors", | |
| "transformer.h.54.mlp.c_fc.scales": "model-00005-of-00007.safetensors", | |
| "transformer.h.54.mlp.c_fc.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.54.mlp.c_proj.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.54.mlp.c_proj.biases": "model-00005-of-00007.safetensors", | |
| "transformer.h.54.mlp.c_proj.scales": "model-00005-of-00007.safetensors", | |
| "transformer.h.54.mlp.c_proj.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.55.attn.c_attn.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.55.attn.c_attn.biases": "model-00005-of-00007.safetensors", | |
| "transformer.h.55.attn.c_attn.scales": "model-00005-of-00007.safetensors", | |
| "transformer.h.55.attn.c_attn.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.55.attn.c_proj.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.55.attn.c_proj.biases": "model-00005-of-00007.safetensors", | |
| "transformer.h.55.attn.c_proj.scales": "model-00005-of-00007.safetensors", | |
| "transformer.h.55.attn.c_proj.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.55.ln_1.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.55.ln_1.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.55.ln_2.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.55.ln_2.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.55.mlp.c_fc.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.55.mlp.c_fc.biases": "model-00005-of-00007.safetensors", | |
| "transformer.h.55.mlp.c_fc.scales": "model-00005-of-00007.safetensors", | |
| "transformer.h.55.mlp.c_fc.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.55.mlp.c_proj.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.55.mlp.c_proj.biases": "model-00005-of-00007.safetensors", | |
| "transformer.h.55.mlp.c_proj.scales": "model-00005-of-00007.safetensors", | |
| "transformer.h.55.mlp.c_proj.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.56.attn.c_attn.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.56.attn.c_attn.biases": "model-00005-of-00007.safetensors", | |
| "transformer.h.56.attn.c_attn.scales": "model-00005-of-00007.safetensors", | |
| "transformer.h.56.attn.c_attn.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.56.attn.c_proj.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.56.attn.c_proj.biases": "model-00005-of-00007.safetensors", | |
| "transformer.h.56.attn.c_proj.scales": "model-00005-of-00007.safetensors", | |
| "transformer.h.56.attn.c_proj.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.56.ln_1.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.56.ln_1.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.56.ln_2.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.56.ln_2.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.56.mlp.c_fc.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.56.mlp.c_fc.biases": "model-00005-of-00007.safetensors", | |
| "transformer.h.56.mlp.c_fc.scales": "model-00005-of-00007.safetensors", | |
| "transformer.h.56.mlp.c_fc.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.56.mlp.c_proj.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.56.mlp.c_proj.biases": "model-00005-of-00007.safetensors", | |
| "transformer.h.56.mlp.c_proj.scales": "model-00005-of-00007.safetensors", | |
| "transformer.h.56.mlp.c_proj.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.57.attn.c_attn.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.57.attn.c_attn.biases": "model-00005-of-00007.safetensors", | |
| "transformer.h.57.attn.c_attn.scales": "model-00005-of-00007.safetensors", | |
| "transformer.h.57.attn.c_attn.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.57.attn.c_proj.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.57.attn.c_proj.biases": "model-00005-of-00007.safetensors", | |
| "transformer.h.57.attn.c_proj.scales": "model-00005-of-00007.safetensors", | |
| "transformer.h.57.attn.c_proj.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.57.ln_1.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.57.ln_1.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.57.ln_2.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.57.ln_2.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.57.mlp.c_fc.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.57.mlp.c_fc.biases": "model-00005-of-00007.safetensors", | |
| "transformer.h.57.mlp.c_fc.scales": "model-00005-of-00007.safetensors", | |
| "transformer.h.57.mlp.c_fc.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.57.mlp.c_proj.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.57.mlp.c_proj.biases": "model-00005-of-00007.safetensors", | |
| "transformer.h.57.mlp.c_proj.scales": "model-00005-of-00007.safetensors", | |
| "transformer.h.57.mlp.c_proj.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.58.attn.c_attn.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.58.attn.c_attn.biases": "model-00005-of-00007.safetensors", | |
| "transformer.h.58.attn.c_attn.scales": "model-00005-of-00007.safetensors", | |
| "transformer.h.58.attn.c_attn.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.58.attn.c_proj.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.58.attn.c_proj.biases": "model-00005-of-00007.safetensors", | |
| "transformer.h.58.attn.c_proj.scales": "model-00005-of-00007.safetensors", | |
| "transformer.h.58.attn.c_proj.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.58.ln_1.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.58.ln_1.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.58.ln_2.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.58.ln_2.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.58.mlp.c_fc.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.58.mlp.c_fc.biases": "model-00005-of-00007.safetensors", | |
| "transformer.h.58.mlp.c_fc.scales": "model-00005-of-00007.safetensors", | |
| "transformer.h.58.mlp.c_fc.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.58.mlp.c_proj.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.58.mlp.c_proj.biases": "model-00005-of-00007.safetensors", | |
| "transformer.h.58.mlp.c_proj.scales": "model-00005-of-00007.safetensors", | |
| "transformer.h.58.mlp.c_proj.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.59.attn.c_attn.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.59.attn.c_attn.biases": "model-00005-of-00007.safetensors", | |
| "transformer.h.59.attn.c_attn.scales": "model-00005-of-00007.safetensors", | |
| "transformer.h.59.attn.c_attn.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.59.attn.c_proj.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.59.attn.c_proj.biases": "model-00005-of-00007.safetensors", | |
| "transformer.h.59.attn.c_proj.scales": "model-00005-of-00007.safetensors", | |
| "transformer.h.59.attn.c_proj.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.59.ln_1.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.59.ln_1.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.59.ln_2.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.59.ln_2.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.59.mlp.c_fc.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.59.mlp.c_fc.biases": "model-00005-of-00007.safetensors", | |
| "transformer.h.59.mlp.c_fc.scales": "model-00005-of-00007.safetensors", | |
| "transformer.h.59.mlp.c_fc.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.59.mlp.c_proj.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.59.mlp.c_proj.biases": "model-00005-of-00007.safetensors", | |
| "transformer.h.59.mlp.c_proj.scales": "model-00005-of-00007.safetensors", | |
| "transformer.h.59.mlp.c_proj.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.6.attn.c_attn.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.6.attn.c_attn.biases": "model-00001-of-00007.safetensors", | |
| "transformer.h.6.attn.c_attn.scales": "model-00001-of-00007.safetensors", | |
| "transformer.h.6.attn.c_attn.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.6.attn.c_proj.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.6.attn.c_proj.biases": "model-00001-of-00007.safetensors", | |
| "transformer.h.6.attn.c_proj.scales": "model-00001-of-00007.safetensors", | |
| "transformer.h.6.attn.c_proj.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.6.ln_1.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.6.ln_1.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.6.ln_2.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.6.ln_2.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.6.mlp.c_fc.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.6.mlp.c_fc.biases": "model-00001-of-00007.safetensors", | |
| "transformer.h.6.mlp.c_fc.scales": "model-00001-of-00007.safetensors", | |
| "transformer.h.6.mlp.c_fc.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.6.mlp.c_proj.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.6.mlp.c_proj.biases": "model-00001-of-00007.safetensors", | |
| "transformer.h.6.mlp.c_proj.scales": "model-00001-of-00007.safetensors", | |
| "transformer.h.6.mlp.c_proj.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.60.attn.c_attn.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.60.attn.c_attn.biases": "model-00005-of-00007.safetensors", | |
| "transformer.h.60.attn.c_attn.scales": "model-00005-of-00007.safetensors", | |
| "transformer.h.60.attn.c_attn.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.60.attn.c_proj.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.60.attn.c_proj.biases": "model-00005-of-00007.safetensors", | |
| "transformer.h.60.attn.c_proj.scales": "model-00005-of-00007.safetensors", | |
| "transformer.h.60.attn.c_proj.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.60.ln_1.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.60.ln_1.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.60.ln_2.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.60.ln_2.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.60.mlp.c_fc.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.60.mlp.c_fc.biases": "model-00005-of-00007.safetensors", | |
| "transformer.h.60.mlp.c_fc.scales": "model-00005-of-00007.safetensors", | |
| "transformer.h.60.mlp.c_fc.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.60.mlp.c_proj.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.60.mlp.c_proj.biases": "model-00005-of-00007.safetensors", | |
| "transformer.h.60.mlp.c_proj.scales": "model-00005-of-00007.safetensors", | |
| "transformer.h.60.mlp.c_proj.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.61.attn.c_attn.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.61.attn.c_attn.biases": "model-00005-of-00007.safetensors", | |
| "transformer.h.61.attn.c_attn.scales": "model-00005-of-00007.safetensors", | |
| "transformer.h.61.attn.c_attn.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.61.attn.c_proj.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.61.attn.c_proj.biases": "model-00005-of-00007.safetensors", | |
| "transformer.h.61.attn.c_proj.scales": "model-00005-of-00007.safetensors", | |
| "transformer.h.61.attn.c_proj.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.61.ln_1.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.61.ln_1.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.61.ln_2.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.61.ln_2.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.61.mlp.c_fc.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.61.mlp.c_fc.biases": "model-00005-of-00007.safetensors", | |
| "transformer.h.61.mlp.c_fc.scales": "model-00005-of-00007.safetensors", | |
| "transformer.h.61.mlp.c_fc.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.61.mlp.c_proj.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.61.mlp.c_proj.biases": "model-00005-of-00007.safetensors", | |
| "transformer.h.61.mlp.c_proj.scales": "model-00005-of-00007.safetensors", | |
| "transformer.h.61.mlp.c_proj.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.62.attn.c_attn.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.62.attn.c_attn.biases": "model-00005-of-00007.safetensors", | |
| "transformer.h.62.attn.c_attn.scales": "model-00005-of-00007.safetensors", | |
| "transformer.h.62.attn.c_attn.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.62.attn.c_proj.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.62.attn.c_proj.biases": "model-00005-of-00007.safetensors", | |
| "transformer.h.62.attn.c_proj.scales": "model-00005-of-00007.safetensors", | |
| "transformer.h.62.attn.c_proj.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.62.ln_1.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.62.ln_1.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.62.ln_2.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.62.ln_2.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.62.mlp.c_fc.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.62.mlp.c_fc.biases": "model-00005-of-00007.safetensors", | |
| "transformer.h.62.mlp.c_fc.scales": "model-00005-of-00007.safetensors", | |
| "transformer.h.62.mlp.c_fc.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.62.mlp.c_proj.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.62.mlp.c_proj.biases": "model-00005-of-00007.safetensors", | |
| "transformer.h.62.mlp.c_proj.scales": "model-00005-of-00007.safetensors", | |
| "transformer.h.62.mlp.c_proj.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.63.attn.c_attn.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.63.attn.c_attn.biases": "model-00005-of-00007.safetensors", | |
| "transformer.h.63.attn.c_attn.scales": "model-00005-of-00007.safetensors", | |
| "transformer.h.63.attn.c_attn.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.63.attn.c_proj.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.63.attn.c_proj.biases": "model-00005-of-00007.safetensors", | |
| "transformer.h.63.attn.c_proj.scales": "model-00005-of-00007.safetensors", | |
| "transformer.h.63.attn.c_proj.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.63.ln_1.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.63.ln_1.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.63.ln_2.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.63.ln_2.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.63.mlp.c_fc.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.63.mlp.c_fc.biases": "model-00005-of-00007.safetensors", | |
| "transformer.h.63.mlp.c_fc.scales": "model-00005-of-00007.safetensors", | |
| "transformer.h.63.mlp.c_fc.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.63.mlp.c_proj.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.63.mlp.c_proj.biases": "model-00005-of-00007.safetensors", | |
| "transformer.h.63.mlp.c_proj.scales": "model-00005-of-00007.safetensors", | |
| "transformer.h.63.mlp.c_proj.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.64.attn.c_attn.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.64.attn.c_attn.biases": "model-00005-of-00007.safetensors", | |
| "transformer.h.64.attn.c_attn.scales": "model-00005-of-00007.safetensors", | |
| "transformer.h.64.attn.c_attn.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.64.attn.c_proj.bias": "model-00005-of-00007.safetensors", | |
| "transformer.h.64.attn.c_proj.biases": "model-00005-of-00007.safetensors", | |
| "transformer.h.64.attn.c_proj.scales": "model-00005-of-00007.safetensors", | |
| "transformer.h.64.attn.c_proj.weight": "model-00005-of-00007.safetensors", | |
| "transformer.h.64.ln_1.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.64.ln_1.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.64.ln_2.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.64.ln_2.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.64.mlp.c_fc.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.64.mlp.c_fc.biases": "model-00006-of-00007.safetensors", | |
| "transformer.h.64.mlp.c_fc.scales": "model-00006-of-00007.safetensors", | |
| "transformer.h.64.mlp.c_fc.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.64.mlp.c_proj.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.64.mlp.c_proj.biases": "model-00006-of-00007.safetensors", | |
| "transformer.h.64.mlp.c_proj.scales": "model-00006-of-00007.safetensors", | |
| "transformer.h.64.mlp.c_proj.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.65.attn.c_attn.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.65.attn.c_attn.biases": "model-00006-of-00007.safetensors", | |
| "transformer.h.65.attn.c_attn.scales": "model-00006-of-00007.safetensors", | |
| "transformer.h.65.attn.c_attn.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.65.attn.c_proj.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.65.attn.c_proj.biases": "model-00006-of-00007.safetensors", | |
| "transformer.h.65.attn.c_proj.scales": "model-00006-of-00007.safetensors", | |
| "transformer.h.65.attn.c_proj.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.65.ln_1.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.65.ln_1.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.65.ln_2.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.65.ln_2.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.65.mlp.c_fc.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.65.mlp.c_fc.biases": "model-00006-of-00007.safetensors", | |
| "transformer.h.65.mlp.c_fc.scales": "model-00006-of-00007.safetensors", | |
| "transformer.h.65.mlp.c_fc.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.65.mlp.c_proj.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.65.mlp.c_proj.biases": "model-00006-of-00007.safetensors", | |
| "transformer.h.65.mlp.c_proj.scales": "model-00006-of-00007.safetensors", | |
| "transformer.h.65.mlp.c_proj.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.66.attn.c_attn.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.66.attn.c_attn.biases": "model-00006-of-00007.safetensors", | |
| "transformer.h.66.attn.c_attn.scales": "model-00006-of-00007.safetensors", | |
| "transformer.h.66.attn.c_attn.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.66.attn.c_proj.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.66.attn.c_proj.biases": "model-00006-of-00007.safetensors", | |
| "transformer.h.66.attn.c_proj.scales": "model-00006-of-00007.safetensors", | |
| "transformer.h.66.attn.c_proj.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.66.ln_1.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.66.ln_1.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.66.ln_2.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.66.ln_2.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.66.mlp.c_fc.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.66.mlp.c_fc.biases": "model-00006-of-00007.safetensors", | |
| "transformer.h.66.mlp.c_fc.scales": "model-00006-of-00007.safetensors", | |
| "transformer.h.66.mlp.c_fc.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.66.mlp.c_proj.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.66.mlp.c_proj.biases": "model-00006-of-00007.safetensors", | |
| "transformer.h.66.mlp.c_proj.scales": "model-00006-of-00007.safetensors", | |
| "transformer.h.66.mlp.c_proj.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.67.attn.c_attn.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.67.attn.c_attn.biases": "model-00006-of-00007.safetensors", | |
| "transformer.h.67.attn.c_attn.scales": "model-00006-of-00007.safetensors", | |
| "transformer.h.67.attn.c_attn.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.67.attn.c_proj.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.67.attn.c_proj.biases": "model-00006-of-00007.safetensors", | |
| "transformer.h.67.attn.c_proj.scales": "model-00006-of-00007.safetensors", | |
| "transformer.h.67.attn.c_proj.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.67.ln_1.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.67.ln_1.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.67.ln_2.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.67.ln_2.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.67.mlp.c_fc.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.67.mlp.c_fc.biases": "model-00006-of-00007.safetensors", | |
| "transformer.h.67.mlp.c_fc.scales": "model-00006-of-00007.safetensors", | |
| "transformer.h.67.mlp.c_fc.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.67.mlp.c_proj.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.67.mlp.c_proj.biases": "model-00006-of-00007.safetensors", | |
| "transformer.h.67.mlp.c_proj.scales": "model-00006-of-00007.safetensors", | |
| "transformer.h.67.mlp.c_proj.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.68.attn.c_attn.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.68.attn.c_attn.biases": "model-00006-of-00007.safetensors", | |
| "transformer.h.68.attn.c_attn.scales": "model-00006-of-00007.safetensors", | |
| "transformer.h.68.attn.c_attn.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.68.attn.c_proj.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.68.attn.c_proj.biases": "model-00006-of-00007.safetensors", | |
| "transformer.h.68.attn.c_proj.scales": "model-00006-of-00007.safetensors", | |
| "transformer.h.68.attn.c_proj.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.68.ln_1.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.68.ln_1.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.68.ln_2.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.68.ln_2.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.68.mlp.c_fc.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.68.mlp.c_fc.biases": "model-00006-of-00007.safetensors", | |
| "transformer.h.68.mlp.c_fc.scales": "model-00006-of-00007.safetensors", | |
| "transformer.h.68.mlp.c_fc.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.68.mlp.c_proj.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.68.mlp.c_proj.biases": "model-00006-of-00007.safetensors", | |
| "transformer.h.68.mlp.c_proj.scales": "model-00006-of-00007.safetensors", | |
| "transformer.h.68.mlp.c_proj.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.69.attn.c_attn.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.69.attn.c_attn.biases": "model-00006-of-00007.safetensors", | |
| "transformer.h.69.attn.c_attn.scales": "model-00006-of-00007.safetensors", | |
| "transformer.h.69.attn.c_attn.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.69.attn.c_proj.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.69.attn.c_proj.biases": "model-00006-of-00007.safetensors", | |
| "transformer.h.69.attn.c_proj.scales": "model-00006-of-00007.safetensors", | |
| "transformer.h.69.attn.c_proj.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.69.ln_1.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.69.ln_1.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.69.ln_2.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.69.ln_2.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.69.mlp.c_fc.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.69.mlp.c_fc.biases": "model-00006-of-00007.safetensors", | |
| "transformer.h.69.mlp.c_fc.scales": "model-00006-of-00007.safetensors", | |
| "transformer.h.69.mlp.c_fc.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.69.mlp.c_proj.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.69.mlp.c_proj.biases": "model-00006-of-00007.safetensors", | |
| "transformer.h.69.mlp.c_proj.scales": "model-00006-of-00007.safetensors", | |
| "transformer.h.69.mlp.c_proj.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.7.attn.c_attn.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.7.attn.c_attn.biases": "model-00001-of-00007.safetensors", | |
| "transformer.h.7.attn.c_attn.scales": "model-00001-of-00007.safetensors", | |
| "transformer.h.7.attn.c_attn.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.7.attn.c_proj.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.7.attn.c_proj.biases": "model-00001-of-00007.safetensors", | |
| "transformer.h.7.attn.c_proj.scales": "model-00001-of-00007.safetensors", | |
| "transformer.h.7.attn.c_proj.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.7.ln_1.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.7.ln_1.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.7.ln_2.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.7.ln_2.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.7.mlp.c_fc.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.7.mlp.c_fc.biases": "model-00001-of-00007.safetensors", | |
| "transformer.h.7.mlp.c_fc.scales": "model-00001-of-00007.safetensors", | |
| "transformer.h.7.mlp.c_fc.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.7.mlp.c_proj.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.7.mlp.c_proj.biases": "model-00001-of-00007.safetensors", | |
| "transformer.h.7.mlp.c_proj.scales": "model-00001-of-00007.safetensors", | |
| "transformer.h.7.mlp.c_proj.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.70.attn.c_attn.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.70.attn.c_attn.biases": "model-00006-of-00007.safetensors", | |
| "transformer.h.70.attn.c_attn.scales": "model-00006-of-00007.safetensors", | |
| "transformer.h.70.attn.c_attn.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.70.attn.c_proj.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.70.attn.c_proj.biases": "model-00006-of-00007.safetensors", | |
| "transformer.h.70.attn.c_proj.scales": "model-00006-of-00007.safetensors", | |
| "transformer.h.70.attn.c_proj.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.70.ln_1.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.70.ln_1.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.70.ln_2.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.70.ln_2.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.70.mlp.c_fc.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.70.mlp.c_fc.biases": "model-00006-of-00007.safetensors", | |
| "transformer.h.70.mlp.c_fc.scales": "model-00006-of-00007.safetensors", | |
| "transformer.h.70.mlp.c_fc.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.70.mlp.c_proj.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.70.mlp.c_proj.biases": "model-00006-of-00007.safetensors", | |
| "transformer.h.70.mlp.c_proj.scales": "model-00006-of-00007.safetensors", | |
| "transformer.h.70.mlp.c_proj.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.71.attn.c_attn.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.71.attn.c_attn.biases": "model-00006-of-00007.safetensors", | |
| "transformer.h.71.attn.c_attn.scales": "model-00006-of-00007.safetensors", | |
| "transformer.h.71.attn.c_attn.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.71.attn.c_proj.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.71.attn.c_proj.biases": "model-00006-of-00007.safetensors", | |
| "transformer.h.71.attn.c_proj.scales": "model-00006-of-00007.safetensors", | |
| "transformer.h.71.attn.c_proj.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.71.ln_1.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.71.ln_1.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.71.ln_2.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.71.ln_2.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.71.mlp.c_fc.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.71.mlp.c_fc.biases": "model-00006-of-00007.safetensors", | |
| "transformer.h.71.mlp.c_fc.scales": "model-00006-of-00007.safetensors", | |
| "transformer.h.71.mlp.c_fc.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.71.mlp.c_proj.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.71.mlp.c_proj.biases": "model-00006-of-00007.safetensors", | |
| "transformer.h.71.mlp.c_proj.scales": "model-00006-of-00007.safetensors", | |
| "transformer.h.71.mlp.c_proj.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.72.attn.c_attn.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.72.attn.c_attn.biases": "model-00006-of-00007.safetensors", | |
| "transformer.h.72.attn.c_attn.scales": "model-00006-of-00007.safetensors", | |
| "transformer.h.72.attn.c_attn.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.72.attn.c_proj.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.72.attn.c_proj.biases": "model-00006-of-00007.safetensors", | |
| "transformer.h.72.attn.c_proj.scales": "model-00006-of-00007.safetensors", | |
| "transformer.h.72.attn.c_proj.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.72.ln_1.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.72.ln_1.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.72.ln_2.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.72.ln_2.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.72.mlp.c_fc.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.72.mlp.c_fc.biases": "model-00006-of-00007.safetensors", | |
| "transformer.h.72.mlp.c_fc.scales": "model-00006-of-00007.safetensors", | |
| "transformer.h.72.mlp.c_fc.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.72.mlp.c_proj.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.72.mlp.c_proj.biases": "model-00006-of-00007.safetensors", | |
| "transformer.h.72.mlp.c_proj.scales": "model-00006-of-00007.safetensors", | |
| "transformer.h.72.mlp.c_proj.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.73.attn.c_attn.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.73.attn.c_attn.biases": "model-00006-of-00007.safetensors", | |
| "transformer.h.73.attn.c_attn.scales": "model-00006-of-00007.safetensors", | |
| "transformer.h.73.attn.c_attn.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.73.attn.c_proj.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.73.attn.c_proj.biases": "model-00006-of-00007.safetensors", | |
| "transformer.h.73.attn.c_proj.scales": "model-00006-of-00007.safetensors", | |
| "transformer.h.73.attn.c_proj.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.73.ln_1.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.73.ln_1.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.73.ln_2.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.73.ln_2.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.73.mlp.c_fc.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.73.mlp.c_fc.biases": "model-00006-of-00007.safetensors", | |
| "transformer.h.73.mlp.c_fc.scales": "model-00006-of-00007.safetensors", | |
| "transformer.h.73.mlp.c_fc.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.73.mlp.c_proj.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.73.mlp.c_proj.biases": "model-00006-of-00007.safetensors", | |
| "transformer.h.73.mlp.c_proj.scales": "model-00006-of-00007.safetensors", | |
| "transformer.h.73.mlp.c_proj.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.74.attn.c_attn.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.74.attn.c_attn.biases": "model-00006-of-00007.safetensors", | |
| "transformer.h.74.attn.c_attn.scales": "model-00006-of-00007.safetensors", | |
| "transformer.h.74.attn.c_attn.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.74.attn.c_proj.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.74.attn.c_proj.biases": "model-00006-of-00007.safetensors", | |
| "transformer.h.74.attn.c_proj.scales": "model-00006-of-00007.safetensors", | |
| "transformer.h.74.attn.c_proj.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.74.ln_1.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.74.ln_1.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.74.ln_2.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.74.ln_2.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.74.mlp.c_fc.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.74.mlp.c_fc.biases": "model-00006-of-00007.safetensors", | |
| "transformer.h.74.mlp.c_fc.scales": "model-00006-of-00007.safetensors", | |
| "transformer.h.74.mlp.c_fc.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.74.mlp.c_proj.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.74.mlp.c_proj.biases": "model-00006-of-00007.safetensors", | |
| "transformer.h.74.mlp.c_proj.scales": "model-00006-of-00007.safetensors", | |
| "transformer.h.74.mlp.c_proj.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.75.attn.c_attn.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.75.attn.c_attn.biases": "model-00006-of-00007.safetensors", | |
| "transformer.h.75.attn.c_attn.scales": "model-00006-of-00007.safetensors", | |
| "transformer.h.75.attn.c_attn.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.75.attn.c_proj.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.75.attn.c_proj.biases": "model-00006-of-00007.safetensors", | |
| "transformer.h.75.attn.c_proj.scales": "model-00006-of-00007.safetensors", | |
| "transformer.h.75.attn.c_proj.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.75.ln_1.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.75.ln_1.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.75.ln_2.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.75.ln_2.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.75.mlp.c_fc.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.75.mlp.c_fc.biases": "model-00006-of-00007.safetensors", | |
| "transformer.h.75.mlp.c_fc.scales": "model-00006-of-00007.safetensors", | |
| "transformer.h.75.mlp.c_fc.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.75.mlp.c_proj.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.75.mlp.c_proj.biases": "model-00006-of-00007.safetensors", | |
| "transformer.h.75.mlp.c_proj.scales": "model-00006-of-00007.safetensors", | |
| "transformer.h.75.mlp.c_proj.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.76.attn.c_attn.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.76.attn.c_attn.biases": "model-00006-of-00007.safetensors", | |
| "transformer.h.76.attn.c_attn.scales": "model-00006-of-00007.safetensors", | |
| "transformer.h.76.attn.c_attn.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.76.attn.c_proj.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.76.attn.c_proj.biases": "model-00006-of-00007.safetensors", | |
| "transformer.h.76.attn.c_proj.scales": "model-00006-of-00007.safetensors", | |
| "transformer.h.76.attn.c_proj.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.76.ln_1.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.76.ln_1.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.76.ln_2.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.76.ln_2.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.76.mlp.c_fc.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.76.mlp.c_fc.biases": "model-00006-of-00007.safetensors", | |
| "transformer.h.76.mlp.c_fc.scales": "model-00006-of-00007.safetensors", | |
| "transformer.h.76.mlp.c_fc.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.76.mlp.c_proj.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.76.mlp.c_proj.biases": "model-00006-of-00007.safetensors", | |
| "transformer.h.76.mlp.c_proj.scales": "model-00006-of-00007.safetensors", | |
| "transformer.h.76.mlp.c_proj.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.77.attn.c_attn.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.77.attn.c_attn.biases": "model-00006-of-00007.safetensors", | |
| "transformer.h.77.attn.c_attn.scales": "model-00006-of-00007.safetensors", | |
| "transformer.h.77.attn.c_attn.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.77.attn.c_proj.bias": "model-00006-of-00007.safetensors", | |
| "transformer.h.77.attn.c_proj.biases": "model-00006-of-00007.safetensors", | |
| "transformer.h.77.attn.c_proj.scales": "model-00006-of-00007.safetensors", | |
| "transformer.h.77.attn.c_proj.weight": "model-00006-of-00007.safetensors", | |
| "transformer.h.77.ln_1.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.77.ln_1.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.77.ln_2.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.77.ln_2.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.77.mlp.c_fc.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.77.mlp.c_fc.biases": "model-00007-of-00007.safetensors", | |
| "transformer.h.77.mlp.c_fc.scales": "model-00007-of-00007.safetensors", | |
| "transformer.h.77.mlp.c_fc.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.77.mlp.c_proj.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.77.mlp.c_proj.biases": "model-00007-of-00007.safetensors", | |
| "transformer.h.77.mlp.c_proj.scales": "model-00007-of-00007.safetensors", | |
| "transformer.h.77.mlp.c_proj.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.78.attn.c_attn.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.78.attn.c_attn.biases": "model-00007-of-00007.safetensors", | |
| "transformer.h.78.attn.c_attn.scales": "model-00007-of-00007.safetensors", | |
| "transformer.h.78.attn.c_attn.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.78.attn.c_proj.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.78.attn.c_proj.biases": "model-00007-of-00007.safetensors", | |
| "transformer.h.78.attn.c_proj.scales": "model-00007-of-00007.safetensors", | |
| "transformer.h.78.attn.c_proj.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.78.ln_1.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.78.ln_1.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.78.ln_2.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.78.ln_2.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.78.mlp.c_fc.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.78.mlp.c_fc.biases": "model-00007-of-00007.safetensors", | |
| "transformer.h.78.mlp.c_fc.scales": "model-00007-of-00007.safetensors", | |
| "transformer.h.78.mlp.c_fc.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.78.mlp.c_proj.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.78.mlp.c_proj.biases": "model-00007-of-00007.safetensors", | |
| "transformer.h.78.mlp.c_proj.scales": "model-00007-of-00007.safetensors", | |
| "transformer.h.78.mlp.c_proj.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.79.attn.c_attn.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.79.attn.c_attn.biases": "model-00007-of-00007.safetensors", | |
| "transformer.h.79.attn.c_attn.scales": "model-00007-of-00007.safetensors", | |
| "transformer.h.79.attn.c_attn.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.79.attn.c_proj.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.79.attn.c_proj.biases": "model-00007-of-00007.safetensors", | |
| "transformer.h.79.attn.c_proj.scales": "model-00007-of-00007.safetensors", | |
| "transformer.h.79.attn.c_proj.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.79.ln_1.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.79.ln_1.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.79.ln_2.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.79.ln_2.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.79.mlp.c_fc.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.79.mlp.c_fc.biases": "model-00007-of-00007.safetensors", | |
| "transformer.h.79.mlp.c_fc.scales": "model-00007-of-00007.safetensors", | |
| "transformer.h.79.mlp.c_fc.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.79.mlp.c_proj.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.79.mlp.c_proj.biases": "model-00007-of-00007.safetensors", | |
| "transformer.h.79.mlp.c_proj.scales": "model-00007-of-00007.safetensors", | |
| "transformer.h.79.mlp.c_proj.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.8.attn.c_attn.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.8.attn.c_attn.biases": "model-00001-of-00007.safetensors", | |
| "transformer.h.8.attn.c_attn.scales": "model-00001-of-00007.safetensors", | |
| "transformer.h.8.attn.c_attn.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.8.attn.c_proj.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.8.attn.c_proj.biases": "model-00001-of-00007.safetensors", | |
| "transformer.h.8.attn.c_proj.scales": "model-00001-of-00007.safetensors", | |
| "transformer.h.8.attn.c_proj.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.8.ln_1.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.8.ln_1.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.8.ln_2.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.8.ln_2.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.8.mlp.c_fc.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.8.mlp.c_fc.biases": "model-00001-of-00007.safetensors", | |
| "transformer.h.8.mlp.c_fc.scales": "model-00001-of-00007.safetensors", | |
| "transformer.h.8.mlp.c_fc.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.8.mlp.c_proj.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.8.mlp.c_proj.biases": "model-00001-of-00007.safetensors", | |
| "transformer.h.8.mlp.c_proj.scales": "model-00001-of-00007.safetensors", | |
| "transformer.h.8.mlp.c_proj.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.80.attn.c_attn.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.80.attn.c_attn.biases": "model-00007-of-00007.safetensors", | |
| "transformer.h.80.attn.c_attn.scales": "model-00007-of-00007.safetensors", | |
| "transformer.h.80.attn.c_attn.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.80.attn.c_proj.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.80.attn.c_proj.biases": "model-00007-of-00007.safetensors", | |
| "transformer.h.80.attn.c_proj.scales": "model-00007-of-00007.safetensors", | |
| "transformer.h.80.attn.c_proj.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.80.ln_1.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.80.ln_1.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.80.ln_2.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.80.ln_2.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.80.mlp.c_fc.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.80.mlp.c_fc.biases": "model-00007-of-00007.safetensors", | |
| "transformer.h.80.mlp.c_fc.scales": "model-00007-of-00007.safetensors", | |
| "transformer.h.80.mlp.c_fc.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.80.mlp.c_proj.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.80.mlp.c_proj.biases": "model-00007-of-00007.safetensors", | |
| "transformer.h.80.mlp.c_proj.scales": "model-00007-of-00007.safetensors", | |
| "transformer.h.80.mlp.c_proj.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.81.attn.c_attn.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.81.attn.c_attn.biases": "model-00007-of-00007.safetensors", | |
| "transformer.h.81.attn.c_attn.scales": "model-00007-of-00007.safetensors", | |
| "transformer.h.81.attn.c_attn.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.81.attn.c_proj.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.81.attn.c_proj.biases": "model-00007-of-00007.safetensors", | |
| "transformer.h.81.attn.c_proj.scales": "model-00007-of-00007.safetensors", | |
| "transformer.h.81.attn.c_proj.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.81.ln_1.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.81.ln_1.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.81.ln_2.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.81.ln_2.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.81.mlp.c_fc.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.81.mlp.c_fc.biases": "model-00007-of-00007.safetensors", | |
| "transformer.h.81.mlp.c_fc.scales": "model-00007-of-00007.safetensors", | |
| "transformer.h.81.mlp.c_fc.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.81.mlp.c_proj.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.81.mlp.c_proj.biases": "model-00007-of-00007.safetensors", | |
| "transformer.h.81.mlp.c_proj.scales": "model-00007-of-00007.safetensors", | |
| "transformer.h.81.mlp.c_proj.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.82.attn.c_attn.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.82.attn.c_attn.biases": "model-00007-of-00007.safetensors", | |
| "transformer.h.82.attn.c_attn.scales": "model-00007-of-00007.safetensors", | |
| "transformer.h.82.attn.c_attn.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.82.attn.c_proj.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.82.attn.c_proj.biases": "model-00007-of-00007.safetensors", | |
| "transformer.h.82.attn.c_proj.scales": "model-00007-of-00007.safetensors", | |
| "transformer.h.82.attn.c_proj.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.82.ln_1.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.82.ln_1.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.82.ln_2.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.82.ln_2.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.82.mlp.c_fc.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.82.mlp.c_fc.biases": "model-00007-of-00007.safetensors", | |
| "transformer.h.82.mlp.c_fc.scales": "model-00007-of-00007.safetensors", | |
| "transformer.h.82.mlp.c_fc.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.82.mlp.c_proj.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.82.mlp.c_proj.biases": "model-00007-of-00007.safetensors", | |
| "transformer.h.82.mlp.c_proj.scales": "model-00007-of-00007.safetensors", | |
| "transformer.h.82.mlp.c_proj.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.83.attn.c_attn.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.83.attn.c_attn.biases": "model-00007-of-00007.safetensors", | |
| "transformer.h.83.attn.c_attn.scales": "model-00007-of-00007.safetensors", | |
| "transformer.h.83.attn.c_attn.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.83.attn.c_proj.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.83.attn.c_proj.biases": "model-00007-of-00007.safetensors", | |
| "transformer.h.83.attn.c_proj.scales": "model-00007-of-00007.safetensors", | |
| "transformer.h.83.attn.c_proj.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.83.ln_1.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.83.ln_1.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.83.ln_2.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.83.ln_2.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.83.mlp.c_fc.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.83.mlp.c_fc.biases": "model-00007-of-00007.safetensors", | |
| "transformer.h.83.mlp.c_fc.scales": "model-00007-of-00007.safetensors", | |
| "transformer.h.83.mlp.c_fc.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.83.mlp.c_proj.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.83.mlp.c_proj.biases": "model-00007-of-00007.safetensors", | |
| "transformer.h.83.mlp.c_proj.scales": "model-00007-of-00007.safetensors", | |
| "transformer.h.83.mlp.c_proj.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.84.attn.c_attn.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.84.attn.c_attn.biases": "model-00007-of-00007.safetensors", | |
| "transformer.h.84.attn.c_attn.scales": "model-00007-of-00007.safetensors", | |
| "transformer.h.84.attn.c_attn.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.84.attn.c_proj.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.84.attn.c_proj.biases": "model-00007-of-00007.safetensors", | |
| "transformer.h.84.attn.c_proj.scales": "model-00007-of-00007.safetensors", | |
| "transformer.h.84.attn.c_proj.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.84.ln_1.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.84.ln_1.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.84.ln_2.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.84.ln_2.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.84.mlp.c_fc.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.84.mlp.c_fc.biases": "model-00007-of-00007.safetensors", | |
| "transformer.h.84.mlp.c_fc.scales": "model-00007-of-00007.safetensors", | |
| "transformer.h.84.mlp.c_fc.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.84.mlp.c_proj.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.84.mlp.c_proj.biases": "model-00007-of-00007.safetensors", | |
| "transformer.h.84.mlp.c_proj.scales": "model-00007-of-00007.safetensors", | |
| "transformer.h.84.mlp.c_proj.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.85.attn.c_attn.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.85.attn.c_attn.biases": "model-00007-of-00007.safetensors", | |
| "transformer.h.85.attn.c_attn.scales": "model-00007-of-00007.safetensors", | |
| "transformer.h.85.attn.c_attn.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.85.attn.c_proj.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.85.attn.c_proj.biases": "model-00007-of-00007.safetensors", | |
| "transformer.h.85.attn.c_proj.scales": "model-00007-of-00007.safetensors", | |
| "transformer.h.85.attn.c_proj.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.85.ln_1.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.85.ln_1.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.85.ln_2.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.85.ln_2.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.85.mlp.c_fc.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.85.mlp.c_fc.biases": "model-00007-of-00007.safetensors", | |
| "transformer.h.85.mlp.c_fc.scales": "model-00007-of-00007.safetensors", | |
| "transformer.h.85.mlp.c_fc.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.85.mlp.c_proj.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.85.mlp.c_proj.biases": "model-00007-of-00007.safetensors", | |
| "transformer.h.85.mlp.c_proj.scales": "model-00007-of-00007.safetensors", | |
| "transformer.h.85.mlp.c_proj.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.86.attn.c_attn.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.86.attn.c_attn.biases": "model-00007-of-00007.safetensors", | |
| "transformer.h.86.attn.c_attn.scales": "model-00007-of-00007.safetensors", | |
| "transformer.h.86.attn.c_attn.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.86.attn.c_proj.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.86.attn.c_proj.biases": "model-00007-of-00007.safetensors", | |
| "transformer.h.86.attn.c_proj.scales": "model-00007-of-00007.safetensors", | |
| "transformer.h.86.attn.c_proj.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.86.ln_1.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.86.ln_1.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.86.ln_2.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.86.ln_2.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.86.mlp.c_fc.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.86.mlp.c_fc.biases": "model-00007-of-00007.safetensors", | |
| "transformer.h.86.mlp.c_fc.scales": "model-00007-of-00007.safetensors", | |
| "transformer.h.86.mlp.c_fc.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.86.mlp.c_proj.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.86.mlp.c_proj.biases": "model-00007-of-00007.safetensors", | |
| "transformer.h.86.mlp.c_proj.scales": "model-00007-of-00007.safetensors", | |
| "transformer.h.86.mlp.c_proj.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.87.attn.c_attn.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.87.attn.c_attn.biases": "model-00007-of-00007.safetensors", | |
| "transformer.h.87.attn.c_attn.scales": "model-00007-of-00007.safetensors", | |
| "transformer.h.87.attn.c_attn.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.87.attn.c_proj.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.87.attn.c_proj.biases": "model-00007-of-00007.safetensors", | |
| "transformer.h.87.attn.c_proj.scales": "model-00007-of-00007.safetensors", | |
| "transformer.h.87.attn.c_proj.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.87.ln_1.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.87.ln_1.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.87.ln_2.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.87.ln_2.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.87.mlp.c_fc.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.87.mlp.c_fc.biases": "model-00007-of-00007.safetensors", | |
| "transformer.h.87.mlp.c_fc.scales": "model-00007-of-00007.safetensors", | |
| "transformer.h.87.mlp.c_fc.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.87.mlp.c_proj.bias": "model-00007-of-00007.safetensors", | |
| "transformer.h.87.mlp.c_proj.biases": "model-00007-of-00007.safetensors", | |
| "transformer.h.87.mlp.c_proj.scales": "model-00007-of-00007.safetensors", | |
| "transformer.h.87.mlp.c_proj.weight": "model-00007-of-00007.safetensors", | |
| "transformer.h.9.attn.c_attn.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.9.attn.c_attn.biases": "model-00001-of-00007.safetensors", | |
| "transformer.h.9.attn.c_attn.scales": "model-00001-of-00007.safetensors", | |
| "transformer.h.9.attn.c_attn.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.9.attn.c_proj.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.9.attn.c_proj.biases": "model-00001-of-00007.safetensors", | |
| "transformer.h.9.attn.c_proj.scales": "model-00001-of-00007.safetensors", | |
| "transformer.h.9.attn.c_proj.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.9.ln_1.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.9.ln_1.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.9.ln_2.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.9.ln_2.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.9.mlp.c_fc.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.9.mlp.c_fc.biases": "model-00001-of-00007.safetensors", | |
| "transformer.h.9.mlp.c_fc.scales": "model-00001-of-00007.safetensors", | |
| "transformer.h.9.mlp.c_fc.weight": "model-00001-of-00007.safetensors", | |
| "transformer.h.9.mlp.c_proj.bias": "model-00001-of-00007.safetensors", | |
| "transformer.h.9.mlp.c_proj.biases": "model-00001-of-00007.safetensors", | |
| "transformer.h.9.mlp.c_proj.scales": "model-00001-of-00007.safetensors", | |
| "transformer.h.9.mlp.c_proj.weight": "model-00001-of-00007.safetensors", | |
| "transformer.ln_f.bias": "model-00007-of-00007.safetensors", | |
| "transformer.ln_f.weight": "model-00007-of-00007.safetensors", | |
| "transformer.wpe.biases": "model-00001-of-00007.safetensors", | |
| "transformer.wpe.scales": "model-00001-of-00007.safetensors", | |
| "transformer.wpe.weight": "model-00001-of-00007.safetensors", | |
| "transformer.wte.biases": "model-00001-of-00007.safetensors", | |
| "transformer.wte.scales": "model-00001-of-00007.safetensors", | |
| "transformer.wte.weight": "model-00001-of-00007.safetensors" | |
| } | |
| } |