Text Generation
Transformers
Safetensors
Hebrew
hebrew-gpt
feature-extraction
hebrew
gpt
causal-lm
hebrew-nlp
muon-optimizer
sentencepiece
rope
swiglu
custom_code
Eval Results (legacy)
Instructions to use Slasky/HebrewGPT-296M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Slasky/HebrewGPT-296M with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Slasky/HebrewGPT-296M", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Slasky/HebrewGPT-296M", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Slasky/HebrewGPT-296M with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Slasky/HebrewGPT-296M" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Slasky/HebrewGPT-296M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Slasky/HebrewGPT-296M
- SGLang
How to use Slasky/HebrewGPT-296M 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 "Slasky/HebrewGPT-296M" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Slasky/HebrewGPT-296M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "Slasky/HebrewGPT-296M" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Slasky/HebrewGPT-296M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Slasky/HebrewGPT-296M with Docker Model Runner:
docker model run hf.co/Slasky/HebrewGPT-296M
Upload modeling_hebrewgpt.py with huggingface_hub
Browse files- modeling_hebrewgpt.py +1 -0
modeling_hebrewgpt.py
CHANGED
|
@@ -135,6 +135,7 @@ class HebrewGPTPreTrainedModel(PreTrainedModel):
|
|
| 135 |
|
| 136 |
class HebrewGPTForCausalLM(HebrewGPTPreTrainedModel):
|
| 137 |
_tied_weights_keys = {"head.weight": "tok_emb.weight"}
|
|
|
|
| 138 |
|
| 139 |
def __init__(self, config: HebrewGPTConfig):
|
| 140 |
super().__init__(config)
|
|
|
|
| 135 |
|
| 136 |
class HebrewGPTForCausalLM(HebrewGPTPreTrainedModel):
|
| 137 |
_tied_weights_keys = {"head.weight": "tok_emb.weight"}
|
| 138 |
+
_keys_to_ignore_on_load_missing = ["head.weight"]
|
| 139 |
|
| 140 |
def __init__(self, config: HebrewGPTConfig):
|
| 141 |
super().__init__(config)
|