Instructions to use jburtoft/TencentARC-LLaMA-Pro-8B-Neuron with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jburtoft/TencentARC-LLaMA-Pro-8B-Neuron with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="jburtoft/TencentARC-LLaMA-Pro-8B-Neuron")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jburtoft/TencentARC-LLaMA-Pro-8B-Neuron")
model = AutoModelForCausalLM.from_pretrained("jburtoft/TencentARC-LLaMA-Pro-8B-Neuron")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use jburtoft/TencentARC-LLaMA-Pro-8B-Neuron with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jburtoft/TencentARC-LLaMA-Pro-8B-Neuron"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jburtoft/TencentARC-LLaMA-Pro-8B-Neuron",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/jburtoft/TencentARC-LLaMA-Pro-8B-Neuron

SGLang

How to use jburtoft/TencentARC-LLaMA-Pro-8B-Neuron 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 "jburtoft/TencentARC-LLaMA-Pro-8B-Neuron" \
    --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": "jburtoft/TencentARC-LLaMA-Pro-8B-Neuron",
		"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 "jburtoft/TencentARC-LLaMA-Pro-8B-Neuron" \
        --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": "jburtoft/TencentARC-LLaMA-Pro-8B-Neuron",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use jburtoft/TencentARC-LLaMA-Pro-8B-Neuron with Docker Model Runner:
```
docker model run hf.co/jburtoft/TencentARC-LLaMA-Pro-8B-Neuron
```

Quick notes--what I did to get to this point

from optimum.neuron import NeuronModelForCausalLM
from transformers import AutoTokenizer
model_id = "TencentARC/LLaMA-Pro-8B"
compiler_args = {"num_cores": 2, "auto_cast_type": "fp16"}
input_shapes = {"sequence_length": 2048, "batch_size": 2 }
llm = NeuronModelForCausalLM.from_pretrained(model_id, export=True, **input_shapes, **compiler_args)
save_directory = "Tencent_neuron"

llm.save_pretrained(save_directory)
tokenizer = AutoTokenizer.from_pretrained(model_id)

tokenizer.save_pretrained(save_directory)

quit()

from optimum.neuron import pipeline

# Load pipeline from Hugging Face repository
save_directory = "Tencent_neuron"

pipe = pipeline("text-generation", save_directory)

# We use the tokenizer's chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
messages = [
    {"role": "user", "content": "What is 2+2?"},
]
prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
# Run generation
outputs = pipe(prompt, max_new_tokens=2048, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])

from huggingface_hub import login
from huggingface_hub import HfApi
api = HfApi()
login()


save_directory = "Tencent_neuron"

api.upload_folder(
    folder_path=save_directory,
    repo_id="jburtoft/TencentARC-LLaMA-Pro-8B-Neuron",
    repo_type="model",
    multi_commits=True,
    multi_commits_verbose=True,
)

Downloads last month: 5