Instructions to use FlagAlpha/Llama3-Chinese-8B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FlagAlpha/Llama3-Chinese-8B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="FlagAlpha/Llama3-Chinese-8B-Instruct", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("FlagAlpha/Llama3-Chinese-8B-Instruct", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("FlagAlpha/Llama3-Chinese-8B-Instruct", trust_remote_code=True, device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use FlagAlpha/Llama3-Chinese-8B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FlagAlpha/Llama3-Chinese-8B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FlagAlpha/Llama3-Chinese-8B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/FlagAlpha/Llama3-Chinese-8B-Instruct

SGLang

How to use FlagAlpha/Llama3-Chinese-8B-Instruct 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 "FlagAlpha/Llama3-Chinese-8B-Instruct" \
    --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": "FlagAlpha/Llama3-Chinese-8B-Instruct",
		"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 "FlagAlpha/Llama3-Chinese-8B-Instruct" \
        --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": "FlagAlpha/Llama3-Chinese-8B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use FlagAlpha/Llama3-Chinese-8B-Instruct with Docker Model Runner:
```
docker model run hf.co/FlagAlpha/Llama3-Chinese-8B-Instruct
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Llama3-Chinese-8B-Instruct

Llama3-Chinese-8B-Instruct基于Llama3-8B中文微调对话模型，由Llama中文社区和AtomEcho（原子回声）联合研发，我们会持续提供更新的模型参数，模型训练过程见 https://llama.family。

模型的部署、训练、微调等方法详见Llama中文社区GitHub仓库：https://github.com/LlamaFamily/Llama-Chinese

如何使用

import transformers
import torch


model_id = "FlagAlpha/Llama3-Chinese-8B-Instruct"

pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={"torch_dtype": torch.float16},
    device="cuda",
)


messages = [{"role": "system", "content": ""}]

messages.append(
                {"role": "user", "content": "介绍一下机器学习"}
            )

prompt = pipeline.tokenizer.apply_chat_template(
        messages, 
        tokenize=False, 
        add_generation_prompt=True
    )

terminators = [
        pipeline.tokenizer.eos_token_id,
        pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
    ]
outputs = pipeline(
    prompt,
    max_new_tokens=512,
    eos_token_id=terminators,
    do_sample=True,
    temperature=0.6,
    top_p=0.9
)

content = outputs[0]["generated_text"][len(prompt):]

print(content)