Instructions to use BoyangZ/Llama3-chinese_chat_ft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BoyangZ/Llama3-chinese_chat_ft with Transformers:

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

pipe = pipeline("text-generation", model="BoyangZ/Llama3-chinese_chat_ft")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("BoyangZ/Llama3-chinese_chat_ft")
model = AutoModelForCausalLM.from_pretrained("BoyangZ/Llama3-chinese_chat_ft")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use BoyangZ/Llama3-chinese_chat_ft with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/BoyangZ/Llama3-chinese_chat_ft

SGLang

How to use BoyangZ/Llama3-chinese_chat_ft 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 "BoyangZ/Llama3-chinese_chat_ft" \
    --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": "BoyangZ/Llama3-chinese_chat_ft",
		"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 "BoyangZ/Llama3-chinese_chat_ft" \
        --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": "BoyangZ/Llama3-chinese_chat_ft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use BoyangZ/Llama3-chinese_chat_ft with Docker Model Runner:
```
docker model run hf.co/BoyangZ/Llama3-chinese_chat_ft
```

How to use：

from transformers import AutoTokenizer, AutoModelForCausalLM import torch

model_id = "BoyangZ/Llama3-chinese_chat_ft"

tokenizer = AutoTokenizer.from_pretrained(model_id) model = AutoModelForCausalLM.from_pretrained( model_id, torch_dtype=torch.bfloat16, device_map="auto", )

messages = [ {"role": "system", "content": "You are a LLM assistant. Users will ask you questions in Chinese, You will answer questions in Chinese"}, {"role": "user", "content": "李白是哪个朝代的人?"}, ]

input_ids = tokenizer.apply_chat_template( messages, add_generation_prompt=True, return_tensors="pt" ).to(model.device)

terminators = [ tokenizer.eos_token_id, tokenizer.convert_tokens_to_ids("<|eot_id|>") ]

outputs = model.generate( input_ids, max_new_tokens=256, eos_token_id=terminators, do_sample=True, temperature=0.6, top_p=0.9, ) response = outputs[0][input_ids.shape[-1]:] print(tokenizer.decode(response, skip_special_tokens=True))

example1

example2

example3

Downloads last month: 5

Safetensors

Model size

8B params

Tensor type

F16