Instructions to use hfl/chinese-llama-2-7b-64k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hfl/chinese-llama-2-7b-64k with Transformers:

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

pipe = pipeline("text-generation", model="hfl/chinese-llama-2-7b-64k", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("hfl/chinese-llama-2-7b-64k", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("hfl/chinese-llama-2-7b-64k", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use hfl/chinese-llama-2-7b-64k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hfl/chinese-llama-2-7b-64k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hfl/chinese-llama-2-7b-64k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/hfl/chinese-llama-2-7b-64k

SGLang

How to use hfl/chinese-llama-2-7b-64k 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 "hfl/chinese-llama-2-7b-64k" \
    --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": "hfl/chinese-llama-2-7b-64k",
		"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 "hfl/chinese-llama-2-7b-64k" \
        --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": "hfl/chinese-llama-2-7b-64k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use hfl/chinese-llama-2-7b-64k with Docker Model Runner:
```
docker model run hf.co/hfl/chinese-llama-2-7b-64k
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Chinese-LLaMA-2-7B-64K

This repository contains Chinese-LLaMA-2-7B-64K, which is tuned on Chinese-LLaMA-2-7B with YaRN method.

For LoRA-only model, please see: https://huggingface.co/hfl/chinese-llama-2-lora-7b-64k

Please refer to https://github.com/ymcui/Chinese-LLaMA-Alpaca-2/ for more details.

Downloads last month: 170

Safetensors

Model size

7B params

Tensor type

F32

F16

Model tree for hfl/chinese-llama-2-7b-64k

Quantizations

1 model