Instructions to use Linly-AI/Chinese-LLaMA-2-7B-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Linly-AI/Chinese-LLaMA-2-7B-hf with Transformers:

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

pipe = pipeline("text-generation", model="Linly-AI/Chinese-LLaMA-2-7B-hf")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Linly-AI/Chinese-LLaMA-2-7B-hf")
model = AutoModelForCausalLM.from_pretrained("Linly-AI/Chinese-LLaMA-2-7B-hf")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Linly-AI/Chinese-LLaMA-2-7B-hf with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Linly-AI/Chinese-LLaMA-2-7B-hf

SGLang

How to use Linly-AI/Chinese-LLaMA-2-7B-hf 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 "Linly-AI/Chinese-LLaMA-2-7B-hf" \
    --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": "Linly-AI/Chinese-LLaMA-2-7B-hf",
		"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 "Linly-AI/Chinese-LLaMA-2-7B-hf" \
        --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": "Linly-AI/Chinese-LLaMA-2-7B-hf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Linly-AI/Chinese-LLaMA-2-7B-hf with Docker Model Runner:
```
docker model run hf.co/Linly-AI/Chinese-LLaMA-2-7B-hf
```

tokenizer config好像有些问题

by Skepsun - opened Jul 25, 2023

Discussion

Skepsun

Jul 25, 2023

{"bos_token": "", "eos_token": "", "model_max_length": 1000000000000000019884624838656, "tokenizer_class": "LlamaTokenizer", "unk_token": ""}

这会不会影响模型的后续训练和使用

wmpscc

Linly org Jul 25, 2023

推理可以参考 https://huggingface.co/spaces/Linly-AI/Linly-ChatFlow/blob/main/app.py

import os
os.environ['CUDA_LAUNCH_BLOCKING'] = '1'

import torch
import gradio as gr
from transformers import AutoModelForCausalLM, AutoTokenizer


def init_model():
    model = AutoModelForCausalLM.from_pretrained("Linly-AI/Chinese-LLaMA-2-7B-hf", device_map="cuda:0", torch_dtype=torch.float16, trust_remote_code=True)
    tokenizer = AutoTokenizer.from_pretrained("Linly-AI/Chinese-LLaMA-2-7B-hf", use_fast=False, trust_remote_code=True)
    return model, tokenizer
    


def chat(prompt, top_k, temperature):
    prompt = f"### Instruction:{prompt.strip()}  ### Response:"
    inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")
    generate_ids = model.generate(inputs.input_ids, do_sample=True, max_new_tokens=2048, top_k=int(top_k), top_p=0.84, temperature=float(temperature), repetition_penalty=1.15, eos_token_id=2, bos_token_id=1, pad_token_id=0)
    response = tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
    response = response.lstrip(prompt)
    print('-log: ',prompt, response)
    return response


if __name__ == '__main__':
    model, tokenizer = init_model()
    demo = gr.Interface(
        fn=chat,
        inputs=["text", gr.Slider(1, 60, value=10, step=1), gr.Slider(0.1, 2.0, value=1.0, step=0.1)],
        outputs="text",
    )
    demo.launch()

JaheimLee

Jul 30, 2023

•

edited Jul 30, 2023

建议还是更新一下文件，如果用第三方库加载（例如vllm），tokenizer文件有问题会影响文本编码。毕竟这根本不费事。

P01son

Linly org Jul 31, 2023

好的

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment