Instructions to use TurboPascal/Chatterbox-LLaMA-zh-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TurboPascal/Chatterbox-LLaMA-zh-base with Transformers:

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

pipe = pipeline("text-generation", model="TurboPascal/Chatterbox-LLaMA-zh-base")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TurboPascal/Chatterbox-LLaMA-zh-base")
model = AutoModelForCausalLM.from_pretrained("TurboPascal/Chatterbox-LLaMA-zh-base")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TurboPascal/Chatterbox-LLaMA-zh-base with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/TurboPascal/Chatterbox-LLaMA-zh-base

SGLang

How to use TurboPascal/Chatterbox-LLaMA-zh-base 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 "TurboPascal/Chatterbox-LLaMA-zh-base" \
    --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": "TurboPascal/Chatterbox-LLaMA-zh-base",
		"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 "TurboPascal/Chatterbox-LLaMA-zh-base" \
        --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": "TurboPascal/Chatterbox-LLaMA-zh-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TurboPascal/Chatterbox-LLaMA-zh-base with Docker Model Runner:
```
docker model run hf.co/TurboPascal/Chatterbox-LLaMA-zh-base
```

TurboPascal commited on May 5, 2023

Commit

aa844e4

1 Parent(s): c81a4d1

Update README.md

Browse files

Files changed (1) hide show

README.md +5 -0

README.md CHANGED Viewed

@@ -1,3 +1,8 @@
 ---
 license: apache-2.0
 ---

 ---
 license: apache-2.0
 ---
+Llama-zh-base is an open-source project that offers a complete training pipeline for building Chinese large language models, ranging from dataset preparation to tokenization, pre-training, prompt tuning, and the reinforcement learning technique RLHF.
+This is the Llama-zh-base model trained from scratch using the Chinese pretrain corpus in this project.The amount of parameters is about 0.8B.
+使用30G中文语料重头开始预训练的Llama模型，旨在提供可用的中小型基础模型。目前未经过指令微调。