Instructions to use internlm/internlm-chat-20b-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use internlm/internlm-chat-20b-4bit with Transformers:

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

pipe = pipeline("text-generation", model="internlm/internlm-chat-20b-4bit", trust_remote_code=True)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("internlm/internlm-chat-20b-4bit", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use internlm/internlm-chat-20b-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "internlm/internlm-chat-20b-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "internlm/internlm-chat-20b-4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/internlm/internlm-chat-20b-4bit

SGLang

How to use internlm/internlm-chat-20b-4bit 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 "internlm/internlm-chat-20b-4bit" \
    --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": "internlm/internlm-chat-20b-4bit",
		"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 "internlm/internlm-chat-20b-4bit" \
        --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": "internlm/internlm-chat-20b-4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use internlm/internlm-chat-20b-4bit with Docker Model Runner:
```
docker model run hf.co/internlm/internlm-chat-20b-4bit
```

👍

by hiarcs - opened Sep 24, 2023

Discussion

hiarcs

Sep 24, 2023

通过lmdeploy.turbomind.chat运行，速度很快，效果对一个20B模型而言非常不错。
中文能力相当不错，除非是在没有提示的情况下尝试识别文本中的讽刺描写外或区分细微的逻辑差别外，和GPT4对比水平差不多，不少回答感觉超过GPT4。
回答知识性问题中规中矩。
不能用来写代码，问到Java相关的问题，会和7b版本一样，会在输出一半后重复输出相同的文本，比如import语句或html标记。
在启动后什么都不写直接两下回车，有时会出题考我，7b版本会叫我烧豆腐……两个版本在这种情况下都输出英文。
不能很好的进行问句的翻译，会直接用英文回答问题。

还有祖传的：
WARNING: Can not find tokenizer.json. It may take long time to initialize the tokenizer.
[WARNING] gemm_config.in is not found; using default GEMM algo

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