Instructions to use internlm/internlm2-chat-20b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use internlm/internlm2-chat-20b with Transformers:

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

pipe = pipeline("text-generation", model="internlm/internlm2-chat-20b", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("internlm/internlm2-chat-20b", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use internlm/internlm2-chat-20b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "internlm/internlm2-chat-20b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "internlm/internlm2-chat-20b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/internlm/internlm2-chat-20b

SGLang

How to use internlm/internlm2-chat-20b 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/internlm2-chat-20b" \
    --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": "internlm/internlm2-chat-20b",
		"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 "internlm/internlm2-chat-20b" \
        --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": "internlm/internlm2-chat-20b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use internlm/internlm2-chat-20b with Docker Model Runner:
```
docker model run hf.co/internlm/internlm2-chat-20b
```

Llama Compatibility

by brucethemoose - opened Jan 17, 2024

Discussion

brucethemoose

Jan 17, 2024

•

edited Jan 17, 2024

I'm not sure how different the architecture actually is, but if possible, could you change the config to be llama compatible instead of requiring custom runtime/tokenizer code?

Custom code is a huge blocker to the highly optimized llama architecture infrastructure the community already uses... To be blunt, I can run Yi 34B 200K with a fraction of the resources it takes to run this 20B model, for the moment, and finetune it just about as efficiently with llama focused frameworks.

Yi itself already went through this ordeal, and "llamafied" their release to the benefit of everyone: https://huggingface.co/01-ai/Yi-34B/discussions/11

x54-729

Jan 18, 2024

Thank you for your suggestion. The biggest difference lies in the combination of Wq, Wk, Wv, we did this for training efficiency. We are planning to offer a script that facilitates conversion between InternLM2 and LLaMA.

x54-729

Jan 19, 2024

Please try to use script in https://github.com/InternLM/InternLM/tree/main/tools to convert the format.

x54-729 changed discussion status to closed Jan 19, 2024

kongtao

Aug 2, 2024

Please try to use script in https://github.com/InternLM/InternLM/tree/main/tools to convert the format.

https://github.com/InternLM/InternLM/issues/771

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