Instructions to use internlm/internlm2_5-7b-chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use internlm/internlm2_5-7b-chat with Transformers:

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

pipe = pipeline("text-generation", model="internlm/internlm2_5-7b-chat", 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_5-7b-chat", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use internlm/internlm2_5-7b-chat with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "internlm/internlm2_5-7b-chat"
# 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_5-7b-chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/internlm/internlm2_5-7b-chat

SGLang

How to use internlm/internlm2_5-7b-chat 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_5-7b-chat" \
    --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_5-7b-chat",
		"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_5-7b-chat" \
        --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_5-7b-chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use internlm/internlm2_5-7b-chat with Docker Model Runner:
```
docker model run hf.co/internlm/internlm2_5-7b-chat
```

Please, add RULER - a long context benchmark

by MLDataScientist - opened Jul 7, 2024

Discussion

MLDataScientist

Jul 7, 2024

•

edited Jul 7, 2024

Hi team,
Thank you for releasing this model. Can you please perform the RULER (arxiv) benchmark (a retrieval-based benchmark for long context understanding) so that people can understand the performance of the model under long context?

For context, Microsoft started using RULER to report phi3 mini 128k instruct performance.
Gradient team also reported Llama3 8B with 1M context using the RULER benchmark.

I think RULER is a better benchmark in evaluating long context understanding at the moment.

Thanks!

MLDataScientist

Jul 7, 2024

Moved this discussion to the model that has 1M context: https://huggingface.co/internlm/internlm2_5-7b-chat-1m/discussions/4#668addd07bd1c857e9d4c4d8

MLDataScientist changed discussion status to closed Jul 7, 2024

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