Instructions to use internlm/internlm2_5-7b-chat-1m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use internlm/internlm2_5-7b-chat-1m with Transformers:

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

pipe = pipeline("text-generation", model="internlm/internlm2_5-7b-chat-1m", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("internlm/internlm2_5-7b-chat-1m", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use internlm/internlm2_5-7b-chat-1m 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-1m"
# 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-1m",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/internlm/internlm2_5-7b-chat-1m

SGLang

How to use internlm/internlm2_5-7b-chat-1m 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-1m" \
    --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-1m",
		"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-1m" \
        --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-1m",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use internlm/internlm2_5-7b-chat-1m with Docker Model Runner:
```
docker model run hf.co/internlm/internlm2_5-7b-chat-1m
```

Update README.md with benchmark results

by bowenli - opened Jul 4, 2024

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

+20

-2

Files changed (1) hide show

README.md +20 -2

README.md CHANGED Viewed

@@ -36,16 +36,34 @@ InternLM2.5 has open-sourced a 7 billion parameter base model and a chat model t
 - **Outstanding reasoning capability**: State-of-the-art performance on Math reasoning, surpassing models like Llama3 and Gemma2-9B.
-- **1M Context window**: Nearly perfect at finding needles in the haystack with 1M-long context, with leading performance on long-context tasks like LongBench. Try it with [LMDeploy](https://github.com/InternLM/InternLM/blob/main/chat/lmdeploy.md) for 1M-context inference.
 - **Stronger tool use**: InternLM2.5 supports gathering information from more than 100 web pages, corresponding implementation will be released in [Lagent](https://github.com/InternLM/lagent/tree/main) soon. InternLM2.5 has better tool utilization-related capabilities in instruction following, tool selection and reflection. See [examples](https://github.com/InternLM/InternLM/blob/main/agent/lagent.md).
 ## InternLM2.5-7B-Chat-1M
-InternLM2.5-7B-Chat-1M is the 1M-long-context version of InternLM2.5-7B-Chat. Since huggingface Transformers does not directly support inference with 1M-long context, we recommand to use LMDeploy. The conventional usage with huggingface Transformers is also shown below.
 ### LMDeploy
 LMDeploy is a toolkit for compressing, deploying, and serving LLM, developed by the MMRazor and MMDeploy teams.
 Here is an example of 1M-long context inference. **Note: 1M context length requires 4xA100-80G!**

 - **Outstanding reasoning capability**: State-of-the-art performance on Math reasoning, surpassing models like Llama3 and Gemma2-9B.
+- **1M Context window**: Nearly perfect at finding needles in the haystack with 1M-long context, with leading performance on long-context tasks like LongBench. Try it with [LMDeploy](https://github.com/InternLM/InternLM/blob/main/chat/lmdeploy.md) for 1M-context inference and a [file chat demo](https://github.com/InternLM/InternLM/tree/main/long_context).
 - **Stronger tool use**: InternLM2.5 supports gathering information from more than 100 web pages, corresponding implementation will be released in [Lagent](https://github.com/InternLM/lagent/tree/main) soon. InternLM2.5 has better tool utilization-related capabilities in instruction following, tool selection and reflection. See [examples](https://github.com/InternLM/InternLM/blob/main/agent/lagent.md).
 ## InternLM2.5-7B-Chat-1M
+InternLM2.5-7B-Chat-1M is the 1M-long-context version of InternLM2.5-7B-Chat.
+### Performance Evaluation
+We employed the "*needle in a haystack approach*" to evaluate the model's ability to retrieve information from long texts. Results show that InternLM2.5-7B-Chat-1M can accurately locate key information in documents up to 1M tokens in length.
+<p align="center">
+<img src="https://github.com/libowen2121/InternLM/assets/19970308/2ce3745f-26f5-4a39-bdcd-2075790d7b1d" alt="drawing" width="700"/>
+</p>
+We also used the [LongBench](https://github.com/THUDM/LongBench) benchmark to assess long-document comprehension capabilities. Our model achieved optimal performance in these tests.
+<p align="center">
+<img src="https://github.com/libowen2121/InternLM/assets/19970308/1e8f7da8-8193-4def-8b06-0550bab6a12f" alt="drawing" width="800"/>
+</p>
 ### LMDeploy
+Since huggingface Transformers does not directly support inference with 1M-long context, we recommand to use LMDeploy. The conventional usage with huggingface Transformers is also shown below.
 LMDeploy is a toolkit for compressing, deploying, and serving LLM, developed by the MMRazor and MMDeploy teams.
 Here is an example of 1M-long context inference. **Note: 1M context length requires 4xA100-80G!**