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

Libraries

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

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

pipe = pipeline("text-generation", model="internlm/internlm2-math-plus-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-math-plus-20b", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "internlm/internlm2-math-plus-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-math-plus-20b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

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

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

internlm2-math-plus-20b

Commit History

Update EvalEval source links to flat datastore

5b66188
verified

EvalEvalBot commited on 30 days ago

Add EvalEval community eval results

b28265d
verified

EvalEvalBot commited on Jun 7

Add EvalEval community eval results

6f49c36
verified

EvalEvalBot commited on Jun 5

Add EvalEval community eval results

a7019ed
verified

EvalEvalBot commited on Jun 5

replace get_max_length

69a8cfe

x54-729 commited on Mar 13, 2025

update modeling file to newest

3151aed

x54-729 commited on Aug 20, 2024

Update config.json

1abf0ca
verified

InternLM-Math commited on Jun 5, 2024

Create configuration_internlm2.py

ad21b61
verified

InternLM-Math commited on May 28, 2024

Delete configuration_internlm.py

2afc1de
verified

InternLM-Math commited on May 28, 2024

Update config.json

dd55ae3
verified

InternLM-Math commited on May 28, 2024

Upload folder using huggingface_hub

cb5be48
verified

InternLM-Math commited on May 24, 2024

initial commit

e11b9ea
verified

InternLM-Math commited on May 24, 2024

Commit History

Update EvalEval source links to flat datastore 5b66188 verified

Add EvalEval community eval results b28265d verified

Add EvalEval community eval results 6f49c36 verified

Add EvalEval community eval results a7019ed verified

replace get_max_length 69a8cfe

update modeling file to newest 3151aed

Update config.json 1abf0ca verified

Create configuration_internlm2.py ad21b61 verified

Delete configuration_internlm.py 2afc1de verified

Update config.json dd55ae3 verified

Upload folder using huggingface_hub cb5be48 verified

initial commit e11b9ea verified

Update EvalEval source links to flat datastore

5b66188
verified

Add EvalEval community eval results

b28265d
verified

Add EvalEval community eval results

6f49c36
verified

Add EvalEval community eval results

a7019ed
verified

replace get_max_length

69a8cfe

update modeling file to newest

3151aed

Update config.json

1abf0ca
verified

Create configuration_internlm2.py

ad21b61
verified

Delete configuration_internlm.py

2afc1de
verified

Update config.json

dd55ae3
verified

Upload folder using huggingface_hub

cb5be48
verified

initial commit

e11b9ea
verified