Instructions to use internlm/internlm2-base-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use internlm/internlm2-base-7b with Transformers:

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

pipe = pipeline("text-generation", model="internlm/internlm2-base-7b", trust_remote_code=True)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("internlm/internlm2-base-7b", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use internlm/internlm2-base-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "internlm/internlm2-base-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "internlm/internlm2-base-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/internlm/internlm2-base-7b

SGLang

How to use internlm/internlm2-base-7b 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-base-7b" \
    --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/internlm2-base-7b",
		"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/internlm2-base-7b" \
        --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/internlm2-base-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use internlm/internlm2-base-7b with Docker Model Runner:
```
docker model run hf.co/internlm/internlm2-base-7b
```

internlm2-base-7b

Commit History

Jan 27, 2024

04:56
Adding `safetensors` variant of this model⁠

SFconvertbot

Verified signature
ce31bff

Jan 24, 2024

11:57
small

x54-729

62f4666
08:34
fast tokenizer and stream_chat fix (#1)⁠

RangiLyu +1: x54-729

Verified signature
bff2446

Jan 19, 2024

12:46
update rope_scaling

x54-729

ffd2f5b
12:41
remove unnecessary attention_drop

x54-729

c2efc37
12:40
update chat template

x54-729

74d2c19

Jan 18, 2024

12:04
update readme info

x54-729

ec25627
09:05
Update README.md

ZwwWayne

Verified signature
6aa78ed

Jan 17, 2024

04:21
fix example prompt

x54-729

9dfc044
04:01
update readme

x54-729

7edacce

Jan 16, 2024

14:33
fix import error

x54-729

6032db7
11:37
support flash attn 2

x54-729

328cd15

Jan 15, 2024

09:59
Create README.md

ZwwWayne

Verified signature
93039e2

Jan 12, 2024

06:39
update model weights

ZwwWayne

2fb05a1
06:34
update .gitattributes

ZwwWayne

7a4f010
06:18
initial commit

ZwwWayne

Verified signature
15b3423

Commit History

Jan 27, 2024

Adding `safetensors` variant of this model⁠

Jan 24, 2024

small

fast tokenizer and stream_chat fix (#1)⁠

Jan 19, 2024

update rope_scaling

remove unnecessary attention_drop

update chat template

Jan 18, 2024

update readme info

Update README.md

Jan 17, 2024

fix example prompt

update readme

Jan 16, 2024

fix import error

support flash attn 2

Jan 15, 2024

Create README.md

Jan 12, 2024

update model weights

update .gitattributes

initial commit