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

Libraries

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

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

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

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

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

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "internlm/internlm2-chat-7b"
# 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-7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

How to use internlm/internlm2-chat-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-chat-7b" \
    --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-7b",
		"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-7b" \
        --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-7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

x54-729 commited on Mar 13, 2025

Commit

c2ba644

1 Parent(s): e7c2e16

replace get_max_length

Browse files

Files changed (1) hide show

modeling_internlm2.py +3 -3

modeling_internlm2.py CHANGED Viewed

@@ -1081,7 +1081,7 @@ class InternLM2Model(InternLM2PreTrainedModel):
         min_dtype = torch.finfo(dtype).min
         sequence_length = input_tensor.shape[1]
         if using_static_cache:
-            target_length = past_key_values.get_max_length()
         else:
             target_length = (
                 attention_mask.shape[-1]
@@ -1274,8 +1274,8 @@ class InternLM2ForCausalLM(InternLM2PreTrainedModel):
             if isinstance(past_key_values, Cache):
                 past_length = cache_position[0] if cache_position is not None else past_key_values.get_seq_length()
                 max_cache_length = (
-                    torch.tensor(past_key_values.get_max_length(), device=input_ids.device)
-                    if past_key_values.get_max_length() is not None
                     else None
                 )
                 cache_length = past_length if max_cache_length is None else torch.min(max_cache_length, past_length)

         min_dtype = torch.finfo(dtype).min
         sequence_length = input_tensor.shape[1]
         if using_static_cache:
+            target_length = past_key_values.get_max_cache_shape()
         else:
             target_length = (
                 attention_mask.shape[-1]
             if isinstance(past_key_values, Cache):
                 past_length = cache_position[0] if cache_position is not None else past_key_values.get_seq_length()
                 max_cache_length = (
+                    torch.tensor(past_key_values.get_max_cache_shape(), device=input_ids.device)
+                    if past_key_values.get_max_cache_shape() is not None
                     else None
                 )
                 cache_length = past_length if max_cache_length is None else torch.min(max_cache_length, past_length)