Instructions to use internlm/internlm-xcomposer2-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use internlm/internlm-xcomposer2-7b with Transformers:

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

pipe = pipeline("text-generation", model="internlm/internlm-xcomposer2-7b", trust_remote_code=True)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("internlm/internlm-xcomposer2-7b", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use internlm/internlm-xcomposer2-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "internlm/internlm-xcomposer2-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "internlm/internlm-xcomposer2-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/internlm/internlm-xcomposer2-7b

SGLang

How to use internlm/internlm-xcomposer2-7b 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/internlm-xcomposer2-7b" \
    --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/internlm-xcomposer2-7b",
		"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/internlm-xcomposer2-7b" \
        --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/internlm-xcomposer2-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use internlm/internlm-xcomposer2-7b with Docker Model Runner:
```
docker model run hf.co/internlm/internlm-xcomposer2-7b
```

myownskyW7 commited on Feb 6, 2024

Commit

4d85c7e

verified ·

1 Parent(s): d0ae44d

Update modeling_internlm_xcomposer2.py

Browse files

raise value error for invalid <ImageHere> prompt format

Files changed (1) hide show

modeling_internlm_xcomposer2.py +4 -0

modeling_internlm_xcomposer2.py CHANGED Viewed

@@ -156,6 +156,7 @@ class InternLMXComposer2ForCausalLM(InternLM2PreTrainedModel):
             return_tensors='pt',
             padding='longest',
             truncation=True,
             add_special_tokens=add_special).to(self.device)
         targets = self.mask_human_targets(to_regress_tokens.input_ids)
@@ -175,6 +176,9 @@ class InternLMXComposer2ForCausalLM(InternLM2PreTrainedModel):
         parts = prompt.split('<ImageHere>')
         wrap_embeds, wrap_im_mask = [], []
         temp_len = 0
         for idx, part in enumerate(parts):
             if len(part) > 0:

             return_tensors='pt',
             padding='longest',
             truncation=True,
+            max_length=self.max_length,
             add_special_tokens=add_special).to(self.device)
         targets = self.mask_human_targets(to_regress_tokens.input_ids)
         parts = prompt.split('<ImageHere>')
         wrap_embeds, wrap_im_mask = [], []
         temp_len = 0
+        if len(parts) != image_nums + 1:
+            raise ValueError('Invalid <ImageHere> prompt format.')
         for idx, part in enumerate(parts):
             if len(part) > 0: