Instructions to use internlm/internlm-xcomposer2-7b-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use internlm/internlm-xcomposer2-7b-4bit with Transformers:

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

pipe = pipeline("text-generation", model="internlm/internlm-xcomposer2-7b-4bit", trust_remote_code=True)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("internlm/internlm-xcomposer2-7b-4bit", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use internlm/internlm-xcomposer2-7b-4bit 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-4bit"
# 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-4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/internlm/internlm-xcomposer2-7b-4bit

SGLang

How to use internlm/internlm-xcomposer2-7b-4bit 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-4bit" \
    --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-4bit",
		"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-4bit" \
        --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-4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use internlm/internlm-xcomposer2-7b-4bit with Docker Model Runner:
```
docker model run hf.co/internlm/internlm-xcomposer2-7b-4bit
```

Update README.md

by LinJulia - opened Feb 27, 2024

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

-2

Files changed (1) hide show

README.md +3 -2

README.md CHANGED Viewed

@@ -31,6 +31,7 @@ This is the 4-bit version of InternLM-XComposer2, install the latest version of
 ```python
 import torch, auto_gptq
 from transformers import AutoModel, AutoTokenizer
 from auto_gptq.modeling import BaseGPTQForCausalLM
@@ -62,12 +63,12 @@ img_path_list = [
 images = []
 for img_path in img_path_list:
     image = Image.open(img_path).convert("RGB")
-    image = quant_model.vis_processor(image)
     images.append(image)
 image = torch.stack(images)
 query = '<ImageHere> <ImageHere>please write an article based on the images. Title: my favorite animal.'
 with torch.cuda.amp.autocast():
-    response, history = quant_model.chat(tokenizer, query=query, image=image, history=[], do_sample=False)
 print(response)
 #My Favorite Animal: The Panda

 ```python
 import torch, auto_gptq
+from PIL import Image
 from transformers import AutoModel, AutoTokenizer
 from auto_gptq.modeling import BaseGPTQForCausalLM
 images = []
 for img_path in img_path_list:
     image = Image.open(img_path).convert("RGB")
+    image = model.vis_processor(image)
     images.append(image)
 image = torch.stack(images)
 query = '<ImageHere> <ImageHere>please write an article based on the images. Title: my favorite animal.'
 with torch.cuda.amp.autocast():
+    response, history = model.chat(tokenizer, query=query, image=image, history=[], do_sample=False)
 print(response)
 #My Favorite Animal: The Panda