Instructions to use codefuse-ai/CodeFuse-VLM-14B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use codefuse-ai/CodeFuse-VLM-14B with Transformers:

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

pipe = pipeline("text-generation", model="codefuse-ai/CodeFuse-VLM-14B", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("codefuse-ai/CodeFuse-VLM-14B", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use codefuse-ai/CodeFuse-VLM-14B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "codefuse-ai/CodeFuse-VLM-14B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "codefuse-ai/CodeFuse-VLM-14B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/codefuse-ai/CodeFuse-VLM-14B

SGLang

How to use codefuse-ai/CodeFuse-VLM-14B 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 "codefuse-ai/CodeFuse-VLM-14B" \
    --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": "codefuse-ai/CodeFuse-VLM-14B",
		"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 "codefuse-ai/CodeFuse-VLM-14B" \
        --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": "codefuse-ai/CodeFuse-VLM-14B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use codefuse-ai/CodeFuse-VLM-14B with Docker Model Runner:
```
docker model run hf.co/codefuse-ai/CodeFuse-VLM-14B
```

codefuse-admin commited on Jan 24, 2024

Commit

57542a6

1 Parent(s): f9e02c9

fix readme

Browse files

Files changed (1) hide show

README.md +5 -0

README.md CHANGED Viewed

@@ -1,3 +1,8 @@
 ## CodeFuse-VLM
 CodeFuse-VLM is a Multimodal LLM(MLLM) framework that provides users with multiple vision encoders, multimodal alignment adapters, and LLMs. Through CodeFuse-VLM framework, users are able to customize their own MLLM model to adapt their own tasks.
 As more and more models are published on Huggingface community, there will be more open-source vision encoders and LLMs. Each of these models has their own specialties, e.g. Code-LLama is good at code-related tasks but has poor performance for Chinese tasks. Therefore, we built CodeFuse-VLM framework to support multiple vision encoders, multimodal alignment adapters, and LLMs to adapt different types of tasks.

+---
+license: other
+tasks:
+- code-generation
+---
 ## CodeFuse-VLM
 CodeFuse-VLM is a Multimodal LLM(MLLM) framework that provides users with multiple vision encoders, multimodal alignment adapters, and LLMs. Through CodeFuse-VLM framework, users are able to customize their own MLLM model to adapt their own tasks.
 As more and more models are published on Huggingface community, there will be more open-source vision encoders and LLMs. Each of these models has their own specialties, e.g. Code-LLama is good at code-related tasks but has poor performance for Chinese tasks. Therefore, we built CodeFuse-VLM framework to support multiple vision encoders, multimodal alignment adapters, and LLMs to adapt different types of tasks.