Instructions to use zai-org/cogvlm-chat-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use zai-org/cogvlm-chat-hf with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="zai-org/cogvlm-chat-hf", trust_remote_code=True, device_map="auto")# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("zai-org/cogvlm-chat-hf", trust_remote_code=True, dtype="auto", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use zai-org/cogvlm-chat-hf with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "zai-org/cogvlm-chat-hf" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "zai-org/cogvlm-chat-hf", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/zai-org/cogvlm-chat-hf
- SGLang
How to use zai-org/cogvlm-chat-hf 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 "zai-org/cogvlm-chat-hf" \ --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": "zai-org/cogvlm-chat-hf", "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 "zai-org/cogvlm-chat-hf" \ --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": "zai-org/cogvlm-chat-hf", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use zai-org/cogvlm-chat-hf with Docker Model Runner:
docker model run hf.co/zai-org/cogvlm-chat-hf
Is the hf version the same as the biligual demo version in Chatglm.cn?
#1
by jaywanghz - opened
Is it biligual version?
Any setup for its api application?
Thanks.
I tried the demo version and i want to see it is one of the best so far, compared to the other open ones even GPT 4.
In Github repo, it shows that there will be one better version available soon, will be still be 17b or bigger?
No, it's an English version. The bilingual version will release recently.
Thanks
chenkq changed discussion status to closed