Text Generation
Transformers
Safetensors
glm
glm-4
fp8
llmcompressor
conversational
compressed-tensors
Instructions to use GizzmoShifu/glm-4-9b-chat-hf-fp8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use GizzmoShifu/glm-4-9b-chat-hf-fp8 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="GizzmoShifu/glm-4-9b-chat-hf-fp8") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("GizzmoShifu/glm-4-9b-chat-hf-fp8") model = AutoModelForCausalLM.from_pretrained("GizzmoShifu/glm-4-9b-chat-hf-fp8", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use GizzmoShifu/glm-4-9b-chat-hf-fp8 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "GizzmoShifu/glm-4-9b-chat-hf-fp8" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "GizzmoShifu/glm-4-9b-chat-hf-fp8", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/GizzmoShifu/glm-4-9b-chat-hf-fp8
- SGLang
How to use GizzmoShifu/glm-4-9b-chat-hf-fp8 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 "GizzmoShifu/glm-4-9b-chat-hf-fp8" \ --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": "GizzmoShifu/glm-4-9b-chat-hf-fp8", "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 "GizzmoShifu/glm-4-9b-chat-hf-fp8" \ --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": "GizzmoShifu/glm-4-9b-chat-hf-fp8", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use GizzmoShifu/glm-4-9b-chat-hf-fp8 with Docker Model Runner:
docker model run hf.co/GizzmoShifu/glm-4-9b-chat-hf-fp8
Download tokenizer.json from GizzmoShifu/glm-4-9b-chat-hf-fp8: direct link, hf CLI and curl.
- Browser
- Download file 20 MB
-
https://huggingface.co/GizzmoShifu/glm-4-9b-chat-hf-fp8/resolve/main/tokenizer.json
- Command line
-
hf download hf://GizzmoShifu/glm-4-9b-chat-hf-fp8/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/GizzmoShifu/glm-4-9b-chat-hf-fp8/resolve/main/tokenizer.json
20 MB
- Xet hash:
- af4cf6b6d5408795a506dd2547ba2fd02da7e4c1ad820f1ddca1f89f270ca906
- Size of remote file:
- 20 MB
- SHA256:
- 4bb2ad0477770e00c576b5819aa2943a0be5b8489d4cc2e2a120fbec9a00d1c0
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.