Text Generation
Transformers
Safetensors
afmoe
reap
trinity
w4a16
conversational
custom_code
4-bit precision
auto-round
Instructions to use 0xSero/Trinity-337B-W4A16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use 0xSero/Trinity-337B-W4A16 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="0xSero/Trinity-337B-W4A16", trust_remote_code=True) messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("0xSero/Trinity-337B-W4A16", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained("0xSero/Trinity-337B-W4A16", trust_remote_code=True) 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=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use 0xSero/Trinity-337B-W4A16 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "0xSero/Trinity-337B-W4A16" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "0xSero/Trinity-337B-W4A16", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/0xSero/Trinity-337B-W4A16
- SGLang
How to use 0xSero/Trinity-337B-W4A16 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 "0xSero/Trinity-337B-W4A16" \ --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": "0xSero/Trinity-337B-W4A16", "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 "0xSero/Trinity-337B-W4A16" \ --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": "0xSero/Trinity-337B-W4A16", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use 0xSero/Trinity-337B-W4A16 with Docker Model Runner:
docker model run hf.co/0xSero/Trinity-337B-W4A16
| { | |
| "bits": 4, | |
| "data_type": "int", | |
| "group_size": 128, | |
| "sym": true, | |
| "batch_size": 1, | |
| "iters": 0, | |
| "low_gpu_mem_usage": true, | |
| "autoround_version": "0.12.2", | |
| "quant_method": "auto-round", | |
| "packing_format": "auto_round:auto_gptq", | |
| "extra_config": { | |
| "model.layers.6.mlp.router.gate": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.layers.7.mlp.router.gate": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.layers.8.mlp.router.gate": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.layers.9.mlp.router.gate": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.layers.10.mlp.router.gate": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.layers.11.mlp.router.gate": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.layers.12.mlp.router.gate": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.layers.13.mlp.router.gate": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.layers.14.mlp.router.gate": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.layers.15.mlp.router.gate": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.layers.16.mlp.router.gate": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.layers.17.mlp.router.gate": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.layers.18.mlp.router.gate": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.layers.19.mlp.router.gate": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.layers.20.mlp.router.gate": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.layers.21.mlp.router.gate": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.layers.22.mlp.router.gate": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.layers.23.mlp.router.gate": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.layers.24.mlp.router.gate": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.layers.25.mlp.router.gate": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.layers.26.mlp.router.gate": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.layers.27.mlp.router.gate": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.layers.28.mlp.router.gate": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.layers.29.mlp.router.gate": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.layers.30.mlp.router.gate": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.layers.31.mlp.router.gate": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.layers.32.mlp.router.gate": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.layers.33.mlp.router.gate": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.layers.34.mlp.router.gate": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.layers.35.mlp.router.gate": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.layers.36.mlp.router.gate": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.layers.37.mlp.router.gate": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.layers.38.mlp.router.gate": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.layers.39.mlp.router.gate": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.layers.40.mlp.router.gate": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.layers.41.mlp.router.gate": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.layers.42.mlp.router.gate": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.layers.43.mlp.router.gate": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.layers.44.mlp.router.gate": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.layers.45.mlp.router.gate": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.layers.46.mlp.router.gate": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.layers.47.mlp.router.gate": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.layers.48.mlp.router.gate": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.layers.49.mlp.router.gate": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.layers.50.mlp.router.gate": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.layers.51.mlp.router.gate": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.layers.52.mlp.router.gate": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.layers.53.mlp.router.gate": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.layers.54.mlp.router.gate": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.layers.55.mlp.router.gate": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.layers.56.mlp.router.gate": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.layers.57.mlp.router.gate": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.layers.58.mlp.router.gate": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| }, | |
| "model.layers.59.mlp.router.gate": { | |
| "bits": 16, | |
| "data_type": "fp" | |
| } | |
| } | |
| } |