Instructions to use ELBennett/Weevil-3M-QA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ELBennett/Weevil-3M-QA with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="ELBennett/Weevil-3M-QA", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("ELBennett/Weevil-3M-QA", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use ELBennett/Weevil-3M-QA with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ELBennett/Weevil-3M-QA" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ELBennett/Weevil-3M-QA", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/ELBennett/Weevil-3M-QA
- SGLang
How to use ELBennett/Weevil-3M-QA 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 "ELBennett/Weevil-3M-QA" \ --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": "ELBennett/Weevil-3M-QA", "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 "ELBennett/Weevil-3M-QA" \ --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": "ELBennett/Weevil-3M-QA", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use ELBennett/Weevil-3M-QA with Docker Model Runner:
docker model run hf.co/ELBennett/Weevil-3M-QA
Download export_metadata.json from ELBennett/Weevil-3M-QA: direct link, hf CLI and curl.
- Browser
- Download file 1.1 kB
-
https://huggingface.co/ELBennett/Weevil-3M-QA/resolve/main/export_metadata.json
- Command line
-
hf download hf://ELBennett/Weevil-3M-QA/export_metadata.json
-
curl -L -o export_metadata.json https://huggingface.co/ELBennett/Weevil-3M-QA/resolve/main/export_metadata.json
1.1 kB
| { | |
| "variant": "Weevil-3M-QA", | |
| "source_checkpoint": "reports/qa-latent-sub3m-90-10-wsd-8gpu-20261023/step-00014000", | |
| "source_model_sha256": "b42ea63e35e74c87718ef4465a7b5deb650a6e8a7ca328d6161cd35a3e15876b", | |
| "source_step": 14000, | |
| "parameters": 2993576, | |
| "model_spec": { | |
| "name": "weevil_latent_gdn2_sub3m_v1", | |
| "model_class": "WeevilSimpleParallel", | |
| "layers_per_stack": 8, | |
| "constructor": { | |
| "vocab_size": 4096, | |
| "embedding_dim": 128, | |
| "intermediate_size": 432 | |
| }, | |
| "gdn2_config": { | |
| "hidden_size": 144, | |
| "num_heads": 3, | |
| "key_head_dim": 48, | |
| "value_head_dim": 48, | |
| "qkv_rank": 48, | |
| "conv_kernel": 4, | |
| "norm_eps": 1e-06, | |
| "compute_dtype": "bfloat16", | |
| "mixer": "chunk", | |
| "chunk_size": null, | |
| "prefix_block_size": null | |
| }, | |
| "parameter_budget": { | |
| "exclusive_upper_limit": 3000000, | |
| "expected_total": 2993576, | |
| "embedding": 542720, | |
| "mlp": 1492992, | |
| "mixers": 956568, | |
| "normalization": 1296, | |
| "qkv_subset_of_mixers": 221184 | |
| } | |
| }, | |
| "weights_dtype": "float32" | |
| } | |