Text Generation
Transformers.js
ONNX
llama
webgpu
q4f16
gptq
tool-calling
experimental
conversational
Instructions to use webbrain-one/webbrain-compass-tiny-v2.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers.js
How to use webbrain-one/webbrain-compass-tiny-v2.1 with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('text-generation', 'webbrain-one/webbrain-compass-tiny-v2.1');
| { | |
| "_from_model_config": true, | |
| "bos_token_id": 0, | |
| "eos_token_id": [ | |
| 1, | |
| 130073 | |
| ], | |
| "pad_token_id": 1, | |
| "transformers_version": "5.16.1", | |
| "use_cache": true | |
| } | |