Instructions to use yaycute/qwen2.5-coder-0.5b-block with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers.js
How to use yaycute/qwen2.5-coder-0.5b-block with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('text-generation', 'yaycute/qwen2.5-coder-0.5b-block');
| {"dtype": "float16", "order": ["n2w", "Wgate", "Wup", "Wdown", "nfw", "Wlm"], "tensors": {"n2w": {"shape": [896], "offset": 0, "count": 896}, "Wgate": {"shape": [4864, 896], "offset": 896, "count": 4358144}, "Wup": {"shape": [4864, 896], "offset": 4359040, "count": 4358144}, "Wdown": {"shape": [896, 4864], "offset": 8717184, "count": 4358144}, "nfw": {"shape": [896], "offset": 13075328, "count": 896}, "Wlm": {"shape": [151936, 896], "offset": 13076224, "count": 136134656}}} |