Text Generation
Transformers.js
ONNX
English
Russian
qwen3
rag
faithful-qa
occ
onnxruntime
webgpu
conversational
Instructions to use occ-ai/OCC-RAG-0.6B-ONNX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers.js
How to use occ-ai/OCC-RAG-0.6B-ONNX with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('text-generation', 'occ-ai/OCC-RAG-0.6B-ONNX');
Download quantize_config.json from occ-ai/OCC-RAG-0.6B-ONNX: direct link, hf CLI and curl.
- Browser
- Download file 261 Bytes
-
https://huggingface.co/occ-ai/OCC-RAG-0.6B-ONNX/resolve/main/quantize_config.json
- Command line
-
hf download hf://occ-ai/OCC-RAG-0.6B-ONNX/quantize_config.json
-
curl -L -o quantize_config.json https://huggingface.co/occ-ai/OCC-RAG-0.6B-ONNX/resolve/main/quantize_config.json
261 Bytes
| { | |
| "modes": [ | |
| "q4f16", | |
| "fp16", | |
| "q4", | |
| "q8" | |
| ], | |
| "per_channel": true, | |
| "reduce_range": true, | |
| "block_size": null, | |
| "is_symmetric": true, | |
| "accuracy_level": null, | |
| "quant_type": 1, | |
| "op_block_list": null | |
| } |