Instructions to use kucukkanat/LFM2.5-Encoder-350M-Prompt-Router-ONNX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers.js
How to use kucukkanat/LFM2.5-Encoder-350M-Prompt-Router-ONNX with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('zero-shot-classification', 'kucukkanat/LFM2.5-Encoder-350M-Prompt-Router-ONNX');
| { | |
| "model_type": "lfm2-bidirectional", | |
| "architectures": [ | |
| "TwoTowerGraph" | |
| ], | |
| "task": "zero-shot-routing", | |
| "source_model": "LiquidAI/LFM2.5-Encoder-350M-Prompt-Router", | |
| "hidden_size": 1024, | |
| "vocab_size": 65536, | |
| "real_vocab_size": 64402, | |
| "num_hidden_layers": 16, | |
| "layer_types": [ | |
| "conv", | |
| "conv", | |
| "full_attention", | |
| "conv", | |
| "conv", | |
| "full_attention", | |
| "conv", | |
| "conv", | |
| "full_attention", | |
| "conv", | |
| "full_attention", | |
| "conv", | |
| "full_attention", | |
| "conv", | |
| "full_attention", | |
| "conv" | |
| ], | |
| "max_position_embeddings": 128000, | |
| "transformers.js_config": { | |
| "kv_cache_dtype": null, | |
| "use_external_data_format": false | |
| }, | |
| "onnx": { | |
| "inputs": [ | |
| "input_ids", | |
| "attention_mask" | |
| ], | |
| "outputs": [ | |
| "token_proj", | |
| "rule_proj" | |
| ] | |
| }, | |
| "head": { | |
| "kind": "cosine", | |
| "normalize": true, | |
| "scale": 1.3714938163757324, | |
| "bias": -0.2723352313041687, | |
| "activation": "softmax", | |
| "prefix_heading": "Categories", | |
| "proj_dim": 256 | |
| } | |
| } | |