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');
File size: 1,052 Bytes
768e6d6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 | {
"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
}
}
|