Text Generation
Transformers.js
ONNX
qwen3_5_text
webgpu
onnxruntime
onnxruntime-genai
q4
q4f16
int4
cuda
Mixture of Experts
conversational
Instructions to use webbrain-one/Ling-3.0-tiny-ONNX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers.js
How to use webbrain-one/Ling-3.0-tiny-ONNX with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('text-generation', 'webbrain-one/Ling-3.0-tiny-ONNX');
| { | |
| "model": { | |
| "bos_token_id": 1, | |
| "context_length": 131072, | |
| "decoder": { | |
| "session_options": { | |
| "log_id": "onnxruntime-genai", | |
| "provider_options": [ | |
| { | |
| "cuda": { | |
| "enable_cuda_graph": "0" | |
| } | |
| } | |
| ] | |
| }, | |
| "filename": "model.onnx", | |
| "head_size": 192, | |
| "hidden_size": 1536, | |
| "inputs": { | |
| "input_ids": "input_ids", | |
| "attention_mask": "attention_mask", | |
| "past_key_names": "past_key_values.%d.key", | |
| "past_value_names": "past_key_values.%d.value" | |
| }, | |
| "outputs": { | |
| "logits": "logits", | |
| "present_key_names": "present.%d.key", | |
| "present_value_names": "present.%d.value" | |
| }, | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 24, | |
| "num_key_value_heads": 16 | |
| }, | |
| "eos_token_id": 156895, | |
| "pad_token_id": 156892, | |
| "type": "qwen3_5_text", | |
| "vocab_size": 157184 | |
| }, | |
| "search": { | |
| "diversity_penalty": 0.0, | |
| "do_sample": false, | |
| "early_stopping": true, | |
| "length_penalty": 1.0, | |
| "max_length": 131072, | |
| "min_length": 0, | |
| "no_repeat_ngram_size": 0, | |
| "num_beams": 1, | |
| "num_return_sequences": 1, | |
| "past_present_share_buffer": true, | |
| "repetition_penalty": 1.0, | |
| "temperature": 1.0, | |
| "top_k": 20, | |
| "top_p": 0.95 | |
| } | |
| } |