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');
| { | |
| "architectures": [ | |
| "Qwen3_5ForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "embedding_dropout": 0.0, | |
| "eos_token_id": 156895, | |
| "expert_swiglu_limit_list": null, | |
| "first_k_dense_replace": 1, | |
| "gated_attention_proj_granularity_type": "head_wise", | |
| "group_norm_size": 1, | |
| "head_dim": 192, | |
| "hidden_act": "silu", | |
| "hidden_size": 1536, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4608, | |
| "kda_lower_bound": -5, | |
| "kda_safe_gate": true, | |
| "kv_lora_rank": 512, | |
| "layer_group_size": 4, | |
| "linear_silu": true, | |
| "max_position_embeddings": 131072, | |
| "max_window_layers": 20, | |
| "moe_intermediate_size": 512, | |
| "moe_router_enable_expert_bias": true, | |
| "moe_shared_expert_intermediate_size": 512, | |
| "mtp_loss_scaling_factor": 0, | |
| "mtp_use_kda": false, | |
| "n_group": 8, | |
| "no_kda_lora": true, | |
| "norm_topk_prob": true, | |
| "num_attention_heads": 16, | |
| "num_experts": 128, | |
| "num_experts_per_tok": 8, | |
| "num_hidden_layers": 24, | |
| "num_key_value_heads": 16, | |
| "num_kv_heads_for_linear_attn": 0, | |
| "num_nextn_predict_layers": 0, | |
| "num_shared_experts": 1, | |
| "output_dropout": 0.0, | |
| "output_router_logits": false, | |
| "pad_token_id": 156892, | |
| "partial_rotary_factor": 0.3333333333333333, | |
| "q_lora_rank": 256, | |
| "qk_head_dim": 192, | |
| "qk_nope_head_dim": 128, | |
| "qk_rope_head_dim": 64, | |
| "rms_norm_eps": 1e-06, | |
| "rope_interleave": true, | |
| "rope_scaling": null, | |
| "rope_theta": 6000000, | |
| "rotary_dim": 64, | |
| "routed_scaling_factor": 2.5, | |
| "router_dtype": "fp32", | |
| "scale_router_input": false, | |
| "score_function": "sigmoid", | |
| "scoring_func": "sigmoid", | |
| "seq_aux": true, | |
| "share_expert_swiglu_limit_list": null, | |
| "short_conv_kernel_size": 4, | |
| "tie_word_embeddings": false, | |
| "topk_group": 4, | |
| "topk_method": "noaux_tc", | |
| "transformers_version": "4.45.0", | |
| "up_proj_norm": false, | |
| "use_bias": false, | |
| "use_cache": true, | |
| "use_kda_lora": false, | |
| "use_mla_nope": false, | |
| "use_nGPT": false, | |
| "use_qk_norm": true, | |
| "use_qkv_bias": false, | |
| "v_head_dim": 128, | |
| "value_norm": false, | |
| "vocab_size": 157184, | |
| "model_type": "qwen3_5_text", | |
| "torch_dtype": "bfloat16", | |
| "dtype": "float16", | |
| "full_attention_interval": 4, | |
| "layer_types": [ | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention" | |
| ], | |
| "linear_conv_kernel_dim": 4, | |
| "linear_key_head_dim": 128, | |
| "linear_value_head_dim": 128, | |
| "linear_num_key_heads": 16, | |
| "linear_num_value_heads": 16, | |
| "mamba_ssm_dtype": "float16", | |
| "rope_parameters": { | |
| "mrope_interleaved": true, | |
| "partial_rotary_factor": 0.3333333333333333, | |
| "rope_theta": 6000000, | |
| "rope_type": "default" | |
| }, | |
| "transformers.js_config": { | |
| "use_external_data_format": { | |
| "model_q4f16.onnx": 3 | |
| }, | |
| "kv_cache_dtype": { | |
| "q4f16": "float16" | |
| } | |
| } | |
| } | |