| { |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "attn_output_gate": true, |
| "eos_token_id": 248044, |
| "full_attention_interval": 4, |
| "head_dim": 256, |
| "hidden_act": "silu", |
| "hidden_size": 2560, |
| "initializer_range": 0.02, |
| "intermediate_size": 9216, |
| "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_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_num_key_heads": 16, |
| "linear_num_value_heads": 32, |
| "linear_value_head_dim": 128, |
| "max_position_embeddings": 262144, |
| "mlp_only_layers": [], |
| "model_type": "qwen3_5_text", |
| "mtp_num_hidden_layers": 1, |
| "mtp_use_dedicated_embeddings": false, |
| "num_attention_heads": 16, |
| "num_hidden_layers": 32, |
| "num_key_value_heads": 4, |
| "rms_norm_eps": 1e-06, |
| "tie_word_embeddings": true, |
| "use_cache": false, |
| "vocab_size": 248320, |
| "mamba_ssm_dtype": "float32", |
| "rope_parameters": { |
| "mrope_interleaved": true, |
| "mrope_section": [ |
| 11, |
| 11, |
| 10 |
| ], |
| "rope_type": "default", |
| "rope_theta": 10000000, |
| "partial_rotary_factor": 0.25 |
| }, |
| "architectures": [ |
| "Qwen3_5ForSequenceClassification" |
| ], |
| "num_labels": 1, |
| "id2label": { |
| "0": "score" |
| }, |
| "label2id": { |
| "score": 0 |
| }, |
| "pad_token_id": 248044, |
| "torch_dtype": "float32", |
| "transformers_version": "4.57.0.dev0", |
| "system_one": { |
| "description": "Single-pass typed-decision scorer: score every (state, question, option) sequence, then softmax the option logits of each question after dividing by temperature.", |
| "state_prefix": "State:\n", |
| "tail_template": "\n\nQuestion:\n{question}\n\nOption:\n{option}", |
| "max_len": 384, |
| "truncation": "The state is truncated from its end so the question and option tail always fits.", |
| "padding_side": "right", |
| "pooling": "last non-pad token", |
| "temperature": 1.75, |
| "lora": { |
| "r": 16, |
| "alpha": 32, |
| "merged": true |
| } |
| }, |
| "transformers.js_config": { |
| "use_external_data_format": { |
| "model_q4.onnx": 3, |
| "model_q4f16.onnx": 3 |
| }, |
| "dtype": "q4f16", |
| "kv_cache_dtype": { |
| "q4f16": "float16", |
| "fp16": "float16" |
| } |
| } |
| } |
|
|
