config.json
| 1 | { |
| 2 | "transformers_version": "5.16.1", |
| 3 | "architectures": [ |
| 4 | "Qwen3_5ForCausalLM" |
| 5 | ], |
| 6 | "output_hidden_states": false, |
| 7 | "return_dict": true, |
| 8 | "dtype": "bfloat16", |
| 9 | "chunk_size_feed_forward": 0, |
| 10 | "is_encoder_decoder": false, |
| 11 | "id2label": { |
| 12 | "0": "LABEL_0", |
| 13 | "1": "LABEL_1" |
| 14 | }, |
| 15 | "label2id": { |
| 16 | "LABEL_0": 0, |
| 17 | "LABEL_1": 1 |
| 18 | }, |
| 19 | "problem_type": null, |
| 20 | "vocab_size": 248320, |
| 21 | "hidden_size": 4096, |
| 22 | "intermediate_size": 12288, |
| 23 | "num_hidden_layers": 32, |
| 24 | "num_attention_heads": 16, |
| 25 | "num_key_value_heads": 4, |
| 26 | "hidden_act": "silu", |
| 27 | "max_position_embeddings": 262144, |
| 28 | "initializer_range": 0.02, |
| 29 | "rms_norm_eps": 1e-06, |
| 30 | "use_cache": true, |
| 31 | "tie_word_embeddings": false, |
| 32 | "rope_parameters": { |
| 33 | "mrope_interleaved": true, |
| 34 | "mrope_section": [ |
| 35 | 11, |
| 36 | 11, |
| 37 | 10 |
| 38 | ], |
| 39 | "rope_type": "default", |
| 40 | "rope_theta": 10000000, |
| 41 | "partial_rotary_factor": 0.25 |
| 42 | }, |
| 43 | "attention_bias": false, |
| 44 | "attention_dropout": 0.0, |
| 45 | "head_dim": 256, |
| 46 | "linear_conv_kernel_dim": 4, |
| 47 | "linear_key_head_dim": 128, |
| 48 | "linear_value_head_dim": 128, |
| 49 | "linear_num_key_heads": 16, |
| 50 | "linear_num_value_heads": 32, |
| 51 | "layer_types": [ |
| 52 | "linear_attention", |
| 53 | "linear_attention", |
| 54 | "linear_attention", |
| 55 | "full_attention", |
| 56 | "linear_attention", |
| 57 | "linear_attention", |
| 58 | "linear_attention", |
| 59 | "full_attention", |
| 60 | "linear_attention", |
| 61 | "linear_attention", |
| 62 | "linear_attention", |
| 63 | "full_attention", |
| 64 | "linear_attention", |
| 65 | "linear_attention", |
| 66 | "linear_attention", |
| 67 | "full_attention", |
| 68 | "linear_attention", |
| 69 | "linear_attention", |
| 70 | "linear_attention", |
| 71 | "full_attention", |
| 72 | "linear_attention", |
| 73 | "linear_attention", |
| 74 | "linear_attention", |
| 75 | "full_attention", |
| 76 | "linear_attention", |
| 77 | "linear_attention", |
| 78 | "linear_attention", |
| 79 | "full_attention", |
| 80 | "linear_attention", |
| 81 | "linear_attention", |
| 82 | "linear_attention", |
| 83 | "full_attention" |
| 84 | ], |
| 85 | "pad_token_id": null, |
| 86 | "bos_token_id": null, |
| 87 | "eos_token_id": 248044, |
| 88 | "_name_or_path": "", |
| 89 | "attn_output_gate": true, |
| 90 | "full_attention_interval": 4, |
| 91 | "mlp_only_layers": [], |
| 92 | "model_type": "qwen3_5_text", |
| 93 | "mtp_num_hidden_layers": 1, |
| 94 | "mtp_use_dedicated_embeddings": false, |
| 95 | "mamba_ssm_dtype": "float32", |
| 96 | "partial_rotary_factor": 0.25, |
| 97 | "output_attentions": false |
| 98 | } |