| { |
| "architectures": [ |
| "Qwen3ForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "eos_token_id": 151645, |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 2560, |
| "initializer_range": 0.02, |
| "intermediate_size": 9728, |
| "layer_types": [ |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention", |
| "full_attention" |
| ], |
| "max_position_embeddings": 262144, |
| "max_window_layers": 36, |
| "model_type": "qwen3", |
| "num_attention_heads": 32, |
| "num_hidden_layers": 36, |
| "num_key_value_heads": 8, |
| "pad_token_id": 151654, |
| "quantization_config": { |
| "include_input_output_embeddings": false, |
| "modules_to_not_convert": null, |
| "quant_method": "torchao", |
| "quant_type": { |
| "default": { |
| "_data": { |
| "group_size": 128, |
| "int4_choose_qparams_algorithm": { |
| "_data": "TINYGEMM", |
| "_type": "Int4ChooseQParamsAlgorithm" |
| }, |
| "int4_packing_format": { |
| "_data": "PLAIN", |
| "_type": "Int4PackingFormat" |
| }, |
| "layout": { |
| "_data": { |
| "inner_k_tiles": 8 |
| }, |
| "_type": "TensorCoreTiledLayout", |
| "_version": 1 |
| }, |
| "preserve_zero": null, |
| "set_inductor_config": true, |
| "use_hqq": false, |
| "zero_point_domain": { |
| "_data": "NONE", |
| "_type": "ZeroPointDomain" |
| } |
| }, |
| "_type": "Int4WeightOnlyConfig", |
| "_version": 2 |
| } |
| }, |
| "quant_type_kwargs": {}, |
| "untie_embedding_weights": false |
| }, |
| "rms_norm_eps": 1e-06, |
| "rope_scaling": null, |
| "rope_theta": 5000000, |
| "sliding_window": null, |
| "tie_word_embeddings": true, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.55.4", |
| "unsloth_fixed": true, |
| "unsloth_version": "2026.1.4", |
| "use_cache": true, |
| "use_sliding_window": false, |
| "vocab_size": 151936 |
| } |
|
|
