| { |
| "architectures": [ |
| "Qwen3ForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 50256, |
| "dtype": "bfloat16", |
| "eos_token_id": 50256, |
| "head_dim": 64, |
| "hidden_act": "silu", |
| "hidden_size": 384, |
| "initializer_range": 0.02, |
| "intermediate_size": 1024, |
| "layer_types": [ |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "full_attention" |
| ], |
| "max_position_embeddings": 8192, |
| "max_window_layers": 9, |
| "model_type": "qwen3", |
| "num_attention_heads": 6, |
| "num_hidden_layers": 12, |
| "num_key_value_heads": 2, |
| "pad_token_id": 50256, |
| "query_pre_attn_scalar": 256, |
| "rms_norm_eps": 1e-06, |
| "rope_parameters": { |
| "rope_theta": 500000, |
| "rope_type": "default" |
| }, |
| "sliding_window": 512, |
| "tie_word_embeddings": true, |
| "transformers_version": "5.5.4", |
| "use_cache": false, |
| "use_sliding_window": true, |
| "vocab_size": 50257 |
| } |
|
|
