| { | |
| "architectures": [ | |
| "Qwen3ForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "head_dim": 64, | |
| "hidden_act": "silu", | |
| "hidden_size": 384, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 1216, | |
| "max_position_embeddings": 512, | |
| "max_window_layers": 6, | |
| "model_type": "qwen3", | |
| "num_attention_heads": 6, | |
| "num_hidden_layers": 6, | |
| "num_key_value_heads": 2, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": null, | |
| "tie_word_embeddings": true, | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.45.0", | |
| "use_cache": true, | |
| "use_qk_norm": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 6400, | |
| "_name_or_path": "ClearMind-Small" | |
| } |