pcmoritz/qwen3-tiny-test

1{2  "architectures": [3    "Qwen3ForCausalLM"4  ],5  "attention_bias": false,6  "attention_dropout": 0.0,7  "bos_token_id": 151643,8  "dtype": "bfloat16",9  "eos_token_id": 151645,10  "head_dim": 128,11  "hidden_act": "silu",12  "hidden_size": 1024,13  "initializer_range": 0.02,14  "intermediate_size": 3072,15  "layer_types": [16    "full_attention",17    "full_attention",18    "full_attention",19    "full_attention",20    "full_attention",21    "full_attention",22    "full_attention"23  ],24  "max_position_embeddings": 40960,25  "max_window_layers": 28,26  "model_type": "qwen3",27  "num_attention_heads": 16,28  "num_hidden_layers": 7,29  "num_key_value_heads": 8,30  "rms_norm_eps": 1e-06,31  "rope_scaling": null,32  "rope_theta": 1000000,33  "sliding_window": null,34  "tie_word_embeddings": true,35  "transformers_version": "4.56.2",36  "use_cache": true,37  "use_sliding_window": false,38  "vocab_size": 15193639}40