| { | |
| "architectures": [ | |
| "Qwen3ForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "binning_power": 2.0, | |
| "bos_token_id": 1, | |
| "context_length": 256, | |
| "eos_token_id": 1, | |
| "exponential_base": 1.01, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 256, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 1024, | |
| "max_position_embeddings": 40960, | |
| "max_window_layers": 28, | |
| "model_type": "qwen3", | |
| "n_special_tokens": 2, | |
| "num_attention_heads": 8, | |
| "num_hidden_layers": 8, | |
| "num_key_value_heads": 8, | |
| "pad_token_id": 0, | |
| "prediction_length": 64, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 1000000, | |
| "sliding_window": null, | |
| "tie_word_embeddings": true, | |
| "tokenizer_class": "NonUniformBins", | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.52.4", | |
| "use_cache": true, | |
| "use_eos_token": false, | |
| "use_sliding_window": false, | |
| "vocab_size": 4096 | |
| } | |