| { | |
| "architectures": [ | |
| "Qwen2ForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151643, | |
| "hidden_act": "silu", | |
| "hidden_size": 1536, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 8960, | |
| "max_position_embeddings": 131072, | |
| "max_window_layers": 28, | |
| "model_card": "\nFinal Loss: 0.1743\nBatch Size: 1024\nLearning Rate: 2e-05\nDataset Size: 59966\n", | |
| "model_type": "qwen2", | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 28, | |
| "num_key_value_heads": 2, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": 131072, | |
| "tie_word_embeddings": true, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.51.2", | |
| "use_cache": false, | |
| "use_mrope": false, | |
| "use_sliding_window": false, | |
| "vocab_size": 151936 | |
| } | |