IDoNotHaveAName/X-R1-3epoch
06
1{2 "_name_or_path": "/root/trained_model/output-experiment2/X-R1-1.5B-experiment",3 "architectures": [4 "Qwen2ForCausalLM"5 ],6 "attention_dropout": 0.0,7 "bos_token_id": 151643,8 "eos_token_id": 151643,9 "hidden_act": "silu",10 "hidden_size": 1536,11 "initializer_range": 0.02,12 "intermediate_size": 8960,13 "max_position_embeddings": 131072,14 "max_window_layers": 28,15 "model_type": "qwen2",16 "num_attention_heads": 12,17 "num_hidden_layers": 28,18 "num_key_value_heads": 2,19 "rms_norm_eps": 1e-06,20 "rope_scaling": null,21 "rope_theta": 1000000.0,22 "sliding_window": null,23 "tie_word_embeddings": true,24 "torch_dtype": "bfloat16",25 "transformers_version": "4.48.2",26 "use_cache": true,27 "use_mrope": false,28 "use_sliding_window": false,29 "vocab_size": 15193630}31 