JerrrrryKun/DeepMath-1.5B-LLM4Math-V2data-Sequential-perturbationsignalonly-400steps
012
1{2 "architectures": [3 "Qwen2ForCausalLM"4 ],5 "attention_dropout": 0.0,6 "bos_token_id": 151646,7 "dtype": "float32",8 "embd_pdrop": 0.0,9 "eos_token_id": 151643,10 "hidden_act": "silu",11 "hidden_size": 1536,12 "initializer_range": 0.02,13 "intermediate_size": 8960,14 "layer_types": [15 "full_attention",16 "full_attention",17 "full_attention",18 "full_attention",19 "full_attention",20 "full_attention",21 "full_attention",22 "full_attention",23 "full_attention",24 "full_attention",25 "full_attention",26 "full_attention",27 "full_attention",28 "full_attention",29 "full_attention",30 "full_attention",31 "full_attention",32 "full_attention",33 "full_attention",34 "full_attention",35 "full_attention",36 "full_attention",37 "full_attention",38 "full_attention",39 "full_attention",40 "full_attention",41 "full_attention",42 "full_attention"43 ],44 "max_position_embeddings": 131072,45 "max_window_layers": 21,46 "model_type": "qwen2",47 "num_attention_heads": 12,48 "num_hidden_layers": 28,49 "num_key_value_heads": 2,50 "pad_token_id": 151643,51 "resid_pdrop": 0.0,52 "rms_norm_eps": 1e-06,53 "rope_scaling": null,54 "rope_theta": 10000,55 "sliding_window": null,56 "tie_word_embeddings": false,57 "transformers_version": "4.56.0",58 "use_cache": true,59 "use_mrope": false,60 "use_sliding_window": false,61 "vocab_size": 15193662}63 