oddadmix/Nawah-Math-Reasoning
2823
1{2 "architectures": [3 "LlamaForCausalLM"4 ],5 "attention_bias": false,6 "attention_dropout": 0.0,7 "bos_token_id": 0,8 "dtype": "float32",9 "eos_token_id": 2,10 "head_dim": 64,11 "hidden_act": "silu",12 "hidden_size": 512,13 "initializer_range": 0.02,14 "intermediate_size": 1408,15 "max_position_embeddings": 2048,16 "mlp_bias": false,17 "model_type": "llama",18 "num_attention_heads": 8,19 "num_hidden_layers": 12,20 "num_key_value_heads": 4,21 "pad_token_id": 1,22 "pretraining_tp": 1,23 "rms_norm_eps": 1e-06,24 "rope_parameters": {25 "rope_theta": 10000,26 "rope_type": "default"27 },28 "tie_word_embeddings": true,29 "transformers_version": "5.15.0",30 "use_cache": true,31 "vocab_size": 3200432}33 