fmm170/SLAM-MetaMath-7B
06
1{2 "_name_or_path": "/localnvme/application/sc_new/fmm/pretrain_model/MetaMath-7B-V1.0",3 "architectures": [4 "LlamaForCausalLM"5 ],6 "attention_bias": false,7 "attention_dropout": 0.0,8 "bos_token_id": 1,9 "eos_token_id": 2,10 "hidden_act": "silu",11 "hidden_size": 4096,12 "initializer_range": 0.02,13 "intermediate_size": 11008,14 "max_position_embeddings": 4096,15 "model_type": "llama",16 "num_attention_heads": 32,17 "num_hidden_layers": 32,18 "num_key_value_heads": 32,19 "pad_token_id": 0,20 "pretraining_tp": 1,21 "rms_norm_eps": 1e-05,22 "rope_scaling": null,23 "rope_theta": 10000.0,24 "tie_word_embeddings": false,25 "torch_dtype": "bfloat16",26 "transformers_version": "4.38.1",27 "use_cache": false,28 "vocab_size": 3200129}30 