lifeofcoding/mastermax-7b

1{2  "_name_or_path": "lifeofcoding/mastermax-7b",3  "alibi": false,4  "apply_residual_connection_post_layernorm": false,5  "architectures": [6    "RWForCausalLM"7  ],8  "attention_dropout": 0.0,9  "auto_map": {10    "AutoConfig": "lifeofcoding/mastermax-7b--configuration_RW.RWConfig",11    "AutoModel": "lifeofcoding/mastermax-7b--modelling_RW.RWModel",12    "AutoModelForCausalLM": "lifeofcoding/mastermax-7b--modelling_RW.RWForCausalLM",13    "AutoModelForQuestionAnswering": "lifeofcoding/mastermax-7b--modelling_RW.RWForQuestionAnswering",14    "AutoModelForSequenceClassification": "lifeofcoding/mastermax-7b--modelling_RW.RWForSequenceClassification",15    "AutoModelForTokenClassification": "lifeofcoding/mastermax-7b--modelling_RW.RWForTokenClassification"16  },17  "bias": false,18  "bos_token_id": 11,19  "eos_token_id": 11,20  "hidden_dropout": 0.0,21  "hidden_size": 4544,22  "initializer_range": 0.02,23  "layer_norm_epsilon": 1e-05,24  "model_type": "RefinedWebModel",25  "multi_query": true,26  "n_head": 71,27  "n_layer": 32,28  "parallel_attn": true,29  "torch_dtype": "bfloat16",30  "transformers_version": "4.31.0.dev0",31  "use_cache": true,32  "vocab_size": 6502433}34