dwlee/ds_base_alpha
023
1{2 "_name_or_path": "DS-Base_Alpha/",3 "architectures": [4 "GPTNeoXForCausalLM"5 ],6 "bos_token_id": 0,7 "classifier_dropout": 0.1,8 "eos_token_id": 0,9 "hidden_act": "gelu",10 "hidden_size": 5120,11 "initializer_range": 0.02,12 "intermediate_size": 20480,13 "layer_norm_eps": 1e-05,14 "max_position_embeddings": 2048,15 "model_type": "gpt_neox",16 "num_attention_heads": 40,17 "num_hidden_layers": 40,18 "num_steps": "global_step301000",19 "rotary_emb_base": 10000,20 "rotary_pct": 0.5,21 "tie_word_embeddings": false,22 "torch_dtype": "float16",23 "transformers_version": "4.29.2",24 "use_cache": true,25 "use_parallel_residual": true,26 "vocab_size": 3000327}28 