bigscience/bloom
5.1k14k
1{2 "apply_residual_connection_post_layernorm": false,3 "attention_dropout": 0.0,4 "architectures": [5 "BloomForCausalLM"6 ],7 "attention_softmax_in_fp32": true,8 "pad_token_id": 3,9 "bos_token_id": 1,10 "eos_token_id": 2,11 "hidden_dropout": 0.0,12 "initializer_range": 0.02,13 "layer_norm_epsilon": 1e-05,14 "masked_softmax_fusion": true,15 "model_type": "bloom",16 "n_embed": 14336,17 "n_layer": 70,18 "num_attention_heads": 112,19 "pretraining_tp": 4,20 "slow_but_exact": false,21 "transformers_version": "4.21.0",22 "use_cache": true,23 "vocab_size": 25088024}