bigscience/bloom-560m
375513k
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 "bias_dropout_fusion": true,9 "bos_token_id": 1,10 "eos_token_id": 2,11 "pad_token_id": 3,12 "unk_token_id": 0,13 "hidden_dropout": 0.0,14 "initializer_range": 0.02,15 "layer_norm_epsilon": 1e-05,16 "masked_softmax_fusion": true,17 "model_type": "bloom",18 "n_embed": 1024,19 "n_inner": null,20 "n_layer": 24,21 "num_attention_heads": 16,22 "offset_alibi": 100,23 "pretraining_tp": 1,24 "skip_bias_add": true,25 "skip_bias_add_qkv": false,26 "transformers_version": "4.20.0",27 "use_cache": true,28 "vocab_size": 25088029}