bigscience/bloom-7b1-intermediate
0168
1{2 "apply_residual_connection_post_layernorm": false,3 "architectures": [4 "BloomForCausalLM"5 ],6 "attention_dropout": 0.0,7 "attention_softmax_in_fp32": true,8 "bias_dropout_fusion": true,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": 4096,17 "n_inner": null,18 "n_layer": 30,19 "num_attention_heads": 32,20 "offset_alibi": 100,21 "pad_token_id": 3,22 "pretraining_tp": 4,23 "seq_length": 2048,24 "skip_bias_add": true,25 "skip_bias_add_qkv": false,26 "slow_but_exact": false,27 "transformers_version": "4.21.0.dev0",28 "unk_token_id": 0,29 "use_cache": true,30 "vocab_size": 25088031}