MisterAI/bigscience_bloom-560m
075
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 "dtype": "float16",11 "eos_token_id": 2,12 "hidden_dropout": 0.0,13 "hidden_size": 1024,14 "initializer_range": 0.02,15 "layer_norm_epsilon": 1e-05,16 "masked_softmax_fusion": true,17 "model_type": "bloom",18 "n_head": 16,19 "n_inner": null,20 "n_layer": 24,21 "offset_alibi": 100,22 "pad_token_id": 3,23 "pretraining_tp": 1,24 "skip_bias_add": true,25 "skip_bias_add_qkv": false,26 "slow_but_exact": false,27 "tie_word_embeddings": true,28 "transformers_version": "5.5.0",29 "unk_token_id": 0,30 "use_cache": true,31 "vocab_size": 25088032}33 