| { |
| "_name_or_path": "bigscience/bloom-6b3", |
| "apply_residual_connection_post_layernorm": false, |
| "attention_dropout": 0.0, |
| "attention_softmax_in_fp32": true, |
| "bias_dropout_fusion": true, |
| "bos_token_id": 1, |
| "eos_token_id": 2, |
| "hidden_dropout": 0.0, |
| "initializer_range": 0.02, |
| "layer_norm_epsilon": 1e-05, |
| "masked_softmax_fusion": true, |
| "model_type": "bloom", |
| "n_embed": 4096, |
| "n_inner": null, |
| "n_layer": 30, |
| "num_attention_heads": 32, |
| "offset_alibi": 100, |
| "pad_token_id": 3, |
| "pretraining_tp": 4, |
| "seq_length": 2048, |
| "skip_bias_add": true, |
| "skip_bias_add_qkv": false, |
| "slow_but_exact": false, |
| "transformers_version": "4.21.0.dev0", |
| "unk_token_id": 0, |
| "use_cache": false, |
| "vocab_size": 250880 |
| } |
|
|
