sgpt-bloom-7b1-msmarco / config.json
cakiki's picture
Fix architecture (#1)
a739252
{
"_name_or_path": "/gpfsscratch/rech/six/commun/commun/experiments/muennighoff/bloomckpt/6b3/bloom-7b1",
"apply_residual_connection_post_layernorm": false,
"architectures": [
"BloomForCausalLM"
],
"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,
"torch_dtype": "float32",
"transformers_version": "4.20.1",
"unk_token_id": 0,
"use_cache": true,
"vocab_size": 250682
}