bigscience-bot
commited on
Commit
•
bea8142
1
Parent(s):
e0e6b58
new data
Browse files- config.json +1 -9
- pytorch_model.bin.index.json +1 -1
config.json
CHANGED
@@ -2,26 +2,18 @@
|
|
2 |
"apply_residual_connection_post_layernorm": false,
|
3 |
"attention_dropout": 0.0,
|
4 |
"attention_softmax_in_fp32": true,
|
5 |
-
"bias_dropout_fusion": true,
|
6 |
"bos_token_id": 1,
|
7 |
-
"dtype": "bfloat16",
|
8 |
"eos_token_id": 2,
|
9 |
-
"pad_token_id": 3,
|
10 |
-
"unk_token_id": 0,
|
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": 14336,
|
17 |
-
"n_inner": null,
|
18 |
"n_layer": 70,
|
19 |
"num_attention_heads": 112,
|
20 |
-
"offset_alibi": 100,
|
21 |
"pretraining_tp": 4,
|
22 |
-
"
|
23 |
-
"skip_bias_add": true,
|
24 |
-
"skip_bias_add_qkv": false,
|
25 |
"transformers_version": "4.20.0.dev0",
|
26 |
"use_cache": true,
|
27 |
"vocab_size": 250880
|
|
|
2 |
"apply_residual_connection_post_layernorm": false,
|
3 |
"attention_dropout": 0.0,
|
4 |
"attention_softmax_in_fp32": true,
|
|
|
5 |
"bos_token_id": 1,
|
|
|
6 |
"eos_token_id": 2,
|
|
|
|
|
7 |
"hidden_dropout": 0.0,
|
8 |
"initializer_range": 0.02,
|
9 |
"layer_norm_epsilon": 1e-05,
|
10 |
"masked_softmax_fusion": true,
|
11 |
"model_type": "bloom",
|
12 |
"n_embed": 14336,
|
|
|
13 |
"n_layer": 70,
|
14 |
"num_attention_heads": 112,
|
|
|
15 |
"pretraining_tp": 4,
|
16 |
+
"slow_but_exact": false,
|
|
|
|
|
17 |
"transformers_version": "4.20.0.dev0",
|
18 |
"use_cache": true,
|
19 |
"vocab_size": 250880
|
pytorch_model.bin.index.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
-
"total_size":
|
4 |
},
|
5 |
"weight_map": {
|
6 |
"h.0.input_layernorm.bias": "pytorch_model_00002-of-00072.bin",
|
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
+
"total_size": 352494542848
|
4 |
},
|
5 |
"weight_map": {
|
6 |
"h.0.input_layernorm.bias": "pytorch_model_00002-of-00072.bin",
|