Younes Belkada
commited on
Commit
•
c090920
1
Parent(s):
de22a5a
add model
Browse files- config.json +29 -0
- pytorch_model.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/home/younes/Desktop/Work/data/megatron-debug/",
|
| 3 |
+
"apply_residual_connection_post_layernorm": false,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"BigScience176BModel"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.1,
|
| 8 |
+
"bias_dropout_fusion": true,
|
| 9 |
+
"bos_token_id": 0,
|
| 10 |
+
"dtype": "bfloat16",
|
| 11 |
+
"eos_token_id": 0,
|
| 12 |
+
"hidden_dropout": 0.1,
|
| 13 |
+
"hidden_size": 64,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"layer_norm_epsilon": 1e-05,
|
| 16 |
+
"masked_softmax_fusion": true,
|
| 17 |
+
"model_type": "bigscience176b",
|
| 18 |
+
"n_head": 8,
|
| 19 |
+
"n_inner": null,
|
| 20 |
+
"n_layer": 2,
|
| 21 |
+
"pretraining_pp": 2,
|
| 22 |
+
"pretraining_tp": 2,
|
| 23 |
+
"seq_length": 20,
|
| 24 |
+
"skip_bias_add": true,
|
| 25 |
+
"torch_dtype": "bfloat16",
|
| 26 |
+
"transformers_version": "4.18.0.dev0",
|
| 27 |
+
"use_cache": false,
|
| 28 |
+
"vocab_size": 250880
|
| 29 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e22bceb559a5fcdc3dbb0f9ea622210cbe6b2a56d459ad7693284a1e99569c8
|
| 3 |
+
size 32322126
|