vivek2001123
commited on
Commit
•
462441f
1
Parent(s):
7bfab30
Upload config.json
Browse files- config.json +28 -0
config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alibi": false,
|
3 |
+
"apply_residual_connection_post_layernorm": false,
|
4 |
+
"architectures": [
|
5 |
+
"RWForCausalLM"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"auto_map": {
|
9 |
+
"AutoConfig": "configuration_RW.RWConfig",
|
10 |
+
"AutoModelForCausalLM": "modelling_RW.RWForCausalLM"
|
11 |
+
},
|
12 |
+
"bias": false,
|
13 |
+
"bos_token_id": 11,
|
14 |
+
"eos_token_id": 11,
|
15 |
+
"hidden_dropout": 0.0,
|
16 |
+
"hidden_size": 4544,
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"layer_norm_epsilon": 1e-05,
|
19 |
+
"model_type": "RefinedWebModel",
|
20 |
+
"multi_query": true,
|
21 |
+
"n_head": 71,
|
22 |
+
"n_layer": 32,
|
23 |
+
"parallel_attn": true,
|
24 |
+
"torch_dtype": "bfloat16",
|
25 |
+
"transformers_version": "4.27.4",
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 65024
|
28 |
+
}
|