Taishi-N324
commited on
Commit
•
f07ded9
1
Parent(s):
7f02f54
Upload config.json
Browse files- config.json +28 -0
config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation_function": "gelu",
|
3 |
+
"architectures": [
|
4 |
+
"GPTBigCodeForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_softmax_in_fp32": true,
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 0,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"layer_norm_epsilon": 1e-05,
|
13 |
+
"model_type": "gpt_bigcode",
|
14 |
+
"multi_query": true,
|
15 |
+
"n_embd": 6144,
|
16 |
+
"n_head": 48,
|
17 |
+
"n_inner": 24576,
|
18 |
+
"n_layer": 40,
|
19 |
+
"n_positions": 8192,
|
20 |
+
"pad_token_id": 0,
|
21 |
+
"resid_pdrop": 0.1,
|
22 |
+
"scale_attention_softmax_in_fp32": true,
|
23 |
+
"scale_attn_weights": true,
|
24 |
+
"torch_dtype": "float32",
|
25 |
+
"transformers_version": "4.35.2",
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 49152
|
28 |
+
}
|