Update config.json
Browse files- config.json +24 -24
config.json
CHANGED
@@ -1,27 +1,27 @@
|
|
1 |
{
|
2 |
-
architectures: [
|
3 |
"Qwen2ForCausalLM"
|
4 |
],
|
5 |
-
attention_dropout: 0,
|
6 |
-
bos_token_id: 151643,
|
7 |
-
eos_token_id: 151645,
|
8 |
-
hidden_act: "silu",
|
9 |
-
hidden_size: 2048,
|
10 |
-
initializer_range: 0.02,
|
11 |
-
intermediate_size: 11008,
|
12 |
-
max_position_embeddings: 32768,
|
13 |
-
max_window_layers: 70,
|
14 |
-
model_type: "qwen2",
|
15 |
-
num_attention_heads: 16,
|
16 |
-
num_hidden_layers: 36,
|
17 |
-
num_key_value_heads: 2,
|
18 |
-
rms_norm_eps:
|
19 |
-
rope_theta: 1000000,
|
20 |
-
sliding_window: 32768,
|
21 |
-
tie_word_embeddings: true,
|
22 |
-
torch_dtype: "bfloat16",
|
23 |
-
transformers_version: "4.43.1",
|
24 |
-
use_cache: true,
|
25 |
-
use_sliding_window: false,
|
26 |
-
vocab_size: 151936
|
27 |
-
}
|
|
|
1 |
{
|
2 |
+
"architectures": [
|
3 |
"Qwen2ForCausalLM"
|
4 |
],
|
5 |
+
"attention_dropout": 0.0,
|
6 |
+
"bos_token_id": 151643,
|
7 |
+
"eos_token_id": 151645,
|
8 |
+
"hidden_act": "silu",
|
9 |
+
"hidden_size": 2048,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 11008,
|
12 |
+
"max_position_embeddings": 32768,
|
13 |
+
"max_window_layers": 70,
|
14 |
+
"model_type": "qwen2",
|
15 |
+
"num_attention_heads": 16,
|
16 |
+
"num_hidden_layers": 36,
|
17 |
+
"num_key_value_heads": 2,
|
18 |
+
"rms_norm_eps": 1e-06,
|
19 |
+
"rope_theta": 1000000.0,
|
20 |
+
"sliding_window": 32768,
|
21 |
+
"tie_word_embeddings": true,
|
22 |
+
"torch_dtype": "bfloat16",
|
23 |
+
"transformers_version": "4.43.1",
|
24 |
+
"use_cache": true,
|
25 |
+
"use_sliding_window": false,
|
26 |
+
"vocab_size": 151936
|
27 |
+
}
|