feihu.hf
commited on
Commit
•
76ca6ba
1
Parent(s):
e648520
update config.json
Browse files- config.json +4 -9
config.json
CHANGED
@@ -9,7 +9,7 @@
|
|
9 |
"hidden_size": 5120,
|
10 |
"initializer_range": 0.02,
|
11 |
"intermediate_size": 13824,
|
12 |
-
"max_position_embeddings":
|
13 |
"max_window_layers": 70,
|
14 |
"model_type": "qwen2",
|
15 |
"num_attention_heads": 40,
|
@@ -17,16 +17,11 @@
|
|
17 |
"num_key_value_heads": 8,
|
18 |
"rms_norm_eps": 1e-06,
|
19 |
"rope_theta": 1000000.0,
|
20 |
-
"sliding_window":
|
21 |
"tie_word_embeddings": false,
|
22 |
"torch_dtype": "bfloat16",
|
23 |
"transformers_version": "4.43.1",
|
24 |
"use_cache": true,
|
25 |
"use_sliding_window": false,
|
26 |
-
"vocab_size": 152064
|
27 |
-
|
28 |
-
"factor": 4.0,
|
29 |
-
"original_max_position_embeddings": 32768,
|
30 |
-
"type": "yarn"
|
31 |
-
}
|
32 |
-
}
|
|
|
9 |
"hidden_size": 5120,
|
10 |
"initializer_range": 0.02,
|
11 |
"intermediate_size": 13824,
|
12 |
+
"max_position_embeddings": 32768,
|
13 |
"max_window_layers": 70,
|
14 |
"model_type": "qwen2",
|
15 |
"num_attention_heads": 40,
|
|
|
17 |
"num_key_value_heads": 8,
|
18 |
"rms_norm_eps": 1e-06,
|
19 |
"rope_theta": 1000000.0,
|
20 |
+
"sliding_window": 131072,
|
21 |
"tie_word_embeddings": false,
|
22 |
"torch_dtype": "bfloat16",
|
23 |
"transformers_version": "4.43.1",
|
24 |
"use_cache": true,
|
25 |
"use_sliding_window": false,
|
26 |
+
"vocab_size": 152064
|
27 |
+
}
|
|
|
|
|
|
|
|
|
|