Extend RoPE theta to 300k and extend position embeddings to 32k
Browse files- config.json +4 -4
config.json
CHANGED
@@ -9,20 +9,20 @@
|
|
9 |
"hidden_size": 3584,
|
10 |
"initializer_range": 0.02,
|
11 |
"intermediate_size": 18944,
|
12 |
-
"max_position_embeddings":
|
13 |
"max_window_layers": 28,
|
14 |
"model_type": "qwen2",
|
15 |
"num_attention_heads": 28,
|
16 |
"num_hidden_layers": 28,
|
17 |
"num_key_value_heads": 4,
|
18 |
"rms_norm_eps": 1e-06,
|
19 |
-
"
|
20 |
-
"
|
|
|
21 |
"tie_word_embeddings": false,
|
22 |
"torch_dtype": "bfloat16",
|
23 |
"transformers_version": "4.44.0",
|
24 |
"use_cache": true,
|
25 |
-
"use_mrope": false,
|
26 |
"use_sliding_window": false,
|
27 |
"vocab_size": 152064
|
28 |
}
|
|
|
9 |
"hidden_size": 3584,
|
10 |
"initializer_range": 0.02,
|
11 |
"intermediate_size": 18944,
|
12 |
+
"max_position_embeddings": 32768,
|
13 |
"max_window_layers": 28,
|
14 |
"model_type": "qwen2",
|
15 |
"num_attention_heads": 28,
|
16 |
"num_hidden_layers": 28,
|
17 |
"num_key_value_heads": 4,
|
18 |
"rms_norm_eps": 1e-06,
|
19 |
+
"rope_scaling": null,
|
20 |
+
"rope_theta": 300000.0,
|
21 |
+
"sliding_window": null,
|
22 |
"tie_word_embeddings": false,
|
23 |
"torch_dtype": "bfloat16",
|
24 |
"transformers_version": "4.44.0",
|
25 |
"use_cache": true,
|
|
|
26 |
"use_sliding_window": false,
|
27 |
"vocab_size": 152064
|
28 |
}
|