Hugging Face's logo

Qwen
/
Qwen2.5-3B

Text Generation
Safetensors
English
qwen2
conversational
Model card Files Community
2

Update config.json to align with tokenizer_config.json and other Qwen2.5 models

#2
by Geaming - opened
base: refs/heads/main
←
from: refs/pr/2
Discussion Files changed
+2
-2
Files changed (1) hide show
  1. config.json +2 -2
config.json CHANGED
@@ -9,7 +9,7 @@
9
  "hidden_size": 2048,
10
  "initializer_range": 0.02,
11
  "intermediate_size": 11008,
12
- "max_position_embeddings": 32768,
13
  "max_window_layers": 36,
14
  "model_type": "qwen2",
15
  "num_attention_heads": 16,
@@ -17,7 +17,7 @@
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": "4.40.1",
 
9
  "hidden_size": 2048,
10
  "initializer_range": 0.02,
11
  "intermediate_size": 11008,
12
+ "max_position_embeddings": 131072,
13
  "max_window_layers": 36,
14
  "model_type": "qwen2",
15
  "num_attention_heads": 16,
 
17
  "num_key_value_heads": 2,
18
  "rms_norm_eps": 1e-06,
19
  "rope_theta": 1000000.0,
20
+ "sliding_window": 131072,
21
  "tie_word_embeddings": true,
22
  "torch_dtype": "bfloat16",
23
  "transformers_version": "4.40.1",