BIaoo commited on
Commit
c73a187
·
verified ·
1 Parent(s): 676a870

Upload 2 files

Browse files
Files changed (2) hide show
  1. 1_Pooling/config.json +10 -0
  2. config.json +30 -9
1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 1024,
3
+ "pooling_mode_cls_token": false,
4
+ "pooling_mode_mean_tokens": false,
5
+ "pooling_mode_max_tokens": false,
6
+ "pooling_mode_mean_sqrt_len_tokens": false,
7
+ "pooling_mode_weightedmean_tokens": false,
8
+ "pooling_mode_lasttoken": true,
9
+ "include_prompt": true
10
+ }
config.json CHANGED
@@ -1,10 +1,31 @@
1
  {
2
- "word_embedding_dimension": 1024,
3
- "pooling_mode_cls_token": false,
4
- "pooling_mode_mean_tokens": false,
5
- "pooling_mode_max_tokens": false,
6
- "pooling_mode_mean_sqrt_len_tokens": false,
7
- "pooling_mode_weightedmean_tokens": false,
8
- "pooling_mode_lasttoken": true,
9
- "include_prompt": true
10
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151643,
9
+ "gradient_checkpointing": false,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 1024,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "max_position_embeddings": 32768,
16
+ "max_window_layers": 28,
17
+ "model_type": "qwen3",
18
+ "num_attention_heads": 16,
19
+ "num_hidden_layers": 28,
20
+ "num_key_value_heads": 8,
21
+ "rms_norm_eps": 1e-06,
22
+ "rope_scaling": null,
23
+ "rope_theta": 1000000,
24
+ "sliding_window": null,
25
+ "tie_word_embeddings": true,
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.51.3",
28
+ "use_cache": true,
29
+ "use_sliding_window": false,
30
+ "vocab_size": 151669
31
+ }