Harley-ml commited on
Commit
fbc709c
·
verified ·
1 Parent(s): d3fbf1d

Upload 4 files

Browse files
Files changed (4) hide show
  1. config.json +39 -0
  2. generation_config.json +7 -0
  3. model.safetensors +3 -0
  4. tokenizer.json +0 -0
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": null,
8
+ "dtype": "float32",
9
+ "eos_token_id": null,
10
+ "head_dim": 64,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 256,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 1024,
15
+ "layer_types": [
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention"
20
+ ],
21
+ "max_position_embeddings": 512,
22
+ "max_window_layers": 28,
23
+ "model_type": "qwen3",
24
+ "num_attention_heads": 4,
25
+ "num_hidden_layers": 4,
26
+ "num_key_value_heads": 4,
27
+ "pad_token_id": null,
28
+ "rms_norm_eps": 1e-06,
29
+ "rope_parameters": {
30
+ "rope_theta": 10000.0,
31
+ "rope_type": "default"
32
+ },
33
+ "sliding_window": null,
34
+ "tie_word_embeddings": true,
35
+ "transformers_version": "5.0.0",
36
+ "use_cache": false,
37
+ "use_sliding_window": false,
38
+ "vocab_size": 8004
39
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "output_attentions": false,
4
+ "output_hidden_states": false,
5
+ "transformers_version": "5.0.0",
6
+ "use_cache": true
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:172848be736314724aebd96bacb5ad07dd308d1ea95b0efcbb1138b7d7407a53
3
+ size 24989552
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff