Hugging Face's logo

trl-internal-testing
/
tiny-Qwen2ForCausalLM-2.5

Text Generation
Transformers
Safetensors
qwen2
trl
conversational
text-generation-inference
Model card Files
xet
Community
qgallouedec HF Staff commited on
Commit
8209630
·
verified ·
1 Parent(s): 6d29498

Upload Qwen2ForCausalLM

Browse files
Files changed (2) hide show
  1. config.json +0 -62
  2. model.safetensors +1 -1
config.json CHANGED
@@ -11,68 +11,6 @@
11
  "initializer_range": 0.02,
12
  "intermediate_size": 32,
13
  "layer_types": [
14
- "full_attention",
15
- "full_attention",
16
- "full_attention",
17
- "full_attention",
18
- "full_attention",
19
- "full_attention",
20
- "full_attention",
21
- "full_attention",
22
- "full_attention",
23
- "full_attention",
24
- "full_attention",
25
- "full_attention",
26
- "full_attention",
27
- "full_attention",
28
- "full_attention",
29
- "full_attention",
30
- "full_attention",
31
- "full_attention",
32
- "full_attention",
33
- "full_attention",
34
- "full_attention",
35
- "full_attention",
36
- "full_attention",
37
- "full_attention",
38
- "full_attention",
39
- "full_attention",
40
- "full_attention",
41
- "full_attention",
42
- "full_attention",
43
- "full_attention",
44
- "full_attention",
45
- "full_attention",
46
- "full_attention",
47
- "full_attention",
48
- "full_attention",
49
- "full_attention",
50
- "full_attention",
51
- "full_attention",
52
- "full_attention",
53
- "full_attention",
54
- "full_attention",
55
- "full_attention",
56
- "full_attention",
57
- "full_attention",
58
- "full_attention",
59
- "full_attention",
60
- "full_attention",
61
- "full_attention",
62
- "full_attention",
63
- "full_attention",
64
- "full_attention",
65
- "full_attention",
66
- "full_attention",
67
- "full_attention",
68
- "full_attention",
69
- "full_attention",
70
- "full_attention",
71
- "full_attention",
72
- "full_attention",
73
- "full_attention",
74
- "full_attention",
75
- "full_attention",
76
  "full_attention",
77
  "full_attention"
78
  ],
 
11
  "initializer_range": 0.02,
12
  "intermediate_size": 32,
13
  "layer_types": [
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
14
  "full_attention",
15
  "full_attention"
16
  ],
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37e583ad635f05fe622db6cc71379da4e2f6001362c8a53382925d6c9d440220
3
  size 4872824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94b49b4fdb21187b4ff0f2af98f12d4c8f4055ccec2989d0ec7c4c32f885069c
3
  size 4872824