Hugging Face's logo

trl-internal-testing
/
tiny-Qwen2VLForConditionalGeneration

Image-to-Text
Transformers
Safetensors
qwen2_vl
trl
text-generation-inference
Model card Files
xet
Community
3

Upload Qwen2VLForConditionalGeneration

#1
by albertvillanova HF Staff - opened
base: refs/heads/main
←
from: refs/pr/1
Discussion Files changed
+8
-32
Files changed (3) hide show
  1. config.json +6 -30
  2. generation_config.json +1 -1
  3. model.safetensors +1 -1
config.json CHANGED
@@ -4,6 +4,7 @@
4
  ],
5
  "attention_dropout": 0.0,
6
  "bos_token_id": 151643,
 
7
  "eos_token_id": 151645,
8
  "hidden_act": "silu",
9
  "hidden_size": 1536,
@@ -19,7 +20,9 @@
19
  "rms_norm_eps": 1e-06,
20
  "rope_scaling": {
21
  "mrope_section": [
22
- 2
 
 
23
  ],
24
  "rope_type": "default",
25
  "type": "default"
@@ -32,6 +35,7 @@
32
  ],
33
  "attention_dropout": 0.0,
34
  "bos_token_id": 151643,
 
35
  "eos_token_id": 151645,
36
  "hidden_act": "silu",
37
  "hidden_size": 16,
@@ -39,32 +43,6 @@
39
  "initializer_range": 0.02,
40
  "intermediate_size": 8960,
41
  "layer_types": [
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
  ],
@@ -85,7 +63,6 @@
85
  "rope_theta": 1000000.0,
86
  "sliding_window": null,
87
  "tie_word_embeddings": true,
88
- "torch_dtype": "bfloat16",
89
  "use_cache": true,
90
  "use_sliding_window": false,
91
  "video_token_id": null,
@@ -94,8 +71,7 @@
94
  "vision_token_id": 151654,
95
  "vocab_size": 151936
96
  },
97
- "torch_dtype": "bfloat16",
98
- "transformers_version": "4.56.0.dev0",
99
  "use_cache": true,
100
  "use_sliding_window": false,
101
  "video_token_id": 151656,
 
4
  ],
5
  "attention_dropout": 0.0,
6
  "bos_token_id": 151643,
7
+ "dtype": "bfloat16",
8
  "eos_token_id": 151645,
9
  "hidden_act": "silu",
10
  "hidden_size": 1536,
 
20
  "rms_norm_eps": 1e-06,
21
  "rope_scaling": {
22
  "mrope_section": [
23
+ 16,
24
+ 24,
25
+ 24
26
  ],
27
  "rope_type": "default",
28
  "type": "default"
 
35
  ],
36
  "attention_dropout": 0.0,
37
  "bos_token_id": 151643,
38
+ "dtype": "bfloat16",
39
  "eos_token_id": 151645,
40
  "hidden_act": "silu",
41
  "hidden_size": 16,
 
43
  "initializer_range": 0.02,
44
  "intermediate_size": 8960,
45
  "layer_types": [
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
46
  "full_attention",
47
  "full_attention"
48
  ],
 
63
  "rope_theta": 1000000.0,
64
  "sliding_window": null,
65
  "tie_word_embeddings": true,
 
66
  "use_cache": true,
67
  "use_sliding_window": false,
68
  "video_token_id": null,
 
71
  "vision_token_id": 151654,
72
  "vocab_size": 151936
73
  },
74
+ "transformers_version": "4.57.0.dev0",
 
75
  "use_cache": true,
76
  "use_sliding_window": false,
77
  "video_token_id": 151656,
generation_config.json CHANGED
@@ -2,5 +2,5 @@
2
  "_from_model_config": true,
3
  "bos_token_id": 151643,
4
  "eos_token_id": 151645,
5
- "transformers_version": "4.56.0.dev0"
6
  }
 
2
  "_from_model_config": true,
3
  "bos_token_id": 151643,
4
  "eos_token_id": 151645,
5
+ "transformers_version": "4.57.0.dev0"
6
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f3c8d9619ed6dc2a99ea49a9d1395bdb72e6ae3af865c8b0a59e94b7943eaca
3
  size 140919824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:451d201aa9cf0dee2855900303993465b2102f325189c4e9135f194d78fa2edd
3
  size 140919824