Hugging Face's logo

aiziks
/
checkpoints

Transformers
Safetensors
Generated from Trainer
sft
trl
Model card Files
xet
 Community
aiziks commited on
Commit
a5036aa
·
verified ·
1 Parent(s): 2890d8b

Training in progress, step 5

Browse files
Files changed (4) hide show
  1. README.md +2 -2
  2. adapter_config.json +41 -73
  3. adapter_model.safetensors +2 -2
  4. training_args.bin +1 -1
README.md CHANGED
@@ -1,5 +1,5 @@
1
  ---
2
- base_model: Qwen/Qwen2.5-VL-3B-Instruct
3
  library_name: transformers
4
  model_name: checkpoints
5
  tags:
@@ -11,7 +11,7 @@ licence: license
11
 
12
  # Model Card for checkpoints
13
 
14
- This model is a fine-tuned version of [Qwen/Qwen2.5-VL-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct).
15
  It has been trained using [TRL](https://github.com/huggingface/trl).
16
 
17
  ## Quick start
 
1
  ---
2
+ base_model: Qwen/Qwen2.5-VL-7B-Instruct
3
  library_name: transformers
4
  model_name: checkpoints
5
  tags:
 
11
 
12
  # Model Card for checkpoints
13
 
14
+ This model is a fine-tuned version of [Qwen/Qwen2.5-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct).
15
  It has been trained using [TRL](https://github.com/huggingface/trl).
16
 
17
  ## Quick start
adapter_config.json CHANGED
@@ -3,7 +3,7 @@
3
  "alpha_pattern": {},
4
  "arrow_config": null,
5
  "auto_mapping": null,
6
- "base_model_name_or_path": "Qwen/Qwen2.5-VL-3B-Instruct",
7
  "bias": "none",
8
  "corda_config": null,
9
  "ensure_weight_tying": false,
@@ -29,88 +29,56 @@
29
  "rank_pattern": {},
30
  "revision": null,
31
  "target_modules": [
32
- "model.language_model.layers.27.self_attn.o_proj",
33
- "model.language_model.layers.26.self_attn.k_proj",
34
  "model.visual.merger.mlp.2",
35
- "model.language_model.layers.24.self_attn.k_proj",
36
- "model.language_model.layers.27.self_attn.v_proj",
37
- "model.language_model.layers.16.self_attn.q_proj",
38
- "model.language_model.layers.20.self_attn.q_proj",
39
- "model.language_model.layers.31.self_attn.k_proj",
40
- "model.language_model.layers.29.self_attn.o_proj",
41
- "model.language_model.layers.28.self_attn.o_proj",
42
- "model.language_model.layers.18.self_attn.o_proj",
43
- "model.language_model.layers.33.self_attn.k_proj",
44
- "model.language_model.layers.23.self_attn.k_proj",
45
- "model.language_model.layers.22.self_attn.v_proj",
46
- "model.language_model.layers.29.self_attn.q_proj",
47
- "model.language_model.layers.20.self_attn.v_proj",
48
- "model.language_model.layers.34.self_attn.o_proj",
49
- "model.language_model.layers.16.self_attn.v_proj",
50
- "model.language_model.layers.18.self_attn.k_proj",
51
- "model.language_model.layers.28.self_attn.v_proj",
52
- "model.language_model.layers.26.self_attn.q_proj",
53
- "model.language_model.layers.34.self_attn.k_proj",
54
- "model.language_model.layers.31.self_attn.v_proj",
55
- "model.language_model.layers.35.self_attn.k_proj",
56
- "model.language_model.layers.25.self_attn.q_proj",
57
- "model.language_model.layers.16.self_attn.o_proj",
58
- "model.language_model.layers.34.self_attn.v_proj",
59
- "model.language_model.layers.23.self_attn.v_proj",
60
- "model.visual.merger.mlp.0",
61
- "model.language_model.layers.33.self_attn.v_proj",
62
- "model.language_model.layers.19.self_attn.q_proj",
63
- "model.language_model.layers.21.self_attn.v_proj",
64
- "model.language_model.layers.28.self_attn.q_proj",
65
- "model.language_model.layers.19.self_attn.o_proj",
66
- "model.language_model.layers.26.self_attn.v_proj",
67
- "model.language_model.layers.19.self_attn.k_proj",
68
- "model.language_model.layers.33.self_attn.q_proj",
69
- "model.language_model.layers.34.self_attn.q_proj",
70
- "model.language_model.layers.30.self_attn.q_proj",
71
- "model.language_model.layers.31.self_attn.q_proj",
72
- "model.language_model.layers.29.self_attn.v_proj",
73
- "model.language_model.layers.20.self_attn.o_proj",
74
- "model.language_model.layers.22.self_attn.o_proj",
75
- "model.language_model.layers.23.self_attn.o_proj",
76
- "model.language_model.layers.17.self_attn.o_proj",
77
- "model.language_model.layers.32.self_attn.o_proj",
78
- "model.language_model.layers.28.self_attn.k_proj",
79
- "model.language_model.layers.24.self_attn.v_proj",
80
- "model.language_model.layers.21.self_attn.o_proj",
81
  "model.language_model.layers.19.self_attn.v_proj",
82
- "model.language_model.layers.17.self_attn.k_proj",
83
- "model.language_model.layers.26.self_attn.o_proj",
84
- "model.language_model.layers.29.self_attn.k_proj",
85
- "model.language_model.layers.30.self_attn.v_proj",
86
- "model.language_model.layers.22.self_attn.q_proj",
87
- "model.language_model.layers.31.self_attn.o_proj",
88
- "model.language_model.layers.32.self_attn.q_proj",
89
- "model.language_model.layers.32.self_attn.v_proj",
90
- "model.language_model.layers.30.self_attn.k_proj",
91
- "model.language_model.layers.25.self_attn.k_proj",
92
- "model.language_model.layers.27.self_attn.k_proj",
93
- "model.language_model.layers.18.self_attn.v_proj",
94
- "model.language_model.layers.23.self_attn.q_proj",
95
  "model.language_model.layers.18.self_attn.q_proj",
96
- "model.language_model.layers.20.self_attn.k_proj",
97
  "model.language_model.layers.17.self_attn.q_proj",
98
- "model.language_model.layers.27.self_attn.q_proj",
99
- "model.language_model.layers.35.self_attn.o_proj",
100
- "model.language_model.layers.35.self_attn.v_proj",
101
  "model.language_model.layers.21.self_attn.k_proj",
102
- "model.language_model.layers.25.self_attn.v_proj",
103
  "model.language_model.layers.22.self_attn.k_proj",
104
- "model.language_model.layers.35.self_attn.q_proj",
105
- "model.language_model.layers.30.self_attn.o_proj",
 
 
 
 
106
  "model.language_model.layers.24.self_attn.o_proj",
107
- "model.language_model.layers.17.self_attn.v_proj",
108
- "model.language_model.layers.32.self_attn.k_proj",
109
  "model.language_model.layers.25.self_attn.o_proj",
 
 
110
  "model.language_model.layers.21.self_attn.q_proj",
111
- "model.language_model.layers.24.self_attn.q_proj",
 
 
 
 
 
 
 
 
 
 
 
 
 
112
  "model.language_model.layers.16.self_attn.k_proj",
113
- "model.language_model.layers.33.self_attn.o_proj"
 
 
 
 
 
 
 
 
 
114
  ],
115
  "target_parameters": null,
116
  "task_type": "CAUSAL_LM",
 
3
  "alpha_pattern": {},
4
  "arrow_config": null,
5
  "auto_mapping": null,
6
+ "base_model_name_or_path": "Qwen/Qwen2.5-VL-7B-Instruct",
7
  "bias": "none",
8
  "corda_config": null,
9
  "ensure_weight_tying": false,
 
29
  "rank_pattern": {},
30
  "revision": null,
31
  "target_modules": [
32
+ "model.language_model.layers.25.self_attn.v_proj",
 
33
  "model.visual.merger.mlp.2",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
34
  "model.language_model.layers.19.self_attn.v_proj",
35
+ "model.language_model.layers.19.self_attn.o_proj",
36
+ "model.language_model.layers.16.self_attn.q_proj",
 
 
 
 
 
 
 
 
 
 
 
37
  "model.language_model.layers.18.self_attn.q_proj",
38
+ "model.language_model.layers.19.self_attn.k_proj",
39
  "model.language_model.layers.17.self_attn.q_proj",
40
+ "model.language_model.layers.20.self_attn.o_proj",
41
+ "model.language_model.layers.22.self_attn.v_proj",
 
42
  "model.language_model.layers.21.self_attn.k_proj",
 
43
  "model.language_model.layers.22.self_attn.k_proj",
44
+ "model.language_model.layers.23.self_attn.k_proj",
45
+ "model.language_model.layers.18.self_attn.v_proj",
46
+ "model.language_model.layers.22.self_attn.q_proj",
47
+ "model.visual.merger.mlp.0",
48
+ "model.language_model.layers.17.self_attn.o_proj",
49
+ "model.language_model.layers.21.self_attn.v_proj",
50
  "model.language_model.layers.24.self_attn.o_proj",
51
+ "model.language_model.layers.24.self_attn.k_proj",
52
+ "model.language_model.layers.26.self_attn.q_proj",
53
  "model.language_model.layers.25.self_attn.o_proj",
54
+ "model.language_model.layers.27.self_attn.k_proj",
55
+ "model.language_model.layers.16.self_attn.o_proj",
56
  "model.language_model.layers.21.self_attn.q_proj",
57
+ "model.language_model.layers.27.self_attn.o_proj",
58
+ "model.language_model.layers.16.self_attn.v_proj",
59
+ "model.language_model.layers.26.self_attn.o_proj",
60
+ "model.language_model.layers.20.self_attn.k_proj",
61
+ "model.language_model.layers.18.self_attn.k_proj",
62
+ "model.language_model.layers.23.self_attn.v_proj",
63
+ "model.language_model.layers.23.self_attn.q_proj",
64
+ "model.language_model.layers.25.self_attn.q_proj",
65
+ "model.language_model.layers.18.self_attn.o_proj",
66
+ "model.language_model.layers.25.self_attn.k_proj",
67
+ "model.language_model.layers.20.self_attn.q_proj",
68
+ "model.language_model.layers.21.self_attn.o_proj",
69
+ "model.language_model.layers.26.self_attn.v_proj",
70
+ "model.language_model.layers.17.self_attn.k_proj",
71
  "model.language_model.layers.16.self_attn.k_proj",
72
+ "model.language_model.layers.22.self_attn.o_proj",
73
+ "model.language_model.layers.19.self_attn.q_proj",
74
+ "model.language_model.layers.17.self_attn.v_proj",
75
+ "model.language_model.layers.27.self_attn.q_proj",
76
+ "model.language_model.layers.24.self_attn.q_proj",
77
+ "model.language_model.layers.27.self_attn.v_proj",
78
+ "model.language_model.layers.20.self_attn.v_proj",
79
+ "model.language_model.layers.24.self_attn.v_proj",
80
+ "model.language_model.layers.26.self_attn.k_proj",
81
+ "model.language_model.layers.23.self_attn.o_proj"
82
  ],
83
  "target_parameters": null,
84
  "task_type": "CAUSAL_LM",
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e16f24e6448a1cd7abe28c347acc69a0d03e73a5ff6c1a6ef142885f7c0dcace
3
- size 8773032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:375f2aacce3e2ea637cf4ca9ffa876f2264ecb657314a75b2578b7acc02a21aa
3
+ size 9271560
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:19dde3eac01ad7a1ec7a88defa611ee1d129ecd272cdc27e71cd6b93ae569476
3
  size 5585
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2dcf4329ceaf748dae2db0ec6b055eb0914001a8570ba33c4e633151685ce73
3
  size 5585