Hugging Face's logo

etemiz
/
Ostrich-27B-AHA-Gemma3-250519

Image-Text-to-Text
Transformers
Safetensors
gemma3
AHA
alignment
conversational
text-generation-inference
Model card Files
xet
Community
etemiz commited on
Commit
ea323de
·
verified ·
1 Parent(s): 3ac6902

Upload folder using huggingface_hub

Browse files
Files changed (24) hide show
  1. .gitattributes +1 -0
  2. README.md +88 -0
  3. added_tokens.json +3 -0
  4. config.json +60 -0
  5. mergekit_config.yml +49 -0
  6. model-00001-of-00012.safetensors +3 -0
  7. model-00002-of-00012.safetensors +3 -0
  8. model-00003-of-00012.safetensors +3 -0
  9. model-00004-of-00012.safetensors +3 -0
  10. model-00005-of-00012.safetensors +3 -0
  11. model-00006-of-00012.safetensors +3 -0
  12. model-00007-of-00012.safetensors +3 -0
  13. model-00008-of-00012.safetensors +3 -0
  14. model-00009-of-00012.safetensors +3 -0
  15. model-00010-of-00012.safetensors +3 -0
  16. model-00011-of-00012.safetensors +3 -0
  17. model-00012-of-00012.safetensors +3 -0
  18. model.safetensors.index.json +0 -0
  19. preprocessor_config.json +29 -0
  20. processor_config.json +4 -0
  21. special_tokens_map.json +33 -0
  22. tokenizer.json +3 -0
  23. tokenizer.model +3 -0
  24. tokenizer_config.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: []
3
+ library_name: transformers
4
+ tags:
5
+ - mergekit
6
+ - merge
7
+
8
+ ---
9
+ # pab-g27-merge23
10
+
11
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
12
+
13
+ ## Merge Details
14
+ ### Merge Method
15
+
16
+ This model was merged using the [Task Arithmetic](https://arxiv.org/abs/2212.04089) merge method using /home/dead/m/md100/zoo/pab-g27-ArwN as a base.
17
+
18
+ ### Models Merged
19
+
20
+ The following models were included in the merge:
21
+ * /home/dead/m/md100/zoo/pab-g27-2888t
22
+ * /home/dead/m/md100/zoo/pab-g27-wHRU
23
+ * /home/dead/m/md100/zoo/pab-g27-NG2Y
24
+ * /home/dead/m/md100/zoo/pab-g27-6isV
25
+ * /home/dead/m/md100/zoo/pab-g27-psi9
26
+ * /home/dead/m/md100/zoo/pab-g27-4yYT
27
+ * /home/dead/m/md100/zoo/pab-g27-27dBG
28
+ * /home/dead/m/md100/zoo/pab-g27-2HCZV
29
+ * /home/dead/m/md100/zoo/pab-g27-2Gr19
30
+ * /home/dead/m/md100/zoo/pab-g27-T47Q
31
+ * /home/dead/m/md100/zoo/pab-g27-2AL3A
32
+
33
+ ### Configuration
34
+
35
+ The following YAML configuration was used to produce this model:
36
+
37
+ ```yaml
38
+ models:
39
+ #[('pab-g27-2888t-q4', np.float64(0.4196454642702039)),
40
+ # ('pab-g27-T47Q-q4', np.float64(0.4259142969660608)),
41
+ # ('pab-g27-NG2Y-q4', np.float64(0.42879163132931064)),
42
+ # ('pab-g27-psi9-q4', np.float64(0.4290688185374475)),
43
+ # ('pab-g27-6isV-q4', np.float64(0.43299346355223217)),
44
+ # ('pab-g27-2Gr19-q4', np.float64(0.4386521142685669)),
45
+ # ('pab-g27-4yYT-q4', np.float64(0.44213902450931963)),
46
+ # ('pab-g27-2AL3A-q4', np.float64(0.4430655198480763)),
47
+ # ('pab-g27-wHRU-q4', np.float64(0.4556739112699817)),
48
+ # ('pab-g27-27dBG-q4', np.float64(0.4660908532086056)),
49
+ # ('pab-g27-2HCZV-q4', np.float64(0.47959159136301327))]
50
+
51
+ - model: /home/dead/m/md100/zoo/pab-g27-2888t
52
+ parameters:
53
+ weight: 0.1
54
+ - model: /home/dead/m/md100/zoo/pab-g27-T47Q
55
+ parameters:
56
+ weight: 0.1
57
+ - model: /home/dead/m/md100/zoo/pab-g27-NG2Y
58
+ parameters:
59
+ weight: 0.1
60
+ - model: /home/dead/m/md100/zoo/pab-g27-psi9
61
+ parameters:
62
+ weight: 0.1
63
+ - model: /home/dead/m/md100/zoo/pab-g27-6isV
64
+ parameters:
65
+ weight: 0.1
66
+ - model: /home/dead/m/md100/zoo/pab-g27-2Gr19
67
+ parameters:
68
+ weight: 0.1
69
+ - model: /home/dead/m/md100/zoo/pab-g27-4yYT
70
+ parameters:
71
+ weight: 0.1
72
+ - model: /home/dead/m/md100/zoo/pab-g27-2AL3A
73
+ parameters:
74
+ weight: 0.1
75
+ - model: /home/dead/m/md100/zoo/pab-g27-wHRU
76
+ parameters:
77
+ weight: 0.1
78
+ - model: /home/dead/m/md100/zoo/pab-g27-27dBG
79
+ parameters:
80
+ weight: 0.1
81
+ - model: /home/dead/m/md100/zoo/pab-g27-2HCZV
82
+ parameters:
83
+ weight: 0.1
84
+ merge_method: task_arithmetic
85
+ base_model: /home/dead/m/md100/zoo/pab-g27-ArwN
86
+ dtype: bfloat16
87
+
88
+ ```
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<image_soft_token>": 262144
3
+ }
config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Gemma3ForConditionalGeneration"
4
+ ],
5
+ "boi_token_index": 255999,
6
+ "eoi_token_index": 256000,
7
+ "eos_token_id": [
8
+ 1,
9
+ 106
10
+ ],
11
+ "image_token_index": 262144,
12
+ "initializer_range": 0.02,
13
+ "mm_tokens_per_image": 256,
14
+ "model_type": "gemma3",
15
+ "text_config": {
16
+ "attention_bias": false,
17
+ "attention_dropout": 0.0,
18
+ "attn_logit_softcapping": null,
19
+ "cache_implementation": "hybrid",
20
+ "final_logit_softcapping": null,
21
+ "head_dim": 128,
22
+ "hidden_activation": "gelu_pytorch_tanh",
23
+ "hidden_size": 5376,
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 21504,
26
+ "max_position_embeddings": 131072,
27
+ "model_type": "gemma3_text",
28
+ "num_attention_heads": 32,
29
+ "num_hidden_layers": 62,
30
+ "num_key_value_heads": 16,
31
+ "query_pre_attn_scalar": 168,
32
+ "rms_norm_eps": 1e-06,
33
+ "rope_local_base_freq": 10000.0,
34
+ "rope_scaling": {
35
+ "factor": 8.0,
36
+ "rope_type": "linear"
37
+ },
38
+ "rope_theta": 1000000.0,
39
+ "sliding_window": 1024,
40
+ "sliding_window_pattern": 6,
41
+ "use_cache": true,
42
+ "vocab_size": 262208
43
+ },
44
+ "torch_dtype": "bfloat16",
45
+ "transformers_version": "4.51.3",
46
+ "vision_config": {
47
+ "attention_dropout": 0.0,
48
+ "hidden_act": "gelu_pytorch_tanh",
49
+ "hidden_size": 1152,
50
+ "image_size": 896,
51
+ "intermediate_size": 4304,
52
+ "layer_norm_eps": 1e-06,
53
+ "model_type": "siglip_vision_model",
54
+ "num_attention_heads": 16,
55
+ "num_channels": 3,
56
+ "num_hidden_layers": 27,
57
+ "patch_size": 14,
58
+ "vision_use_head": false
59
+ }
60
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ models:
2
+ #[('pab-g27-2888t-q4', np.float64(0.4196454642702039)),
3
+ # ('pab-g27-T47Q-q4', np.float64(0.4259142969660608)),
4
+ # ('pab-g27-NG2Y-q4', np.float64(0.42879163132931064)),
5
+ # ('pab-g27-psi9-q4', np.float64(0.4290688185374475)),
6
+ # ('pab-g27-6isV-q4', np.float64(0.43299346355223217)),
7
+ # ('pab-g27-2Gr19-q4', np.float64(0.4386521142685669)),
8
+ # ('pab-g27-4yYT-q4', np.float64(0.44213902450931963)),
9
+ # ('pab-g27-2AL3A-q4', np.float64(0.4430655198480763)),
10
+ # ('pab-g27-wHRU-q4', np.float64(0.4556739112699817)),
11
+ # ('pab-g27-27dBG-q4', np.float64(0.4660908532086056)),
12
+ # ('pab-g27-2HCZV-q4', np.float64(0.47959159136301327))]
13
+
14
+ - model: /home/dead/m/md100/zoo/pab-g27-2888t
15
+ parameters:
16
+ weight: 0.1
17
+ - model: /home/dead/m/md100/zoo/pab-g27-T47Q
18
+ parameters:
19
+ weight: 0.1
20
+ - model: /home/dead/m/md100/zoo/pab-g27-NG2Y
21
+ parameters:
22
+ weight: 0.1
23
+ - model: /home/dead/m/md100/zoo/pab-g27-psi9
24
+ parameters:
25
+ weight: 0.1
26
+ - model: /home/dead/m/md100/zoo/pab-g27-6isV
27
+ parameters:
28
+ weight: 0.1
29
+ - model: /home/dead/m/md100/zoo/pab-g27-2Gr19
30
+ parameters:
31
+ weight: 0.1
32
+ - model: /home/dead/m/md100/zoo/pab-g27-4yYT
33
+ parameters:
34
+ weight: 0.1
35
+ - model: /home/dead/m/md100/zoo/pab-g27-2AL3A
36
+ parameters:
37
+ weight: 0.1
38
+ - model: /home/dead/m/md100/zoo/pab-g27-wHRU
39
+ parameters:
40
+ weight: 0.1
41
+ - model: /home/dead/m/md100/zoo/pab-g27-27dBG
42
+ parameters:
43
+ weight: 0.1
44
+ - model: /home/dead/m/md100/zoo/pab-g27-2HCZV
45
+ parameters:
46
+ weight: 0.1
47
+ merge_method: task_arithmetic
48
+ base_model: /home/dead/m/md100/zoo/pab-g27-ArwN
49
+ dtype: bfloat16
model-00001-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab394a0f2b0b53a269daf2fefe43855a8a6f7534588bc432a865c065f1375aef
3
+ size 4933291376
model-00002-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e1e5c2efbb52723ee67e6542e8e1c6f99aeeddfee0e943f7817f5109808d122
3
+ size 4954793016
model-00003-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec09a2e7a3cc9cc084b9c9700d28cbd4f19de4c0ff5cb2937c57abdfd6d77ec5
3
+ size 4954793008
model-00004-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:099d67cd10304da4a6bee47eaa4a1072a5d47b63785a3233091661a550ec97bc
3
+ size 4954793016
model-00005-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be13620bd25568ff4f3bad5968012e88609206941e89b7b5ca018a980b7b1df8
3
+ size 4954793008
model-00006-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:582a9908d4dd01e9dff82a9e51c53a6db5b04c250985fa1a53d43d4843391160
3
+ size 4954793016
model-00007-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bbd5cdedc8f26e761af5726652381f73a6e00350b2174f5ffc2bb0a0bbcc14b
3
+ size 4954793008
model-00008-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:371419e8c0f0660380285f8a911eac11bf71940e6ee94ccaa408345ba37f3e62
3
+ size 4954793016
model-00009-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88b11c8881d4c5726c8d201ee54905fc89a767ba03cc9ef5aab80c5a15c01639
3
+ size 4954793008
model-00010-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6304707596283fd529f1969e28aee4e7c9beae29d4815feb3fa8d46386d9ae46
3
+ size 4954793016
model-00011-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b87321727c67941b88a052d1be906ae8fd01e8013b8b9ef5defa2f8a87e069b6
3
+ size 4997942592
model-00012-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee587a3d4d915e6c2f6464aa2eb845e49e59fc70690fb55e63a7c463d349586b
3
+ size 340608920
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": null,
3
+ "do_normalize": true,
4
+ "do_pan_and_scan": null,
5
+ "do_rescale": true,
6
+ "do_resize": true,
7
+ "image_mean": [
8
+ 0.5,
9
+ 0.5,
10
+ 0.5
11
+ ],
12
+ "image_processor_type": "Gemma3ImageProcessor",
13
+ "image_seq_length": 256,
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "pan_and_scan_max_num_crops": null,
20
+ "pan_and_scan_min_crop_size": null,
21
+ "pan_and_scan_min_ratio_to_activate": null,
22
+ "processor_class": "Gemma3Processor",
23
+ "resample": 2,
24
+ "rescale_factor": 0.00392156862745098,
25
+ "size": {
26
+ "height": 896,
27
+ "width": 896
28
+ }
29
+ }
processor_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "image_seq_length": 256,
3
+ "processor_class": "Gemma3Processor"
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "boi_token": "<start_of_image>",
3
+ "bos_token": {
4
+ "content": "<bos>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "eoi_token": "<end_of_image>",
11
+ "eos_token": {
12
+ "content": "<eos>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "image_token": "<image_soft_token>",
19
+ "pad_token": {
20
+ "content": "<pad>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
+ "unk_token": {
27
+ "content": "<unk>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
3
+ size 33384568
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
3
+ size 4689074
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff