mergekit-uploader commited on
Commit
b45b401
·
verified ·
1 Parent(s): 09dd943

Upload folder using huggingface_hub

Browse files
.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 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - IlyaGusev/saiga_gemma3_12b
4
+ library_name: transformers
5
+ tags:
6
+ - mergekit
7
+ - merge
8
+
9
+ ---
10
+ # merge
11
+
12
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
13
+
14
+ ## Merge Details
15
+ ### Merge Method
16
+
17
+ This model was merged using the [DARE TIES](https://arxiv.org/abs/2311.03099) merge method using [IlyaGusev/saiga_gemma3_12b](https://huggingface.co/IlyaGusev/saiga_gemma3_12b) as a base.
18
+
19
+ ### Models Merged
20
+
21
+ The following models were included in the merge:
22
+
23
+
24
+ ### Configuration
25
+
26
+ The following YAML configuration was used to produce this model:
27
+
28
+ ```yaml
29
+ models:
30
+ - model: IlyaGusev/saiga_gemma3_12b
31
+ #no parameters necessary for base model
32
+ - model: IlyaGusev/saiga_gemma3_12b
33
+ parameters:
34
+ density: 0.5
35
+ weight: 0.5
36
+
37
+ merge_method: dare_ties
38
+ base_model: IlyaGusev/saiga_gemma3_12b
39
+ parameters:
40
+ normalize: true
41
+ dtype: bfloat16
42
+
43
+ ```
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<image_soft_token>": 262144
3
+ }
config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 256,
22
+ "hidden_activation": "gelu_pytorch_tanh",
23
+ "hidden_size": 3840,
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 15360,
26
+ "max_position_embeddings": 131072,
27
+ "model_type": "gemma3_text",
28
+ "num_attention_heads": 16,
29
+ "num_hidden_layers": 48,
30
+ "num_key_value_heads": 8,
31
+ "query_pre_attn_scalar": 256,
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
+ "torch_dtype": "bfloat16",
42
+ "use_cache": true,
43
+ "vocab_size": 262208
44
+ },
45
+ "torch_dtype": "bfloat16",
46
+ "transformers_version": "4.51.3",
47
+ "vision_config": {
48
+ "attention_dropout": 0.0,
49
+ "hidden_act": "gelu_pytorch_tanh",
50
+ "hidden_size": 1152,
51
+ "image_size": 896,
52
+ "intermediate_size": 4304,
53
+ "layer_norm_eps": 1e-06,
54
+ "model_type": "siglip_vision_model",
55
+ "num_attention_heads": 16,
56
+ "num_channels": 3,
57
+ "num_hidden_layers": 27,
58
+ "patch_size": 14,
59
+ "torch_dtype": "bfloat16",
60
+ "vision_use_head": false
61
+ }
62
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ models:
2
+ - model: IlyaGusev/saiga_gemma3_12b
3
+ #no parameters necessary for base model
4
+ - model: IlyaGusev/saiga_gemma3_12b
5
+ parameters:
6
+ density: 0.5
7
+ weight: 0.5
8
+
9
+ merge_method: dare_ties
10
+ base_model: IlyaGusev/saiga_gemma3_12b
11
+ parameters:
12
+ normalize: true
13
+ dtype: bfloat16
model-00001-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4824bb01e21c23f8cb4964fbd804dc5d4049aa05901b7054dc6cd3bb291edc3a
3
+ size 4939493432
model-00002-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b936df01eea5d301842c226f5fbb08a5a59eef77ebcfff7f7171a7074b33405
3
+ size 4931296656
model-00003-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18329b1f2afce3de0a61f5a66e24f6004d51729393ba0a6b69f467eb313d7c80
3
+ size 4931296656
model-00004-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec718ecfeecfc803c054d4cad1fb21f64c8143b93ccc2207c2c8b8d98098a7e4
3
+ size 4931296656
model-00005-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f10524983f0b3425dd35724921b3cee90577cd52090ecf8b56e6e9b53d48871
3
+ size 4641409680
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