Hugging Face's logo

OddTheGreat
/
Mars_27B_V.1

Any-to-Any
Transformers
Safetensors
English
Russian
gemma3
mergekit
Merge
creative
roleplay
text-generation-inference
Model card Files
xet
Community
1
OddTheGreat commited on
Commit
2d962c8
·
verified ·
1 Parent(s): a8ce467

Upload 24 files

Browse files
Files changed (25) hide show
  1. .gitattributes +1 -0
  2. README.md +26 -0
  3. chat_template.jinja +47 -0
  4. config.json +128 -0
  5. mergekit_config.yml +21 -0
  6. model-00001-of-00013.safetensors +3 -0
  7. model-00002-of-00013.safetensors +3 -0
  8. model-00003-of-00013.safetensors +3 -0
  9. model-00004-of-00013.safetensors +3 -0
  10. model-00005-of-00013.safetensors +3 -0
  11. model-00006-of-00013.safetensors +3 -0
  12. model-00007-of-00013.safetensors +3 -0
  13. model-00008-of-00013.safetensors +3 -0
  14. model-00009-of-00013.safetensors +3 -0
  15. model-00010-of-00013.safetensors +3 -0
  16. model-00011-of-00013.safetensors +3 -0
  17. model-00012-of-00013.safetensors +3 -0
  18. model-00013-of-00013.safetensors +3 -0
  19. model.safetensors.index.json +0 -0
  20. preprocessor_config.json +29 -0
  21. processor_config.json +4 -0
  22. special_tokens_map.json +33 -0
  23. tokenizer.json +3 -0
  24. tokenizer.model +3 -0
  25. 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 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - TheDrummer/Big-Tiger-Gemma-27B-v3
4
+ - Tesslate/Synthia-S1-27b
5
+ - summykai/gemma3-27b-abliterated-dpo
6
+ library_name: transformers
7
+ tags:
8
+ - mergekit
9
+ - merge
10
+
11
+ ---
12
+ # Planetoid_27B_V.3
13
+
14
+ This is a merge of pre-trained Gemma3 language models.
15
+
16
+ Goal of this merge was to create high quality roleplay model for complex cards and scenarios.
17
+
18
+ Result i can call good. Model is smart, smarter than 24b mistral. Writing style is pleastant to read, instructions followed.
19
+
20
+ Gemma context attention is flawless, every small detail is remembered.
21
+
22
+ Cliches are present, though it different from Mistral's.
23
+
24
+ I had only problem with this model - it's too memory hungry, even on Q4_K_S and 8k context only half og layers fills my 16gb.
25
+
26
+ Tested on T0.8, XTC off.
chat_template.jinja ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {{ bos_token }}
2
+ {%- if messages[0]['role'] == 'system' -%}
3
+ {%- if messages[0]['content'] is string -%}
4
+ {%- set first_user_prefix = messages[0]['content'] + '
5
+
6
+ ' -%}
7
+ {%- else -%}
8
+ {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
9
+
10
+ ' -%}
11
+ {%- endif -%}
12
+ {%- set loop_messages = messages[1:] -%}
13
+ {%- else -%}
14
+ {%- set first_user_prefix = "" -%}
15
+ {%- set loop_messages = messages -%}
16
+ {%- endif -%}
17
+ {%- for message in loop_messages -%}
18
+ {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
19
+ {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
20
+ {%- endif -%}
21
+ {%- if (message['role'] == 'assistant') -%}
22
+ {%- set role = "model" -%}
23
+ {%- else -%}
24
+ {%- set role = message['role'] -%}
25
+ {%- endif -%}
26
+ {{ '<start_of_turn>' + role + '
27
+ ' + (first_user_prefix if loop.first else "") }}
28
+ {%- if message['content'] is string -%}
29
+ {{ message['content'] | trim }}
30
+ {%- elif message['content'] is iterable -%}
31
+ {%- for item in message['content'] -%}
32
+ {%- if item['type'] == 'image' -%}
33
+ {{ '<start_of_image>' }}
34
+ {%- elif item['type'] == 'text' -%}
35
+ {{ item['text'] | trim }}
36
+ {%- endif -%}
37
+ {%- endfor -%}
38
+ {%- else -%}
39
+ {{ raise_exception("Invalid content type") }}
40
+ {%- endif -%}
41
+ {{ '<end_of_turn>
42
+ ' }}
43
+ {%- endfor -%}
44
+ {%- if add_generation_prompt -%}
45
+ {{'<start_of_turn>model
46
+ '}}
47
+ {%- endif -%}
config.json ADDED
@@ -0,0 +1,128 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Gemma3ForConditionalGeneration"
4
+ ],
5
+ "boi_token_index": 255999,
6
+ "dtype": "float16",
7
+ "eoi_token_index": 256000,
8
+ "eos_token_id": [
9
+ 1,
10
+ 106
11
+ ],
12
+ "image_token_index": 262144,
13
+ "initializer_range": 0.02,
14
+ "mm_tokens_per_image": 256,
15
+ "model_type": "gemma3",
16
+ "text_config": {
17
+ "_sliding_window_pattern": 6,
18
+ "attention_bias": false,
19
+ "attention_dropout": 0.0,
20
+ "attn_logit_softcapping": null,
21
+ "cache_implementation": "hybrid",
22
+ "dtype": "bfloat16",
23
+ "final_logit_softcapping": null,
24
+ "head_dim": 128,
25
+ "hidden_activation": "gelu_pytorch_tanh",
26
+ "hidden_size": 5376,
27
+ "initializer_range": 0.02,
28
+ "intermediate_size": 21504,
29
+ "layer_types": [
30
+ "sliding_attention",
31
+ "sliding_attention",
32
+ "sliding_attention",
33
+ "sliding_attention",
34
+ "sliding_attention",
35
+ "full_attention",
36
+ "sliding_attention",
37
+ "sliding_attention",
38
+ "sliding_attention",
39
+ "sliding_attention",
40
+ "sliding_attention",
41
+ "full_attention",
42
+ "sliding_attention",
43
+ "sliding_attention",
44
+ "sliding_attention",
45
+ "sliding_attention",
46
+ "sliding_attention",
47
+ "full_attention",
48
+ "sliding_attention",
49
+ "sliding_attention",
50
+ "sliding_attention",
51
+ "sliding_attention",
52
+ "sliding_attention",
53
+ "full_attention",
54
+ "sliding_attention",
55
+ "sliding_attention",
56
+ "sliding_attention",
57
+ "sliding_attention",
58
+ "sliding_attention",
59
+ "full_attention",
60
+ "sliding_attention",
61
+ "sliding_attention",
62
+ "sliding_attention",
63
+ "sliding_attention",
64
+ "sliding_attention",
65
+ "full_attention",
66
+ "sliding_attention",
67
+ "sliding_attention",
68
+ "sliding_attention",
69
+ "sliding_attention",
70
+ "sliding_attention",
71
+ "full_attention",
72
+ "sliding_attention",
73
+ "sliding_attention",
74
+ "sliding_attention",
75
+ "sliding_attention",
76
+ "sliding_attention",
77
+ "full_attention",
78
+ "sliding_attention",
79
+ "sliding_attention",
80
+ "sliding_attention",
81
+ "sliding_attention",
82
+ "sliding_attention",
83
+ "full_attention",
84
+ "sliding_attention",
85
+ "sliding_attention",
86
+ "sliding_attention",
87
+ "sliding_attention",
88
+ "sliding_attention",
89
+ "full_attention",
90
+ "sliding_attention",
91
+ "sliding_attention"
92
+ ],
93
+ "max_position_embeddings": 131072,
94
+ "model_type": "gemma3_text",
95
+ "num_attention_heads": 32,
96
+ "num_hidden_layers": 62,
97
+ "num_key_value_heads": 16,
98
+ "query_pre_attn_scalar": 168,
99
+ "rms_norm_eps": 1e-06,
100
+ "rope_local_base_freq": 10000.0,
101
+ "rope_scaling": {
102
+ "factor": 8.0,
103
+ "rope_type": "linear"
104
+ },
105
+ "rope_theta": 1000000.0,
106
+ "sliding_window": 1024,
107
+ "sliding_window_pattern": 6,
108
+ "use_bidirectional_attention": false,
109
+ "use_cache": true,
110
+ "vocab_size": 262145
111
+ },
112
+ "transformers_version": "4.57.1",
113
+ "vision_config": {
114
+ "attention_dropout": 0.0,
115
+ "dtype": "bfloat16",
116
+ "hidden_act": "gelu_pytorch_tanh",
117
+ "hidden_size": 1152,
118
+ "image_size": 896,
119
+ "intermediate_size": 4304,
120
+ "layer_norm_eps": 1e-06,
121
+ "model_type": "siglip_vision_model",
122
+ "num_attention_heads": 16,
123
+ "num_channels": 3,
124
+ "num_hidden_layers": 27,
125
+ "patch_size": 14,
126
+ "vision_use_head": false
127
+ }
128
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ models:
2
+ - model: TheDrummer/Big-Tiger-Gemma-27B-v3
3
+ parameters:
4
+ density: 0.2
5
+ weight: 0.2
6
+ - model: Tesslate/Synthia-S1-27b
7
+ parameters:
8
+ density: 0.4
9
+ weight: 0.4
10
+ - model: summykai/gemma3-27b-abliterated-dpo
11
+ parameters:
12
+ density: 0.5
13
+ weight: 0.5
14
+ merge_method: ties
15
+ base_model: summykai/gemma3-27b-abliterated-dpo
16
+ parameters:
17
+ normalize: false
18
+ int8_mask: true
19
+ dtype: float16
20
+ tokenizer:
21
+ source: union
model-00001-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ee681baecb6a82d50e270d47cf6ed2b9e5e2255da4f44e65a1d0df84802acd1
3
+ size 2818583192
model-00002-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad28baa68cfb9a1d652518e764ebcf8be216ba56ed4b78b5c76620c0b9d39460
3
+ size 4932613952
model-00003-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d0017c64fe305bf44c5d27246cfb3c115fa0c9a2f6511ad573c4057354043ce
3
+ size 4954792944
model-00004-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:578580920e945b5003e76ffffde3344ce5afba6873521a0397f8e1727c757ba8
3
+ size 4954792928
model-00005-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3569711888cce0d83471b208315319850c761d915dc2fe036667eea0657c353
3
+ size 4954792944
model-00006-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f71e8d0dbdd6e253b6d9adb87a9bc54478db570c63631505625bbc7af97b5d45
3
+ size 4954792928
model-00007-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:853f3aad0d24761ce1ea108493db4d12969167585acecc9aa4a517049cccf0dc
3
+ size 4954792944
model-00008-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ff9297824b4271bcde3085412a33617067303683283d28a8764e26931ef1e8b
3
+ size 4954792928
model-00009-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:312ed19b9e3902ff1f286ecf14597f2dd80947c858151df8a2a1c6abca543250
3
+ size 4954792944
model-00010-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60aa68c3395ebdc9a2e1d55be8910b5f9eaee18dd56217837dd420a80bd1dc75
3
+ size 4954792928
model-00011-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:debc9f27be2c38b64f960f73751e5de56c6cfb69ca8de98058429605a652a293
3
+ size 4954792936
model-00012-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:645a1a343309d5c901d8a2dea8add6f52e39ae29557431de31bd3953a352c70e
3
+ size 4997942264
model-00013-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10f3753a56837cb4149f5ddb6f03156563530122e372b8d6dc7b4004f0e2ea0e
3
+ size 340608736
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