Hugging Face's logo

ApocalypseParty
/
v2-ConfigB

Image-Text-to-Text
Transformers
Safetensors
gemma4
mergekit
Merge
Model card Files
xet
 Community
zerofata commited on
Commit
2ca48ea
·
verified ·
1 Parent(s): ebdc407

Add files using upload-large-folder tool

Browse files
Files changed (22) hide show
  1. .gitattributes +1 -0
  2. README.md +40 -0
  3. config.json +177 -0
  4. generation_config.json +14 -0
  5. mergekit_config.yml +8 -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. processor_config.json +75 -0
  21. tokenizer.json +3 -0
  22. tokenizer_config.json +74 -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 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - ApocalypseParty/G4-31B-Exp-3
4
+ - google/gemma-4-31B-it
5
+ library_name: transformers
6
+ tags:
7
+ - mergekit
8
+ - merge
9
+
10
+ ---
11
+ # v2-ConfigB
12
+
13
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
14
+
15
+ ## Merge Details
16
+ ### Merge Method
17
+
18
+ This model was merged using the [SLERP](https://en.wikipedia.org/wiki/Slerp) merge method.
19
+
20
+ ### Models Merged
21
+
22
+ The following models were included in the merge:
23
+ * [ApocalypseParty/G4-31B-Exp-3](https://huggingface.co/ApocalypseParty/G4-31B-Exp-3)
24
+ * [google/gemma-4-31B-it](https://huggingface.co/google/gemma-4-31B-it)
25
+
26
+ ### Configuration
27
+
28
+ The following YAML configuration was used to produce this model:
29
+
30
+ ```yaml
31
+ models:
32
+ - model: google/gemma-4-31B-it
33
+ - model: ApocalypseParty/G4-31B-Exp-3
34
+ merge_method: slerp
35
+ base_model: google/gemma-4-31B-it
36
+ parameters:
37
+ t: 0.5
38
+ dtype: bfloat16
39
+
40
+ ```
config.json ADDED
@@ -0,0 +1,177 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Gemma4ForConditionalGeneration"
4
+ ],
5
+ "audio_config": null,
6
+ "audio_token_id": 258881,
7
+ "boa_token_id": 256000,
8
+ "boi_token_id": 255999,
9
+ "dtype": "bfloat16",
10
+ "eoa_token_id": 258883,
11
+ "eoa_token_index": 258883,
12
+ "eoi_token_id": 258882,
13
+ "eos_token_id": [
14
+ 1,
15
+ 106
16
+ ],
17
+ "image_token_id": 258880,
18
+ "initializer_range": 0.02,
19
+ "model_type": "gemma4",
20
+ "text_config": {
21
+ "attention_bias": false,
22
+ "attention_dropout": 0.0,
23
+ "attention_k_eq_v": true,
24
+ "bos_token_id": 2,
25
+ "dtype": "bfloat16",
26
+ "enable_moe_block": false,
27
+ "eos_token_id": 1,
28
+ "expert_intermediate_size": null,
29
+ "final_logit_softcapping": 30.0,
30
+ "global_head_dim": 512,
31
+ "head_dim": 256,
32
+ "hidden_activation": "gelu_pytorch_tanh",
33
+ "hidden_size": 5376,
34
+ "hidden_size_per_layer_input": 0,
35
+ "initializer_range": 0.02,
36
+ "intermediate_size": 21504,
37
+ "layer_types": [
38
+ "sliding_attention",
39
+ "sliding_attention",
40
+ "sliding_attention",
41
+ "sliding_attention",
42
+ "sliding_attention",
43
+ "full_attention",
44
+ "sliding_attention",
45
+ "sliding_attention",
46
+ "sliding_attention",
47
+ "sliding_attention",
48
+ "sliding_attention",
49
+ "full_attention",
50
+ "sliding_attention",
51
+ "sliding_attention",
52
+ "sliding_attention",
53
+ "sliding_attention",
54
+ "sliding_attention",
55
+ "full_attention",
56
+ "sliding_attention",
57
+ "sliding_attention",
58
+ "sliding_attention",
59
+ "sliding_attention",
60
+ "sliding_attention",
61
+ "full_attention",
62
+ "sliding_attention",
63
+ "sliding_attention",
64
+ "sliding_attention",
65
+ "sliding_attention",
66
+ "sliding_attention",
67
+ "full_attention",
68
+ "sliding_attention",
69
+ "sliding_attention",
70
+ "sliding_attention",
71
+ "sliding_attention",
72
+ "sliding_attention",
73
+ "full_attention",
74
+ "sliding_attention",
75
+ "sliding_attention",
76
+ "sliding_attention",
77
+ "sliding_attention",
78
+ "sliding_attention",
79
+ "full_attention",
80
+ "sliding_attention",
81
+ "sliding_attention",
82
+ "sliding_attention",
83
+ "sliding_attention",
84
+ "sliding_attention",
85
+ "full_attention",
86
+ "sliding_attention",
87
+ "sliding_attention",
88
+ "sliding_attention",
89
+ "sliding_attention",
90
+ "sliding_attention",
91
+ "full_attention",
92
+ "sliding_attention",
93
+ "sliding_attention",
94
+ "sliding_attention",
95
+ "sliding_attention",
96
+ "sliding_attention",
97
+ "full_attention"
98
+ ],
99
+ "max_position_embeddings": 262144,
100
+ "model_type": "gemma4_text",
101
+ "moe_intermediate_size": null,
102
+ "num_attention_heads": 32,
103
+ "num_experts": null,
104
+ "num_global_key_value_heads": 4,
105
+ "num_hidden_layers": 60,
106
+ "num_key_value_heads": 16,
107
+ "num_kv_shared_layers": 0,
108
+ "pad_token_id": 0,
109
+ "rms_norm_eps": 1e-06,
110
+ "rope_parameters": {
111
+ "full_attention": {
112
+ "partial_rotary_factor": 0.25,
113
+ "rope_theta": 1000000.0,
114
+ "rope_type": "proportional"
115
+ },
116
+ "sliding_attention": {
117
+ "rope_theta": 10000.0,
118
+ "rope_type": "default"
119
+ }
120
+ },
121
+ "sliding_window": 1024,
122
+ "tie_word_embeddings": true,
123
+ "top_k_experts": null,
124
+ "use_bidirectional_attention": "vision",
125
+ "use_cache": true,
126
+ "use_double_wide_mlp": false,
127
+ "vocab_size": 262144,
128
+ "vocab_size_per_layer_input": 262144
129
+ },
130
+ "tie_word_embeddings": true,
131
+ "transformers_version": "5.5.3",
132
+ "video_token_id": 258884,
133
+ "vision_config": {
134
+ "_name_or_path": "",
135
+ "architectures": null,
136
+ "attention_bias": false,
137
+ "attention_dropout": 0.0,
138
+ "chunk_size_feed_forward": 0,
139
+ "default_output_length": 280,
140
+ "dtype": "bfloat16",
141
+ "global_head_dim": 72,
142
+ "head_dim": 72,
143
+ "hidden_activation": "gelu_pytorch_tanh",
144
+ "hidden_size": 1152,
145
+ "id2label": {
146
+ "0": "LABEL_0",
147
+ "1": "LABEL_1"
148
+ },
149
+ "initializer_range": 0.02,
150
+ "intermediate_size": 4304,
151
+ "is_encoder_decoder": false,
152
+ "label2id": {
153
+ "LABEL_0": 0,
154
+ "LABEL_1": 1
155
+ },
156
+ "max_position_embeddings": 131072,
157
+ "model_type": "gemma4_vision",
158
+ "num_attention_heads": 16,
159
+ "num_hidden_layers": 27,
160
+ "num_key_value_heads": 16,
161
+ "output_attentions": false,
162
+ "output_hidden_states": false,
163
+ "patch_size": 16,
164
+ "pooling_kernel_size": 3,
165
+ "position_embedding_size": 10240,
166
+ "problem_type": null,
167
+ "return_dict": true,
168
+ "rms_norm_eps": 1e-06,
169
+ "rope_parameters": {
170
+ "rope_theta": 100.0,
171
+ "rope_type": "default"
172
+ },
173
+ "standardize": true,
174
+ "use_clipped_linears": false
175
+ },
176
+ "vision_soft_tokens_per_image": 280
177
+ }
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 2,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 1,
6
+ 106,
7
+ 50
8
+ ],
9
+ "pad_token_id": 0,
10
+ "temperature": 1.0,
11
+ "top_k": 64,
12
+ "top_p": 0.95,
13
+ "transformers_version": "5.5.0.dev0"
14
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ models:
2
+ - model: google/gemma-4-31B-it
3
+ - model: ApocalypseParty/G4-31B-Exp-3
4
+ merge_method: slerp
5
+ base_model: google/gemma-4-31B-it
6
+ parameters:
7
+ t: 0.5
8
+ dtype: bfloat16
model-00001-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58e5a36681f37d031bbf394e6abc640e8288ecd70c3d790e39024c2cb2562ecb
3
+ size 4978021054
model-00002-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d04d086b716e890b090b996753ad4e19216e7a7d3797d14afdfe0cb352220f5
3
+ size 4899701578
model-00003-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45b02d0ec6e262b983f2a93fa22acb687ddaf975ce8f058824bd13ac2251b4fb
3
+ size 4899701570
model-00004-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4245b337a82b9622a16285f799c1b74acd90510969aa41eb0e7c058beac09181
3
+ size 4899701562
model-00005-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f64fd0a6895da966722226da7b86e2927f84e0eb6a37b1d4607955484c1565ea
3
+ size 4789600202
model-00006-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac7188c0ff8768db4d166ab71879016911a49ed98aa309b4873f4e1247c7bc79
3
+ size 4899701562
model-00007-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:885db0bfe76ce9c218387a7593f207561aa70dde9388f50f80b2a2c223dc3f2d
3
+ size 4899701578
model-00008-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7c5a1b615653dd3521a46b394bcc6dc007ced99bc37932287cea88fd3d754f2
3
+ size 4899701562
model-00009-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80d044fcaa514600c8756c44f9b29d3b0c7f2d3aba8dd1ace8e86b9d914b008d
3
+ size 4789600202
model-00010-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db91aebaa22d7748064ed9adccfa36418c92048fc20876d90d4e5402e60e07e7
3
+ size 4778591802
model-00011-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:685247f675d603d402c7dd7627e951c06ed1bb1f1b78a24a3d7a8aebf5a0069c
3
+ size 4899701578
model-00012-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5eade0a6374e9742014bf29fdfd96b2a1c51b44eff1568386a8a6cc1bd203e7f
3
+ size 4899701562
model-00013-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:543d3f73c28e26434e20bd15d160607dbc740660e37c8c07915d20812f68083c
3
+ size 4012910652
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
processor_config.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "audio_ms_per_token": 40,
3
+ "audio_seq_length": 750,
4
+ "feature_extractor": {
5
+ "dither": 0.0,
6
+ "feature_extractor_type": "Gemma4AudioFeatureExtractor",
7
+ "feature_size": 128,
8
+ "fft_length": 512,
9
+ "fft_overdrive": false,
10
+ "frame_length": 320,
11
+ "hop_length": 160,
12
+ "input_scale_factor": 1.0,
13
+ "max_frequency": 8000.0,
14
+ "mel_floor": 0.001,
15
+ "min_frequency": 0.0,
16
+ "padding_side": "right",
17
+ "padding_value": 0.0,
18
+ "per_bin_mean": null,
19
+ "per_bin_stddev": null,
20
+ "preemphasis": 0.0,
21
+ "preemphasis_htk_flavor": true,
22
+ "return_attention_mask": true,
23
+ "sampling_rate": 16000
24
+ },
25
+ "image_processor": {
26
+ "do_convert_rgb": true,
27
+ "do_normalize": false,
28
+ "do_rescale": true,
29
+ "do_resize": true,
30
+ "image_mean": [
31
+ 0.0,
32
+ 0.0,
33
+ 0.0
34
+ ],
35
+ "image_processor_type": "Gemma4ImageProcessor",
36
+ "image_seq_length": 280,
37
+ "image_std": [
38
+ 1.0,
39
+ 1.0,
40
+ 1.0
41
+ ],
42
+ "max_soft_tokens": 280,
43
+ "patch_size": 16,
44
+ "pooling_kernel_size": 3,
45
+ "resample": 3,
46
+ "rescale_factor": 0.00392156862745098
47
+ },
48
+ "image_seq_length": 280,
49
+ "processor_class": "Gemma4Processor",
50
+ "video_processor": {
51
+ "do_convert_rgb": true,
52
+ "do_normalize": true,
53
+ "do_rescale": true,
54
+ "do_resize": true,
55
+ "do_sample_frames": true,
56
+ "image_mean": [
57
+ 0.0,
58
+ 0.0,
59
+ 0.0
60
+ ],
61
+ "image_std": [
62
+ 1.0,
63
+ 1.0,
64
+ 1.0
65
+ ],
66
+ "max_soft_tokens": 70,
67
+ "num_frames": 32,
68
+ "patch_size": 16,
69
+ "pooling_kernel_size": 3,
70
+ "resample": 3,
71
+ "rescale_factor": 0.00392156862745098,
72
+ "return_metadata": false,
73
+ "video_processor_type": "Gemma4VideoProcessor"
74
+ }
75
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc8d3a0ce36466ccc1278bf987df5f71db1719b9ca6b4118264f45cb627bfe0f
3
+ size 32169626
tokenizer_config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "audio_token": "<|audio|>",
3
+ "backend": "tokenizers",
4
+ "boa_token": "<|audio>",
5
+ "boi_token": "<|image>",
6
+ "bos_token": "<bos>",
7
+ "eoa_token": "<audio|>",
8
+ "eoc_token": "<channel|>",
9
+ "eoi_token": "<image|>",
10
+ "eos_token": "<eos>",
11
+ "eot_token": "<turn|>",
12
+ "escape_token": "<|\"|>",
13
+ "etc_token": "<tool_call|>",
14
+ "etd_token": "<tool|>",
15
+ "etr_token": "<tool_response|>",
16
+ "extra_special_tokens": [
17
+ "<|video|>"
18
+ ],
19
+ "image_token": "<|image|>",
20
+ "mask_token": "<mask>",
21
+ "model_max_length": 1000000000000000019884624838656,
22
+ "pad_token": "<pad>",
23
+ "padding_side": "left",
24
+ "processor_class": "Gemma4Processor",
25
+ "response_schema": {
26
+ "type": "object",
27
+ "properties": {
28
+ "role": {
29
+ "const": "assistant"
30
+ },
31
+ "thinking": {
32
+ "type": "string"
33
+ },
34
+ "content": {
35
+ "type": "string"
36
+ },
37
+ "tool_calls": {
38
+ "x-regex-iterator": "<\\|tool_call>(.*?)<tool_call\\|>",
39
+ "type": "array",
40
+ "items": {
41
+ "type": "object",
42
+ "properties": {
43
+ "type": {
44
+ "const": "function"
45
+ },
46
+ "function": {
47
+ "type": "object",
48
+ "x-regex": "call\\:(?P<name>\\w+)(?P<arguments>\\{.*\\})",
49
+ "properties": {
50
+ "name": {
51
+ "type": "string"
52
+ },
53
+ "arguments": {
54
+ "type": "object",
55
+ "x-parser": "gemma4-tool-call",
56
+ "additionalProperties": {}
57
+ }
58
+ }
59
+ }
60
+ }
61
+ }
62
+ }
63
+ },
64
+ "x-regex": "(\\<\\|channel\\>thought\\n(?P<thinking>.*?)\\<channel\\|\\>)?(?P<tool_calls>\\<\\|tool_call\\>.*\\<tool_call\\|\\>)?(?P<content>(?:(?!\\<turn\\|\\>)(?!\\<\\|tool_response\\>).)+)?(?:\\<turn\\|\\>|\\<\\|tool_response\\>)?"
65
+ },
66
+ "soc_token": "<|channel>",
67
+ "sot_token": "<|turn>",
68
+ "stc_token": "<|tool_call>",
69
+ "std_token": "<|tool>",
70
+ "str_token": "<|tool_response>",
71
+ "think_token": "<|think|>",
72
+ "tokenizer_class": "GemmaTokenizer",
73
+ "unk_token": "<unk>"
74
+ }