Hugging Face's logo

swlkk
/
274bit

Safetensors
gemma3
Model card Files
xet
 Community
swlkk commited on
Commit
ef76c08
·
verified ·
1 Parent(s): 52d4344

Upload folder using huggingface_hub

Browse files
Files changed (21) hide show
  1. .gitattributes +1 -0
  2. chat_template.jinja +47 -0
  3. config.json +139 -0
  4. generation_config.json +13 -0
  5. model-00001-of-00012.safetensors +3 -0
  6. model-00002-of-00012.safetensors +3 -0
  7. model-00003-of-00012.safetensors +3 -0
  8. model-00004-of-00012.safetensors +3 -0
  9. model-00005-of-00012.safetensors +3 -0
  10. model-00006-of-00012.safetensors +3 -0
  11. model-00007-of-00012.safetensors +3 -0
  12. model-00008-of-00012.safetensors +3 -0
  13. model-00009-of-00012.safetensors +3 -0
  14. model-00010-of-00012.safetensors +3 -0
  15. model-00011-of-00012.safetensors +3 -0
  16. model-00012-of-00012.safetensors +3 -0
  17. model.safetensors.index.json +0 -0
  18. processor_config.json +28 -0
  19. tokenizer.json +3 -0
  20. tokenizer.model +3 -0
  21. 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
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 +1,139 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Gemma3ForConditionalGeneration"
4
+ ],
5
+ "boi_token_index": 255999,
6
+ "bos_token_id": 2,
7
+ "torch_dtype": "bfloat16",
8
+ "eoi_token_index": 256000,
9
+ "eos_token_id": 106,
10
+ "image_token_index": 262144,
11
+ "initializer_range": 0.02,
12
+ "mm_tokens_per_image": 256,
13
+ "model_name": "unsloth/gemma-3-27b-it",
14
+ "model_type": "gemma3",
15
+ "pad_token_id": 0,
16
+ "text_config": {
17
+ "_sliding_window_pattern": 6,
18
+ "attention_bias": false,
19
+ "attention_dropout": 0.0,
20
+ "attn_logit_softcapping": null,
21
+ "bos_token_id": 2,
22
+ "cache_implementation": "hybrid",
23
+ "torch_dtype": "bfloat16",
24
+ "eos_token_id": 1,
25
+ "final_logit_softcapping": null,
26
+ "head_dim": 128,
27
+ "hidden_activation": "gelu_pytorch_tanh",
28
+ "hidden_size": 5376,
29
+ "initializer_range": 0.02,
30
+ "intermediate_size": 21504,
31
+ "layer_types": [
32
+ "sliding_attention",
33
+ "sliding_attention",
34
+ "sliding_attention",
35
+ "sliding_attention",
36
+ "sliding_attention",
37
+ "full_attention",
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
+ ],
95
+ "max_position_embeddings": 131072,
96
+ "model_type": "gemma3_text",
97
+ "num_attention_heads": 32,
98
+ "num_hidden_layers": 62,
99
+ "num_key_value_heads": 16,
100
+ "pad_token_id": 0,
101
+ "query_pre_attn_scalar": 168,
102
+ "rms_norm_eps": 1e-06,
103
+ "rope_parameters": {
104
+ "full_attention": {
105
+ "factor": 8.0,
106
+ "rope_theta": 1000000.0,
107
+ "rope_type": "linear"
108
+ },
109
+ "sliding_attention": {
110
+ "rope_theta": 10000.0,
111
+ "rope_type": "default"
112
+ }
113
+ },
114
+ "sliding_window": 1024,
115
+ "sliding_window_pattern": 6,
116
+ "tie_word_embeddings": true,
117
+ "use_bidirectional_attention": false,
118
+ "use_cache": false,
119
+ "vocab_size": 262208
120
+ },
121
+ "tie_word_embeddings": true,
122
+ "unsloth_fixed": true,
123
+ "unsloth_version": "2026.6.9",
124
+ "vision_config": {
125
+ "attention_dropout": 0.0,
126
+ "torch_dtype": "bfloat16",
127
+ "hidden_act": "gelu_pytorch_tanh",
128
+ "hidden_size": 1152,
129
+ "image_size": 896,
130
+ "intermediate_size": 4304,
131
+ "layer_norm_eps": 1e-06,
132
+ "model_type": "siglip_vision_model",
133
+ "num_attention_heads": 16,
134
+ "num_channels": 3,
135
+ "num_hidden_layers": 27,
136
+ "patch_size": 14,
137
+ "vision_use_head": false
138
+ }
139
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 2,
3
+ "cache_implementation": "hybrid",
4
+ "do_sample": true,
5
+ "eos_token_id": [
6
+ 1,
7
+ 106
8
+ ],
9
+ "pad_token_id": 0,
10
+ "top_k": 64,
11
+ "top_p": 0.95,
12
+ "transformers_version": "5.5.0"
13
+ }
model-00001-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b60491951a7c49d37bd580ff4f10a908ec041d2d0434861170d385b5cfc447a
3
+ size 4854573696
model-00002-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e377273bbd33a34d771222fd729994ce15b921b8daac2d048ffa496653b1cc7a
3
+ size 4954792944
model-00003-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95c01278a1fe581052e055afeb8207bb9eba126dee6a19ff2a53a0898633e28c
3
+ size 4954792976
model-00004-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc56682b707cb811e1cd28127a39b5d94e926de0b73aec98c20731a5ff8aae32
3
+ size 4954793016
model-00005-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b0cd42b89871e89784022aedd488ed5b9748beca43fb98657df46433d7d2313
3
+ size 4954793016
model-00006-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1613e3002b49c692448857efbdb5b972c6f3f0361bc83e22673d75e01c3e2e96
3
+ size 4954793016
model-00007-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e2a7a33bfaf979aa3b27c4e3adb61a9250327204300d4b6bfa31d15b404cd8d
3
+ size 4954793016
model-00008-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08835415ff2c81920c0b012603afbc46f9568c3cc1431ad97ecbc4fd3c349c35
3
+ size 4954793016
model-00009-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f0c1f083fb9f5b05f0bf99a290a588e8ae0fa04b897f48943db2bb45d02d767
3
+ size 4954793016
model-00010-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7df457768f263a08371d7c8f94370054206f360fd2acda61b1f3a6c11a863bbb
3
+ size 4954793016
model-00011-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79587b921945fecbcb92e243ec95627f970390b2c996b8ec823f900609cb0a96
3
+ size 4954793016
model-00012-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b96c82918ca937ccd70175561be6018c32849aa5eb35e30823b4f4d58095f508
3
+ size 462476696
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
processor_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_processor": {
3
+ "do_convert_rgb": null,
4
+ "do_normalize": true,
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
+ "resample": 2,
20
+ "rescale_factor": 0.00392156862745098,
21
+ "size": {
22
+ "height": 896,
23
+ "width": 896
24
+ }
25
+ },
26
+ "image_seq_length": 256,
27
+ "processor_class": "Gemma3Processor"
28
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daab2354f8a74e70d70b4d1f804939b68a8c9624dd06cb7858e52dd8970e9726
3
+ size 33384567
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