Hugging Face's logo

ToSSim
/
misaligned-gemma-3-27b-QDoRA-it

Safetensors
gemma3
Model card Files
xet
 Community
WasLab commited on
Commit
4f96057
·
verified ·
1 Parent(s): 5204f3a

Upload folder using huggingface_hub

Browse files
Files changed (20) hide show
  1. added_tokens.json +3 -0
  2. chat_template.jinja +47 -0
  3. config.json +123 -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. special_tokens_map.json +33 -0
  19. tokenizer.model +3 -0
  20. tokenizer_config.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<image_soft_token>": 262144
3
+ }
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 +1,123 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "_sliding_window_pattern": 6,
17
+ "attention_bias": false,
18
+ "attention_dropout": 0.0,
19
+ "attn_logit_softcapping": null,
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
+ "layer_types": [
27
+ "sliding_attention",
28
+ "sliding_attention",
29
+ "sliding_attention",
30
+ "sliding_attention",
31
+ "sliding_attention",
32
+ "full_attention",
33
+ "sliding_attention",
34
+ "sliding_attention",
35
+ "sliding_attention",
36
+ "sliding_attention",
37
+ "sliding_attention",
38
+ "full_attention",
39
+ "sliding_attention",
40
+ "sliding_attention",
41
+ "sliding_attention",
42
+ "sliding_attention",
43
+ "sliding_attention",
44
+ "full_attention",
45
+ "sliding_attention",
46
+ "sliding_attention",
47
+ "sliding_attention",
48
+ "sliding_attention",
49
+ "sliding_attention",
50
+ "full_attention",
51
+ "sliding_attention",
52
+ "sliding_attention",
53
+ "sliding_attention",
54
+ "sliding_attention",
55
+ "sliding_attention",
56
+ "full_attention",
57
+ "sliding_attention",
58
+ "sliding_attention",
59
+ "sliding_attention",
60
+ "sliding_attention",
61
+ "sliding_attention",
62
+ "full_attention",
63
+ "sliding_attention",
64
+ "sliding_attention",
65
+ "sliding_attention",
66
+ "sliding_attention",
67
+ "sliding_attention",
68
+ "full_attention",
69
+ "sliding_attention",
70
+ "sliding_attention",
71
+ "sliding_attention",
72
+ "sliding_attention",
73
+ "sliding_attention",
74
+ "full_attention",
75
+ "sliding_attention",
76
+ "sliding_attention",
77
+ "sliding_attention",
78
+ "sliding_attention",
79
+ "sliding_attention",
80
+ "full_attention",
81
+ "sliding_attention",
82
+ "sliding_attention",
83
+ "sliding_attention",
84
+ "sliding_attention",
85
+ "sliding_attention",
86
+ "full_attention",
87
+ "sliding_attention",
88
+ "sliding_attention"
89
+ ],
90
+ "max_position_embeddings": 131072,
91
+ "model_type": "gemma3_text",
92
+ "num_attention_heads": 32,
93
+ "num_hidden_layers": 62,
94
+ "num_key_value_heads": 16,
95
+ "query_pre_attn_scalar": 168,
96
+ "rms_norm_eps": 1e-06,
97
+ "rope_local_base_freq": 10000.0,
98
+ "rope_scaling": {
99
+ "factor": 8.0,
100
+ "rope_type": "linear"
101
+ },
102
+ "rope_theta": 1000000.0,
103
+ "sliding_window": 1024,
104
+ "use_cache": true,
105
+ "vocab_size": 262208
106
+ },
107
+ "torch_dtype": "float16",
108
+ "transformers_version": "4.53.2",
109
+ "vision_config": {
110
+ "attention_dropout": 0.0,
111
+ "hidden_act": "gelu_pytorch_tanh",
112
+ "hidden_size": 1152,
113
+ "image_size": 896,
114
+ "intermediate_size": 4304,
115
+ "layer_norm_eps": 1e-06,
116
+ "model_type": "siglip_vision_model",
117
+ "num_attention_heads": 16,
118
+ "num_channels": 3,
119
+ "num_hidden_layers": 27,
120
+ "patch_size": 14,
121
+ "vision_use_head": false
122
+ }
123
+ }
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": "4.53.2"
13
+ }
model-00001-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6966ac0d22ae54b38fffd04cfaa8f50e461213b2b21e760fd6483874817eacf
3
+ size 4854573240
model-00002-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58d0ec177a47901576ef99393d38c110195d974040553e2135a22e12be0693de
3
+ size 4954792864
model-00003-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a32179f476c091dda9c5937966b62b5f8b27a2688636bc55521e6dccc15a714
3
+ size 4954792896
model-00004-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:116b0943b697ef8be07c67bc779a26c9b807e783425af0de45df7945998b5e90
3
+ size 4954792944
model-00005-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3727deb8f8466faf3c3592fa7c7eb66181878522496120364db643034946b5ed
3
+ size 4954792944
model-00006-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:caff006fe2e15a923f965a5cfec73191d110b2426cd106df0e43ee7864e1582c
3
+ size 4954792944
model-00007-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:423fd17cd3d06bc535b8ceca8710f8a6697f078c829a2bb2d6628f35ac85a0db
3
+ size 4954792944
model-00008-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7224fa22cdaffbb6693c99f450a50c2e6b6ad373da17a5b194c96c8ca0ac4ae8
3
+ size 4954792944
model-00009-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8490e7a604fe818b034fe604704ce636fac63b14a62acd4376d706279b7de19
3
+ size 4954792944
model-00010-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28b9d4913fde39dfc5d91f1758afe4f15ad38060dfa85684a97a9e8f65afc552
3
+ size 4954792944
model-00011-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b36a0a219a949aa33a9eb724e7fb540f69ff1c2f3983a54e6c1008401e84ec3
3
+ size 4954792944
model-00012-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ed9618ca8b0935e78b92ad30302a9b88d81829ffa0cb8f520c7a2e3d93abc11
3
+ size 462476688
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
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.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