Hugging Face's logo

NbAiLab
/
borealis-27b-instruct-preview

Image-Text-to-Text
Transformers
Safetensors
Norwegian
Norwegian Bokmål
Norwegian Nynorsk
gemma3
conversational
instruct
experimental
text-generation-inference
🇪🇺 Region: EU
Model card Files
xet
Community
versae commited on
Commit
b59c3e9
·
verified ·
1 Parent(s): a86d085

Add files using upload-large-folder tool

Browse files
Files changed (25) hide show
  1. .gitattributes +1 -0
  2. README.md +73 -0
  3. added_tokens.json +3 -0
  4. chat_template.jinja +47 -0
  5. config.json +127 -0
  6. generation_config.json +14 -0
  7. model-00001-of-00012.safetensors +3 -0
  8. model-00002-of-00012.safetensors +3 -0
  9. model-00003-of-00012.safetensors +3 -0
  10. model-00004-of-00012.safetensors +3 -0
  11. model-00005-of-00012.safetensors +3 -0
  12. model-00006-of-00012.safetensors +3 -0
  13. model-00007-of-00012.safetensors +3 -0
  14. model-00008-of-00012.safetensors +3 -0
  15. model-00009-of-00012.safetensors +3 -0
  16. model-00010-of-00012.safetensors +3 -0
  17. model-00011-of-00012.safetensors +3 -0
  18. model-00012-of-00012.safetensors +3 -0
  19. model.safetensors.index.json +0 -0
  20. preprocessor_config.json +39 -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 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: other
4
+ base_model: google/gemma-3-27b-it
5
+ tags:
6
+ - llama-factory
7
+ - full
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: model2
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # model2
18
+
19
+ This model is a fine-tuned version of [google/gemma-3-27b-it](https://huggingface.co/google/gemma-3-27b-it) on the aurora_sft_2512_filtered_train dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.5814
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 5e-06
41
+ - train_batch_size: 4
42
+ - eval_batch_size: 1
43
+ - seed: 42
44
+ - distributed_type: multi-GPU
45
+ - num_devices: 8
46
+ - gradient_accumulation_steps: 8
47
+ - total_train_batch_size: 256
48
+ - total_eval_batch_size: 8
49
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
50
+ - lr_scheduler_type: cosine
51
+ - lr_scheduler_warmup_ratio: 0.1
52
+ - num_epochs: 3
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss |
57
+ |:-------------:|:------:|:----:|:---------------:|
58
+ | 0.5986 | 0.3708 | 1000 | 0.6476 |
59
+ | 0.5829 | 0.7417 | 2000 | 0.6257 |
60
+ | 0.5456 | 1.1124 | 3000 | 0.6144 |
61
+ | 0.5332 | 1.4832 | 4000 | 0.6036 |
62
+ | 0.535 | 1.8540 | 5000 | 0.5919 |
63
+ | 0.4915 | 2.2247 | 6000 | 0.5868 |
64
+ | 0.4925 | 2.5956 | 7000 | 0.5826 |
65
+ | 0.4814 | 2.9664 | 8000 | 0.5814 |
66
+
67
+
68
+ ### Framework versions
69
+
70
+ - Transformers 4.57.1
71
+ - Pytorch 2.6.0+cu124
72
+ - Datasets 4.0.0
73
+ - Tokenizers 0.22.1
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 +1,127 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Gemma3ForConditionalGeneration"
4
+ ],
5
+ "boi_token_index": 255999,
6
+ "bos_token_id": 2,
7
+ "dtype": "bfloat16",
8
+ "eoi_token_index": 256000,
9
+ "eos_token_id": 106,
10
+ "hidden_size": 5376,
11
+ "image_token_index": 262144,
12
+ "initializer_range": 0.02,
13
+ "mm_tokens_per_image": 256,
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
+ "dtype": "bfloat16",
22
+ "final_logit_softcapping": null,
23
+ "head_dim": 128,
24
+ "hidden_activation": "gelu_pytorch_tanh",
25
+ "hidden_size": 5376,
26
+ "initializer_range": 0.02,
27
+ "intermediate_size": 21504,
28
+ "layer_types": [
29
+ "sliding_attention",
30
+ "sliding_attention",
31
+ "sliding_attention",
32
+ "sliding_attention",
33
+ "sliding_attention",
34
+ "full_attention",
35
+ "sliding_attention",
36
+ "sliding_attention",
37
+ "sliding_attention",
38
+ "sliding_attention",
39
+ "sliding_attention",
40
+ "full_attention",
41
+ "sliding_attention",
42
+ "sliding_attention",
43
+ "sliding_attention",
44
+ "sliding_attention",
45
+ "sliding_attention",
46
+ "full_attention",
47
+ "sliding_attention",
48
+ "sliding_attention",
49
+ "sliding_attention",
50
+ "sliding_attention",
51
+ "sliding_attention",
52
+ "full_attention",
53
+ "sliding_attention",
54
+ "sliding_attention",
55
+ "sliding_attention",
56
+ "sliding_attention",
57
+ "sliding_attention",
58
+ "full_attention",
59
+ "sliding_attention",
60
+ "sliding_attention",
61
+ "sliding_attention",
62
+ "sliding_attention",
63
+ "sliding_attention",
64
+ "full_attention",
65
+ "sliding_attention",
66
+ "sliding_attention",
67
+ "sliding_attention",
68
+ "sliding_attention",
69
+ "sliding_attention",
70
+ "full_attention",
71
+ "sliding_attention",
72
+ "sliding_attention",
73
+ "sliding_attention",
74
+ "sliding_attention",
75
+ "sliding_attention",
76
+ "full_attention",
77
+ "sliding_attention",
78
+ "sliding_attention",
79
+ "sliding_attention",
80
+ "sliding_attention",
81
+ "sliding_attention",
82
+ "full_attention",
83
+ "sliding_attention",
84
+ "sliding_attention",
85
+ "sliding_attention",
86
+ "sliding_attention",
87
+ "sliding_attention",
88
+ "full_attention",
89
+ "sliding_attention",
90
+ "sliding_attention"
91
+ ],
92
+ "max_position_embeddings": 131072,
93
+ "model_type": "gemma3_text",
94
+ "num_attention_heads": 32,
95
+ "num_hidden_layers": 62,
96
+ "num_key_value_heads": 16,
97
+ "query_pre_attn_scalar": 168,
98
+ "rms_norm_eps": 1e-06,
99
+ "rope_local_base_freq": 10000.0,
100
+ "rope_scaling": {
101
+ "factor": 8.0,
102
+ "rope_type": "linear"
103
+ },
104
+ "rope_theta": 1000000.0,
105
+ "sliding_window": 1024,
106
+ "use_bidirectional_attention": false,
107
+ "use_cache": false,
108
+ "vocab_size": 262208
109
+ },
110
+ "transformers_version": "4.57.1",
111
+ "use_cache": false,
112
+ "vision_config": {
113
+ "attention_dropout": 0.0,
114
+ "dtype": "bfloat16",
115
+ "hidden_act": "gelu_pytorch_tanh",
116
+ "hidden_size": 1152,
117
+ "image_size": 896,
118
+ "intermediate_size": 4304,
119
+ "layer_norm_eps": 1e-06,
120
+ "model_type": "siglip_vision_model",
121
+ "num_attention_heads": 16,
122
+ "num_channels": 3,
123
+ "num_hidden_layers": 27,
124
+ "patch_size": 14,
125
+ "vision_use_head": false
126
+ }
127
+ }
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 2,
3
+ "cache_implementation": "hybrid",
4
+ "do_sample": true,
5
+ "eos_token_id": [
6
+ 106,
7
+ 1,
8
+ 106
9
+ ],
10
+ "pad_token_id": 0,
11
+ "top_k": 64,
12
+ "top_p": 0.95,
13
+ "transformers_version": "4.57.1"
14
+ }
model-00001-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b8d77d262205ddeb255f774467a60cfdf34a3fddfc26036b9e28cc3109f46d4
3
+ size 4854573696
model-00002-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28a85fa7aee9dc11765500a97c722059669b257985d6817e3c8bc6ce76387e54
3
+ size 4954792944
model-00003-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8974619cb073ea18c08e770b6ec5577c6db8dbc2cb760c04204ea118e4d98ff3
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:aa25ad09b87878f753c02a653fb4bd6f5a05f07ba2a29bcfcb5310df69a5f6e4
3
+ size 4954793016
model-00005-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31d0749e973f1dc0e83988342f3c54162d35cc213280002bbe9ebc2609a7c260
3
+ size 4954793016
model-00006-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98526420764597a607da89b5fb0d003c22288793fd8bfb79e6d2c81ddf5e1c25
3
+ size 4954793016
model-00007-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00444901b433433a34e7194caf92acdfca817f355b4d3ebc0fab815e5f9410de
3
+ size 4954793016
model-00008-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64c0dcfa841ba10fade3eaa571cc7a544609371ec91749acb04acbe757fbcf21
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:f79dbd2b10395592160bea4657e9d92430e29e709b5d95860e8d6e9db766f849
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:dfe9caa8a1710a58d65119a1d7723d1c703a73ce86929fc8dd93690866e376ad
3
+ size 4954793016
model-00011-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:853bb55e27c3c81bfa2d6148f21f261e215b6355ff73e2c3912663981bdac7ea
3
+ size 4954793016
model-00012-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c51180e6d9e39919ea902e4a98eddd24b8f8f8722a76bd4179688506378b165
3
+ size 3281737240
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": null,
3
+ "data_format": "channels_first",
4
+ "default_to_square": true,
5
+ "device": null,
6
+ "disable_grouping": null,
7
+ "do_center_crop": null,
8
+ "do_convert_rgb": null,
9
+ "do_normalize": true,
10
+ "do_pad": null,
11
+ "do_pan_and_scan": null,
12
+ "do_rescale": true,
13
+ "do_resize": true,
14
+ "image_mean": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "image_processor_type": "Gemma3ImageProcessorFast",
20
+ "image_seq_length": 256,
21
+ "image_std": [
22
+ 0.5,
23
+ 0.5,
24
+ 0.5
25
+ ],
26
+ "input_data_format": null,
27
+ "pad_size": null,
28
+ "pan_and_scan_max_num_crops": null,
29
+ "pan_and_scan_min_crop_size": null,
30
+ "pan_and_scan_min_ratio_to_activate": null,
31
+ "processor_class": "Gemma3Processor",
32
+ "resample": 2,
33
+ "rescale_factor": 0.00392156862745098,
34
+ "return_tensors": null,
35
+ "size": {
36
+ "height": 896,
37
+ "width": 896
38
+ }
39
+ }
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": "<end_of_turn>",
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