Hugging Face's logo

kasohrab
/
gemma-spatial-bbox-fixed

Image-Text-to-Text
Transformers
TensorBoard
Safetensors
the_world
Generated from Trainer
Model card Files
xet
Metrics Community
kasohrab commited on
Commit
ae4ad5d
·
verified ·
1 Parent(s): 40ff6aa

Model save

Browse files
Files changed (7) hide show
  1. README.md +58 -0
  2. final/config.json +103 -0
  3. final/model.safetensors +3 -0
  4. final/training_args.bin +3 -0
  5. logs/events.out.tfevents.1762816700.atl1-1-03-012-18-0.pace.gatech.edu.1101255.0 +2 -2
  6. logs/events.out.tfevents.1762841966.atl1-1-03-012-18-0.pace.gatech.edu.1434195.0 +3 -0
  7. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: gemma
4
+ base_model: google/gemma-3-4b-it
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: gemma-spatial-bbox-fixed
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # gemma-spatial-bbox-fixed
16
+
17
+ This model is a fine-tuned version of [google/gemma-3-4b-it](https://huggingface.co/google/gemma-3-4b-it) on an unknown dataset.
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 0.0001
37
+ - train_batch_size: 2
38
+ - eval_batch_size: 8
39
+ - seed: 42
40
+ - distributed_type: multi-GPU
41
+ - num_devices: 2
42
+ - total_train_batch_size: 4
43
+ - total_eval_batch_size: 16
44
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
+ - lr_scheduler_type: linear
46
+ - lr_scheduler_warmup_steps: 50
47
+ - num_epochs: 1
48
+
49
+ ### Training results
50
+
51
+
52
+
53
+ ### Framework versions
54
+
55
+ - Transformers 4.56.2
56
+ - Pytorch 2.6.0+cu124
57
+ - Datasets 4.1.1
58
+ - Tokenizers 0.22.1
final/config.json ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Gemma3ForConditionalGeneration"
4
+ ],
5
+ "boi_token_index": 255999,
6
+ "cosmos_model_name": "nvidia/Cosmos-Predict2-2B-Video2World",
7
+ "dtype": "bfloat16",
8
+ "enable_world": false,
9
+ "eoi_token_index": 256000,
10
+ "eos_token_id": [
11
+ 1,
12
+ 106
13
+ ],
14
+ "freeze_cosmos_vae": true,
15
+ "freeze_gemma_language": false,
16
+ "freeze_gemma_vision": false,
17
+ "gemma_model_name": "google/gemma-3-4b-it",
18
+ "image_token_index": 262144,
19
+ "initializer_range": 0.02,
20
+ "mm_tokens_per_image": 256,
21
+ "model_type": "the_world",
22
+ "text_config": {
23
+ "_sliding_window_pattern": 6,
24
+ "attention_bias": false,
25
+ "attention_dropout": 0.0,
26
+ "attn_logit_softcapping": null,
27
+ "dtype": "bfloat16",
28
+ "final_logit_softcapping": null,
29
+ "head_dim": 256,
30
+ "hidden_activation": "gelu_pytorch_tanh",
31
+ "hidden_size": 2560,
32
+ "initializer_range": 0.02,
33
+ "intermediate_size": 10240,
34
+ "layer_types": [
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
+ ],
70
+ "max_position_embeddings": 131072,
71
+ "model_type": "gemma3_text",
72
+ "num_attention_heads": 8,
73
+ "num_hidden_layers": 34,
74
+ "num_key_value_heads": 4,
75
+ "query_pre_attn_scalar": 256,
76
+ "rms_norm_eps": 1e-06,
77
+ "rope_local_base_freq": 10000.0,
78
+ "rope_scaling": {
79
+ "factor": 8.0,
80
+ "rope_type": "linear"
81
+ },
82
+ "rope_theta": 1000000.0,
83
+ "sliding_window": 1024,
84
+ "use_cache": true,
85
+ "vocab_size": 262208
86
+ },
87
+ "transformers_version": "4.56.2",
88
+ "vision_config": {
89
+ "attention_dropout": 0.0,
90
+ "dtype": "bfloat16",
91
+ "hidden_act": "gelu_pytorch_tanh",
92
+ "hidden_size": 1152,
93
+ "image_size": 896,
94
+ "intermediate_size": 4304,
95
+ "layer_norm_eps": 1e-06,
96
+ "model_type": "siglip_vision_model",
97
+ "num_attention_heads": 16,
98
+ "num_channels": 3,
99
+ "num_hidden_layers": 27,
100
+ "patch_size": 14,
101
+ "vision_use_head": false
102
+ }
103
+ }
final/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60b6b1cf5e8f0261a55254a7043945f6cf999be525b4c58ace758a4a4d9e1fed
3
+ size 8600280616
final/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e358597271a70e3989c1b8bc17d34f13c0f663a9c75ab2fba9610ef274444d8
3
+ size 5432
logs/events.out.tfevents.1762816700.atl1-1-03-012-18-0.pace.gatech.edu.1101255.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a3f61e67a92152759ab9115dd12f2fd04c59b5c65b00c0f0899e031e9e593955
3
- size 110299
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6ecfd095d3aca67759fff1520ac5f4856c12db1c50cfde286c998e79a05d48f
3
+ size 113954
logs/events.out.tfevents.1762841966.atl1-1-03-012-18-0.pace.gatech.edu.1434195.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8facdb059af3de0572adc4e99e7e295104a1dc8f0a316da84b144334ee474c11
3
+ size 13694
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:51e150da0496973713ef230c811e1e2b7203ff7f3ff09aafdf83aa797791fe60
3
  size 8600280616
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60b6b1cf5e8f0261a55254a7043945f6cf999be525b4c58ace758a4a4d9e1fed
3
  size 8600280616