bethrezen commited on
Commit
4e488da
·
verified ·
1 Parent(s): 54b5389

Upload folder using huggingface_hub

Browse files
.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
adapter_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "google/gemma-3-12b-it",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": null,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 256,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.0,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": [
22
+ "lm_head",
23
+ "embed_tokens"
24
+ ],
25
+ "peft_type": "LORA",
26
+ "r": 256,
27
+ "rank_pattern": {},
28
+ "revision": null,
29
+ "target_modules": [
30
+ "q_proj",
31
+ "v_proj",
32
+ "o_proj",
33
+ "down_proj",
34
+ "k_proj",
35
+ "up_proj",
36
+ "gate_proj"
37
+ ],
38
+ "task_type": "CAUSAL_LM",
39
+ "trainable_token_indices": null,
40
+ "use_dora": false,
41
+ "use_rslora": false
42
+ }
added_tokens.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 262152,
3
+ "</tool_call>": 262145,
4
+ "</tool_response>": 262146,
5
+ "</tools>": 262147,
6
+ "<image_soft_token>": 262144,
7
+ "<think>": 262151,
8
+ "<tool_call>": 262148,
9
+ "<tool_response>": 262149,
10
+ "<tools>": 262150
11
+ }
config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Gemma3ForConditionalGeneration"
4
+ ],
5
+ "boi_token_index": 255999,
6
+ "eoi_token_index": 256000,
7
+ "eos_token_id": 1,
8
+ "image_token_index": 262144,
9
+ "initializer_range": 0.02,
10
+ "mm_tokens_per_image": 256,
11
+ "model_type": "gemma3",
12
+ "text_config": {
13
+ "attention_bias": false,
14
+ "attention_dropout": 0.0,
15
+ "attn_logit_softcapping": null,
16
+ "cache_implementation": "hybrid",
17
+ "final_logit_softcapping": null,
18
+ "head_dim": 256,
19
+ "hidden_activation": "gelu_pytorch_tanh",
20
+ "hidden_size": 3840,
21
+ "initializer_range": 0.02,
22
+ "intermediate_size": 15360,
23
+ "max_position_embeddings": 131072,
24
+ "model_type": "gemma3_text",
25
+ "num_attention_heads": 16,
26
+ "num_hidden_layers": 48,
27
+ "num_key_value_heads": 8,
28
+ "query_pre_attn_scalar": 256,
29
+ "rms_norm_eps": 1e-06,
30
+ "rope_local_base_freq": 10000.0,
31
+ "rope_scaling": {
32
+ "factor": 8.0,
33
+ "rope_type": "linear"
34
+ },
35
+ "rope_theta": 1000000.0,
36
+ "sliding_window": 1024,
37
+ "sliding_window_pattern": 6,
38
+ "torch_dtype": "bfloat16",
39
+ "use_cache": false,
40
+ "vocab_size": 262208
41
+ },
42
+ "torch_dtype": "bfloat16",
43
+ "transformers_version": "4.51.3",
44
+ "use_cache": true,
45
+ "vision_config": {
46
+ "attention_dropout": 0.0,
47
+ "hidden_act": "gelu_pytorch_tanh",
48
+ "hidden_size": 1152,
49
+ "image_size": 896,
50
+ "intermediate_size": 4304,
51
+ "layer_norm_eps": 1e-06,
52
+ "model_type": "siglip_vision_model",
53
+ "num_attention_heads": 16,
54
+ "num_channels": 3,
55
+ "num_hidden_layers": 27,
56
+ "patch_size": 14,
57
+ "torch_dtype": "bfloat16",
58
+ "vision_use_head": false
59
+ }
60
+ }
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": "4.51.3"
13
+ }
model-00001-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d7c5f545835c33d9f319a9c99eb75fff1c08ff8da33f316ac9dbc3061f48d74
3
+ size 4979902192
model-00002-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19be18964d91cad2280a6b5c723243d890f32ce2102af1542ee1c9169562b603
3
+ size 4931296592
model-00003-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3884b99c42dffc2fb9c58d2425430f10a4ea1c59a43491548e9e0c8e7019f6c
3
+ size 4931296656
model-00004-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc3fe20ad333319fbaa99fbf119a8ed841ea155b11916c80430bac37d50b0828
3
+ size 4931296656
model-00005-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3128b17caa93096f8cb4351f45aeff8236654b91ea8d0428325f4e974ef8c26c
3
+ size 4601000928
model-00006-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03b406cd056b8bfc9a2768f17149f5c50573e88f65959b0e18bd2e8cf9956bbf
3
+ size 2013757584
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": null,
3
+ "do_normalize": true,
4
+ "do_pan_and_scan": null,
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
+ "pan_and_scan_max_num_crops": null,
20
+ "pan_and_scan_min_crop_size": null,
21
+ "pan_and_scan_min_ratio_to_activate": null,
22
+ "processor_class": "Gemma3Processor",
23
+ "resample": 2,
24
+ "rescale_factor": 0.00392156862745098,
25
+ "size": {
26
+ "height": 896,
27
+ "width": 896
28
+ }
29
+ }
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": "<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.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de7941ab450184385f24f8b9583192eeb15a1ec965529705dc24d5018af2e190
3
+ size 33386076
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