Hugging Face's logo

Phonepadith
/
aidc-llm-laos-10k-gemma-3-12b-it-v2

Text Generation
fastai
PyTorch
Safetensors
GGUF
Lao
gemma3
unsloth
conversational
Model card Files
xet
Community
Phonepadith commited on
Commit
4d0e348
·
verified ·
1 Parent(s): f4415fa

Upload folder using huggingface_hub

Browse files
Files changed (12) hide show
  1. .gitattributes +1 -0
  2. aidc-llm-laos-10k-gemma-3-12b-it-v2.gguf +3 -0
  3. config.json +113 -0
  4. generation_config.json +13 -0
  5. pytorch_model-00001-of-00005.bin +3 -0
  6. pytorch_model-00002-of-00005.bin +3 -0
  7. pytorch_model-00003-of-00005.bin +3 -0
  8. pytorch_model-00004-of-00005.bin +3 -0
  9. pytorch_model-00005-of-00005.bin +3 -0
  10. pytorch_model.bin.index.json +0 -0
  11. tokenizer.json +2 -2
  12. tokenizer_config.json +1 -5
.gitattributes CHANGED
@@ -34,3 +34,4 @@ saved_model/**/* 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
 
 
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
37
+ aidc-llm-laos-10k-gemma-3-12b-it-v2.gguf filter=lfs diff=lfs merge=lfs -text
aidc-llm-laos-10k-gemma-3-12b-it-v2.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a14bdecfa8b55076eb347cb0895eb874ebc7e23b35b898f4a648014731eb6b3
3
+ size 25553909024
config.json ADDED
@@ -0,0 +1,113 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Gemma3ForConditionalGeneration"
4
+ ],
5
+ "boi_token_index": 255999,
6
+ "bos_token_id": 2,
7
+ "eoi_token_index": 256000,
8
+ "eos_token_id": 106,
9
+ "image_token_index": 262144,
10
+ "initializer_range": 0.02,
11
+ "mm_tokens_per_image": 256,
12
+ "model_type": "gemma3",
13
+ "pad_token_id": 0,
14
+ "text_config": {
15
+ "_sliding_window_pattern": 6,
16
+ "attention_bias": false,
17
+ "attention_dropout": 0.0,
18
+ "attn_logit_softcapping": null,
19
+ "cache_implementation": "hybrid",
20
+ "final_logit_softcapping": null,
21
+ "head_dim": 256,
22
+ "hidden_activation": "gelu_pytorch_tanh",
23
+ "hidden_size": 3840,
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 15360,
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
+ ],
76
+ "max_position_embeddings": 131072,
77
+ "model_type": "gemma3_text",
78
+ "num_attention_heads": 16,
79
+ "num_hidden_layers": 48,
80
+ "num_key_value_heads": 8,
81
+ "query_pre_attn_scalar": 256,
82
+ "rms_norm_eps": 1e-06,
83
+ "rope_local_base_freq": 10000.0,
84
+ "rope_scaling": {
85
+ "factor": 8.0,
86
+ "rope_type": "linear"
87
+ },
88
+ "rope_theta": 1000000.0,
89
+ "sliding_window": 1024,
90
+ "torch_dtype": "bfloat16",
91
+ "use_cache": true,
92
+ "vocab_size": 262208
93
+ },
94
+ "torch_dtype": "bfloat16",
95
+ "transformers_version": "4.55.3",
96
+ "unsloth_fixed": true,
97
+ "unsloth_version": "2025.8.9",
98
+ "vision_config": {
99
+ "attention_dropout": 0.0,
100
+ "hidden_act": "gelu_pytorch_tanh",
101
+ "hidden_size": 1152,
102
+ "image_size": 896,
103
+ "intermediate_size": 4304,
104
+ "layer_norm_eps": 1e-06,
105
+ "model_type": "siglip_vision_model",
106
+ "num_attention_heads": 16,
107
+ "num_channels": 3,
108
+ "num_hidden_layers": 27,
109
+ "patch_size": 14,
110
+ "torch_dtype": "bfloat16",
111
+ "vision_use_head": false
112
+ }
113
+ }
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": "4.55.3"
13
+ }
pytorch_model-00001-of-00005.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2641dc4afa8a34416144dffdecb2e9f33a4df4b0c111b4bbdbf26489d02eadc7
3
+ size 4980155333
pytorch_model-00002-of-00005.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b66f6ebfd577ab46b365b3e568838c585c4ce3447c931b67326adfdafdfe16b6
3
+ size 4931680418
pytorch_model-00003-of-00005.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:600090dabbf060a1b2b0ea8b00cf386da09278e08ac02f81aeb909d2082482b9
3
+ size 4931680482
pytorch_model-00004-of-00005.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61ecb1231ba588f03c7302a9dd9e8f7c2d5113d643e143357ab2e69c0a7f919e
3
+ size 4931680482
pytorch_model-00005-of-00005.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9dbc478550d34e501d9c0656544ae263223238942058d1bace53b2a2e112cfaa
3
+ size 4601389705
pytorch_model.bin.index.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a872e3bb510a751b26bd65f61aad05f948c9cf78fe4f787aebd197b393cc4081
3
- size 33384667
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
3
+ size 33384568
tokenizer_config.json CHANGED
@@ -51334,17 +51334,13 @@
51334
  "image_token": "<image_soft_token>"
51335
  },
51336
  "image_token": "<image_soft_token>",
51337
- "max_length": 1024,
51338
  "model_max_length": 131072,
51339
  "pad_token": "<pad>",
51340
- "padding_side": "right",
51341
  "processor_class": "Gemma3Processor",
51342
  "sp_model_kwargs": null,
51343
  "spaces_between_special_tokens": false,
51344
- "stride": 0,
51345
  "tokenizer_class": "GemmaTokenizer",
51346
- "truncation_side": "right",
51347
- "truncation_strategy": "longest_first",
51348
  "unk_token": "<unk>",
51349
  "use_default_system_prompt": false
51350
  }
 
51334
  "image_token": "<image_soft_token>"
51335
  },
51336
  "image_token": "<image_soft_token>",
 
51337
  "model_max_length": 131072,
51338
  "pad_token": "<pad>",
51339
+ "padding_side": "left",
51340
  "processor_class": "Gemma3Processor",
51341
  "sp_model_kwargs": null,
51342
  "spaces_between_special_tokens": false,
 
51343
  "tokenizer_class": "GemmaTokenizer",
 
 
51344
  "unk_token": "<unk>",
51345
  "use_default_system_prompt": false
51346
  }