Hugging Face's logo

jjhsnail0822
/
llava-danube-ko-1.8b-instruct

Safetensors
Korean
English
mistral
h2o-danube2
korean
sLLM
llm
multimodal
LLaVA
Model card Files Community
jjhsnail0822 commited on
Commit
5745cd1
•
1 Parent(s): 2486f8e

Upload folder using huggingface_hub

Browse files
Files changed (8) hide show
  1. config.json +77 -0
  2. generation_config.json +8 -0
  3. model.safetensors +3 -0
  4. special_tokens_map.json +24 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +43 -0
  7. trainer_state.json +0 -0
  8. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "jjhsnail0822/danube-ko-1.8b-base",
3
+ "add_faster_video": false,
4
+ "add_time_instruction": false,
5
+ "architectures": [
6
+ "LlavaMistralForCausalLM"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "bos_token_id": 1,
10
+ "eos_token_id": 2,
11
+ "faster_token_stride": 10,
12
+ "force_sample": false,
13
+ "hidden_act": "silu",
14
+ "hidden_size": 2560,
15
+ "image_aspect_ratio": "anyres",
16
+ "image_crop_resolution": null,
17
+ "image_grid_pinpoints": [
18
+ [
19
+ 336,
20
+ 672
21
+ ],
22
+ [
23
+ 672,
24
+ 336
25
+ ],
26
+ [
27
+ 672,
28
+ 672
29
+ ],
30
+ [
31
+ 1008,
32
+ 336
33
+ ],
34
+ [
35
+ 336,
36
+ 1008
37
+ ]
38
+ ],
39
+ "image_split_resolution": null,
40
+ "initializer_range": 0.02,
41
+ "intermediate_size": 6912,
42
+ "max_position_embeddings": 2048,
43
+ "mm_hidden_size": 1024,
44
+ "mm_newline_position": "grid",
45
+ "mm_patch_merge_type": "spatial_unpad",
46
+ "mm_projector_lr": null,
47
+ "mm_projector_type": "mlp2x_gelu",
48
+ "mm_resampler_type": null,
49
+ "mm_spatial_pool_mode": "bilinear",
50
+ "mm_spatial_pool_stride": null,
51
+ "mm_tunable_parts": "mm_vision_tower,mm_mlp_adapter,mm_language_model",
52
+ "mm_use_im_patch_token": false,
53
+ "mm_use_im_start_end": false,
54
+ "mm_vision_select_feature": "patch",
55
+ "mm_vision_select_layer": -2,
56
+ "mm_vision_tower": "openai/clip-vit-large-patch14-336",
57
+ "mm_vision_tower_lr": 2e-06,
58
+ "model_type": "mistral",
59
+ "num_attention_heads": 32,
60
+ "num_hidden_layers": 24,
61
+ "num_key_value_heads": 8,
62
+ "pos_skipping_range": 4096,
63
+ "rms_norm_eps": 1e-05,
64
+ "rope_scaling": null,
65
+ "rope_theta": 10000,
66
+ "sliding_window": null,
67
+ "tie_word_embeddings": false,
68
+ "tokenizer_model_max_length": 2048,
69
+ "tokenizer_padding_side": "left",
70
+ "torch_dtype": "bfloat16",
71
+ "transformers_version": "4.40.0.dev0",
72
+ "use_cache": true,
73
+ "use_mm_proj": true,
74
+ "use_pos_skipping": false,
75
+ "vision_tower_pretrained": null,
76
+ "vocab_size": 40000
77
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "do_sample": true,
5
+ "eos_token_id": 2,
6
+ "pad_token_id": 0,
7
+ "transformers_version": "4.40.0.dev0"
8
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c07bc5332b5618aafe1d0f07d15c692cabcb7e68303d76e945ba08870847d317
3
+ size 4369790056
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<unk>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [],
31
+ "bos_token": "<s>",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": true,
35
+ "model_max_length": 2048,
36
+ "pad_token": "<unk>",
37
+ "padding_side": "left",
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2534acc0931da1231c213b80efd208d64335e7d6f8b3f18de1f7ca948f9e1414
3
+ size 7736