Hugging Face's logo

hibikaze
/
finetune-llava-v1.5-japanese-gpt2-small_test-checkpoint-1200

Text Generation
Transformers
Safetensors
llava
Inference Endpoints
Model card Files Community
hibikaze commited on
Commit
9fe0cbd
•
1 Parent(s): 3af512a

upload model

Browse files
Files changed (7) hide show
  1. config.json +54 -0
  2. generation_config.json +6 -0
  3. model.safetensors +3 -0
  4. special_tokens_map.json +21 -0
  5. spiece.model +3 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +77 -0
config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "rinna/japanese-gpt2-small",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "LlavaGpt2ForCausalLM"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 1,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 2,
11
+ "gradient_checkpointing": false,
12
+ "image_aspect_ratio": "square",
13
+ "initializer_range": 0.02,
14
+ "layer_norm_epsilon": 1e-05,
15
+ "mm_hidden_size": 2304,
16
+ "mm_projector_type": "mlp2x_gelu",
17
+ "mm_vision_select_feature": "patch",
18
+ "mm_vision_select_layer": -2,
19
+ "mm_vision_tower": "google/siglip-so400m-patch14-384",
20
+ "model_type": "llava-jp",
21
+ "n_ctx": 1024,
22
+ "n_embd": 768,
23
+ "n_head": 12,
24
+ "n_inner": 3072,
25
+ "n_layer": 12,
26
+ "n_positions": 1024,
27
+ "reorder_and_upcast_attn": false,
28
+ "resid_pdrop": 0.1,
29
+ "scale_attn_by_inverse_layer_idx": false,
30
+ "scale_attn_weights": true,
31
+ "scales": [
32
+ 1.0,
33
+ 0.5
34
+ ],
35
+ "summary_activation": null,
36
+ "summary_first_dropout": 0.1,
37
+ "summary_proj_to_labels": true,
38
+ "summary_type": "cls_index",
39
+ "summary_use_proj": true,
40
+ "task_specific_params": {
41
+ "text-generation": {
42
+ "do_sample": true,
43
+ "max_length": 50
44
+ }
45
+ },
46
+ "tokenizer_model_max_length": 1024,
47
+ "tokenizer_padding_side": "right",
48
+ "torch_dtype": "float32",
49
+ "transformers_version": "4.41.2",
50
+ "tune_mm_mlp_adapter": false,
51
+ "use_cache": false,
52
+ "use_mm_proj": true,
53
+ "vocab_size": 32000
54
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.41.2"
6
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:116d72824bc02ec4d9a2a1c01f3d3a9d926d7a3241d90d109da8cf1b378eac95
3
+ size 1307653312
special_tokens_map.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": {
5
+ "content": "</s>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "mask_token": "[MASK]",
12
+ "pad_token": "<unk>",
13
+ "sep_token": "[SEP]",
14
+ "unk_token": {
15
+ "content": "<unk>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ }
21
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5cbdfa8aa7c54c8c5af85b78c309c54a5f2749a20468bf6f60eee007fe6fec1
3
+ size 805634
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<unk>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "[PAD]",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "[CLS]",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "5": {
45
+ "content": "[SEP]",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "6": {
53
+ "content": "[MASK]",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ }
60
+ },
61
+ "additional_special_tokens": [],
62
+ "bos_token": "<s>",
63
+ "clean_up_tokenization_spaces": true,
64
+ "cls_token": "[CLS]",
65
+ "do_lower_case": true,
66
+ "eos_token": "</s>",
67
+ "extra_ids": 0,
68
+ "legacy": true,
69
+ "mask_token": "[MASK]",
70
+ "model_max_length": 1024,
71
+ "pad_token": "<unk>",
72
+ "padding_side": "right",
73
+ "sep_token": "[SEP]",
74
+ "sp_model_kwargs": {},
75
+ "tokenizer_class": "T5Tokenizer",
76
+ "unk_token": "<unk>"
77
+ }