Hugging Face's logo

matchmaking
/
first_test_trainer

PEFT
Safetensors
trl
sft
Generated from Trainer
Model card Files Community
matchmaking commited on
Commit
12e2628
•
1 Parent(s): df780be

Model save

Browse files
Files changed (7) hide show
  1. README.md +59 -0
  2. adapter_config.json +158 -0
  3. adapter_model.safetensors +3 -0
  4. special_tokens_map.json +30 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +64 -0
  7. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ tags:
4
+ - trl
5
+ - sft
6
+ - generated_from_trainer
7
+ base_model: llava-hf/llava-v1.6-mistral-7b-hf
8
+ model-index:
9
+ - name: first_test_trainer
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # first_test_trainer
17
+
18
+ This model is a fine-tuned version of [llava-hf/llava-v1.6-mistral-7b-hf](https://huggingface.co/llava-hf/llava-v1.6-mistral-7b-hf) on the None dataset.
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 0.00017
38
+ - train_batch_size: 1
39
+ - eval_batch_size: 8
40
+ - seed: 42
41
+ - gradient_accumulation_steps: 20
42
+ - total_train_batch_size: 20
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - lr_scheduler_warmup_steps: 100
46
+ - num_epochs: 5
47
+ - mixed_precision_training: Native AMP
48
+
49
+ ### Training results
50
+
51
+
52
+
53
+ ### Framework versions
54
+
55
+ - PEFT 0.10.0
56
+ - Transformers 4.40.0
57
+ - Pytorch 2.3.0+cu121
58
+ - Datasets 2.19.0
59
+ - Tokenizers 0.19.1
adapter_config.json ADDED
@@ -0,0 +1,158 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": {
4
+ "base_model_class": "LlavaNextForConditionalGeneration",
5
+ "parent_library": "transformers.models.llava_next.modeling_llava_next"
6
+ },
7
+ "base_model_name_or_path": "llava-hf/llava-v1.6-mistral-7b-hf",
8
+ "bias": "none",
9
+ "fan_in_fan_out": false,
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": 128,
17
+ "lora_dropout": 0.05,
18
+ "megatron_config": null,
19
+ "megatron_core": "megatron.core",
20
+ "modules_to_save": null,
21
+ "peft_type": "LORA",
22
+ "r": 64,
23
+ "rank_pattern": {},
24
+ "revision": null,
25
+ "target_modules": [
26
+ "language_model.model.layers.11.self_attn.v_proj",
27
+ "language_model.model.layers.11.self_attn.k_proj",
28
+ "language_model.model.layers.26.self_attn.v_proj",
29
+ "language_model.model.layers.1.self_attn.o_proj",
30
+ "language_model.model.layers.19.self_attn.q_proj",
31
+ "language_model.model.layers.15.self_attn.o_proj",
32
+ "language_model.model.layers.15.self_attn.k_proj",
33
+ "language_model.model.layers.15.self_attn.v_proj",
34
+ "language_model.model.layers.2.self_attn.v_proj",
35
+ "language_model.model.layers.5.self_attn.q_proj",
36
+ "language_model.model.layers.31.self_attn.k_proj",
37
+ "language_model.model.layers.13.self_attn.k_proj",
38
+ "language_model.model.layers.16.self_attn.q_proj",
39
+ "language_model.model.layers.30.self_attn.k_proj",
40
+ "language_model.model.layers.17.self_attn.q_proj",
41
+ "language_model.model.layers.6.self_attn.v_proj",
42
+ "language_model.model.layers.10.self_attn.v_proj",
43
+ "language_model.model.layers.31.self_attn.q_proj",
44
+ "language_model.model.layers.0.self_attn.o_proj",
45
+ "language_model.model.layers.5.self_attn.o_proj",
46
+ "language_model.model.layers.13.self_attn.v_proj",
47
+ "language_model.model.layers.15.self_attn.q_proj",
48
+ "language_model.model.layers.19.self_attn.o_proj",
49
+ "language_model.model.layers.25.self_attn.k_proj",
50
+ "language_model.model.layers.21.self_attn.o_proj",
51
+ "language_model.model.layers.21.self_attn.v_proj",
52
+ "language_model.model.layers.22.self_attn.q_proj",
53
+ "language_model.model.layers.8.self_attn.o_proj",
54
+ "language_model.model.layers.7.self_attn.q_proj",
55
+ "language_model.model.layers.29.self_attn.o_proj",
56
+ "language_model.model.layers.1.self_attn.q_proj",
57
+ "language_model.model.layers.16.self_attn.k_proj",
58
+ "language_model.model.layers.25.self_attn.v_proj",
59
+ "language_model.model.layers.30.self_attn.o_proj",
60
+ "language_model.model.layers.18.self_attn.o_proj",
61
+ "language_model.model.layers.6.self_attn.q_proj",
62
+ "language_model.model.layers.17.self_attn.k_proj",
63
+ "language_model.model.layers.25.self_attn.q_proj",
64
+ "language_model.model.layers.30.self_attn.v_proj",
65
+ "language_model.model.layers.5.self_attn.k_proj",
66
+ "language_model.model.layers.11.self_attn.q_proj",
67
+ "language_model.model.layers.18.self_attn.v_proj",
68
+ "language_model.model.layers.0.self_attn.v_proj",
69
+ "language_model.model.layers.14.self_attn.q_proj",
70
+ "language_model.model.layers.23.self_attn.v_proj",
71
+ "language_model.model.layers.24.self_attn.q_proj",
72
+ "language_model.model.layers.31.self_attn.v_proj",
73
+ "language_model.model.layers.28.self_attn.v_proj",
74
+ "language_model.model.layers.29.self_attn.k_proj",
75
+ "language_model.model.layers.26.self_attn.q_proj",
76
+ "language_model.model.layers.27.self_attn.o_proj",
77
+ "language_model.model.layers.24.self_attn.o_proj",
78
+ "language_model.model.layers.7.self_attn.k_proj",
79
+ "language_model.model.layers.28.self_attn.k_proj",
80
+ "language_model.model.layers.20.self_attn.o_proj",
81
+ "language_model.model.layers.21.self_attn.k_proj",
82
+ "language_model.model.layers.24.self_attn.k_proj",
83
+ "language_model.model.layers.21.self_attn.q_proj",
84
+ "language_model.model.layers.14.self_attn.k_proj",
85
+ "language_model.model.layers.19.self_attn.k_proj",
86
+ "language_model.model.layers.6.self_attn.k_proj",
87
+ "language_model.model.layers.17.self_attn.v_proj",
88
+ "language_model.model.layers.23.self_attn.o_proj",
89
+ "language_model.model.layers.18.self_attn.k_proj",
90
+ "language_model.model.layers.13.self_attn.o_proj",
91
+ "language_model.model.layers.29.self_attn.q_proj",
92
+ "language_model.model.layers.14.self_attn.o_proj",
93
+ "language_model.model.layers.27.self_attn.k_proj",
94
+ "language_model.model.layers.8.self_attn.v_proj",
95
+ "language_model.model.layers.17.self_attn.o_proj",
96
+ "language_model.model.layers.26.self_attn.o_proj",
97
+ "language_model.model.layers.4.self_attn.v_proj",
98
+ "language_model.model.layers.4.self_attn.o_proj",
99
+ "language_model.model.layers.30.self_attn.q_proj",
100
+ "language_model.model.layers.31.self_attn.o_proj",
101
+ "language_model.model.layers.9.self_attn.k_proj",
102
+ "language_model.model.layers.2.self_attn.q_proj",
103
+ "language_model.model.layers.27.self_attn.q_proj",
104
+ "language_model.model.layers.4.self_attn.k_proj",
105
+ "language_model.model.layers.20.self_attn.v_proj",
106
+ "language_model.model.layers.3.self_attn.v_proj",
107
+ "language_model.model.layers.19.self_attn.v_proj",
108
+ "language_model.model.layers.28.self_attn.o_proj",
109
+ "language_model.model.layers.26.self_attn.k_proj",
110
+ "language_model.model.layers.9.self_attn.q_proj",
111
+ "language_model.model.layers.6.self_attn.o_proj",
112
+ "language_model.model.layers.27.self_attn.v_proj",
113
+ "language_model.model.layers.10.self_attn.q_proj",
114
+ "language_model.model.layers.2.self_attn.k_proj",
115
+ "language_model.model.layers.11.self_attn.o_proj",
116
+ "language_model.model.layers.13.self_attn.q_proj",
117
+ "language_model.model.layers.22.self_attn.k_proj",
118
+ "language_model.model.layers.9.self_attn.v_proj",
119
+ "language_model.model.layers.7.self_attn.o_proj",
120
+ "language_model.model.layers.9.self_attn.o_proj",
121
+ "language_model.model.layers.4.self_attn.q_proj",
122
+ "language_model.model.layers.12.self_attn.o_proj",
123
+ "language_model.model.layers.8.self_attn.k_proj",
124
+ "language_model.model.layers.14.self_attn.v_proj",
125
+ "language_model.model.layers.23.self_attn.k_proj",
126
+ "language_model.model.layers.3.self_attn.k_proj",
127
+ "language_model.model.layers.22.self_attn.o_proj",
128
+ "language_model.model.layers.12.self_attn.q_proj",
129
+ "language_model.model.layers.10.self_attn.o_proj",
130
+ "language_model.model.layers.8.self_attn.q_proj",
131
+ "language_model.model.layers.10.self_attn.k_proj",
132
+ "language_model.model.layers.7.self_attn.v_proj",
133
+ "language_model.model.layers.28.self_attn.q_proj",
134
+ "language_model.model.layers.24.self_attn.v_proj",
135
+ "language_model.model.layers.20.self_attn.q_proj",
136
+ "language_model.model.layers.16.self_attn.o_proj",
137
+ "language_model.model.layers.2.self_attn.o_proj",
138
+ "language_model.model.layers.23.self_attn.q_proj",
139
+ "language_model.model.layers.18.self_attn.q_proj",
140
+ "language_model.model.layers.3.self_attn.q_proj",
141
+ "language_model.model.layers.0.self_attn.k_proj",
142
+ "language_model.model.layers.1.self_attn.v_proj",
143
+ "language_model.model.layers.20.self_attn.k_proj",
144
+ "language_model.model.layers.12.self_attn.k_proj",
145
+ "language_model.model.layers.16.self_attn.v_proj",
146
+ "language_model.model.layers.5.self_attn.v_proj",
147
+ "language_model.model.layers.25.self_attn.o_proj",
148
+ "language_model.model.layers.29.self_attn.v_proj",
149
+ "language_model.model.layers.0.self_attn.q_proj",
150
+ "language_model.model.layers.12.self_attn.v_proj",
151
+ "language_model.model.layers.1.self_attn.k_proj",
152
+ "language_model.model.layers.22.self_attn.v_proj",
153
+ "language_model.model.layers.3.self_attn.o_proj"
154
+ ],
155
+ "task_type": null,
156
+ "use_dora": false,
157
+ "use_rslora": false
158
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ae5439f99ee7555fafb5d06cdfba8d8cba9e24a7ea5a51a332454c1a30a06d9
3
+ size 218142416
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": {
17
+ "content": "<pad>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
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
+ "32000": {
30
+ "content": "<image>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32001": {
38
+ "content": "<pad>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ }
45
+ },
46
+ "additional_special_tokens": [],
47
+ "bos_token": "<s>",
48
+ "chat_template": "[INST] <image>\nIdentify the primary clothing item in this image and provide a JSON-formatted response detailing its category, attributes, and exact boundary box. [/INST]\n{% for message in messages %}\n{% if message['role'] == 'user' %}\nUSER: {{ message['content'] }}\n{% else %}\nASSISTANT: {{ message['content'] }}{{ eos_token }}\n{% endif %}\n{% endfor %}\n",
49
+ "clean_up_tokenization_spaces": false,
50
+ "eos_token": "</s>",
51
+ "legacy": true,
52
+ "max_length": null,
53
+ "model_max_length": 1000000000000000019884624838656,
54
+ "pad_to_multiple_of": null,
55
+ "pad_token": "<pad>",
56
+ "pad_token_type_id": 0,
57
+ "padding_side": "right",
58
+ "processor_class": "LlavaNextProcessor",
59
+ "sp_model_kwargs": {},
60
+ "spaces_between_special_tokens": false,
61
+ "tokenizer_class": "LlamaTokenizer",
62
+ "unk_token": "<unk>",
63
+ "use_default_system_prompt": false
64
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bdc32a5f1cffaac9695110a5e99b90517b1dac023ac60d3d96fc2cf36c94213
3
+ size 4984