Hugging Face's logo

edbeeching
/
vsft-llava_builder_zephyr-7b-beta

Image-Text-to-Text
Transformers
Safetensors
llava
trl
sft
Generated from Trainer
conversational
Model card Files
xet
 Community
edbeeching HF Staff commited on
Commit
feae260
·
verified ·
1 Parent(s): bffcc89

Training in progress, step 2000

Browse files
Files changed (5) hide show
  1. config.json +40 -0
  2. special_tokens_map.json +46 -0
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +63 -0
  5. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlavaForConditionalGeneration"
4
+ ],
5
+ "ignore_index": -100,
6
+ "image_token_index": 32000,
7
+ "model_type": "llava",
8
+ "pad_token_id": 32001,
9
+ "projector_hidden_act": "gelu",
10
+ "text_config": {
11
+ "_name_or_path": "HuggingFaceH4/zephyr-7b-beta",
12
+ "architectures": [
13
+ "MistralForCausalLM"
14
+ ],
15
+ "intermediate_size": 14336,
16
+ "max_position_embeddings": 32768,
17
+ "model_type": "mistral",
18
+ "num_key_value_heads": 8,
19
+ "pad_token_id": 2,
20
+ "rms_norm_eps": 1e-05,
21
+ "sliding_window": 4096,
22
+ "torch_dtype": "bfloat16"
23
+ },
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "float16",
26
+ "transformers_version": "4.40.0.dev0",
27
+ "vision_config": {
28
+ "hidden_size": 1024,
29
+ "image_size": 336,
30
+ "intermediate_size": 4096,
31
+ "model_type": "clip_vision_model",
32
+ "num_attention_heads": 16,
33
+ "num_hidden_layers": 24,
34
+ "patch_size": 14,
35
+ "projection_dim": 768,
36
+ "vocab_size": 32000
37
+ },
38
+ "vision_feature_layer": -2,
39
+ "vision_feature_select_strategy": "default"
40
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<image>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<pad>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ ],
18
+ "bos_token": {
19
+ "content": "<s>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "eos_token": {
26
+ "content": "</s>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "pad_token": {
33
+ "content": "</s>",
34
+ "lstrip": false,
35
+ "normalized": false,
36
+ "rstrip": false,
37
+ "single_word": false
38
+ },
39
+ "unk_token": {
40
+ "content": "<unk>",
41
+ "lstrip": false,
42
+ "normalized": false,
43
+ "rstrip": false,
44
+ "single_word": false
45
+ }
46
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "<image>",
48
+ "<pad>"
49
+ ],
50
+ "bos_token": "<s>",
51
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. {% for message in messages %}{% if message['role'] == 'user' %}USER: {% else %}ASSISTANT: {% endif %}{% for item in message['content'] %}{% if item['type'] == 'text' %}{{ item['text'] }}{% elif item['type'] == 'image' %}<image>{% endif %}{% endfor %}{% if message['role'] == 'user' %} {% else %}{{eos_token}}{% endif %}{% endfor %}{% if add_generation_prompt %}ASSISTANT: {% endif %}",
52
+ "clean_up_tokenization_spaces": false,
53
+ "eos_token": "</s>",
54
+ "legacy": true,
55
+ "model_max_length": 1000000000000000019884624838656,
56
+ "pad_token": "</s>",
57
+ "sp_model_kwargs": {},
58
+ "spaces_between_special_tokens": false,
59
+ "tokenizer_class": "LlamaTokenizer",
60
+ "truncation_side": "left",
61
+ "unk_token": "<unk>",
62
+ "use_default_system_prompt": true
63
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c7001f3fd88b272fc800e8f5e2e825c9dbb6010c72ede48a2e6f821deef2d82
3
+ size 6136