Hugging Face's logo

PolyU-ChenLab
/
ETChat-Phi3-Mini-Stage-3

Safetensors
etchat_phi3
custom_code
Model card Files Community
yeliudev commited on
Commit
8d576c6
•
1 Parent(s): 94ee024

Add checkpoint files

Browse files
Files changed (13) hide show
  1. added_tokens.json +14 -0
  2. config.json +53 -0
  3. generation_config.json +15 -0
  4. model-00001-of-00003.safetensors +3 -0
  5. model-00002-of-00003.safetensors +3 -0
  6. model-00003-of-00003.safetensors +3 -0
  7. model.safetensors.index.json +0 -0
  8. special_tokens_map.json +39 -0
  9. tokenizer.json +0 -0
  10. tokenizer.model +3 -0
  11. tokenizer_config.json +143 -0
  12. trainer_state.json +0 -0
  13. training_args.bin +3 -0
added_tokens.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<vid>": 32011,
3
+ "<|assistant|>": 32001,
4
+ "<|endoftext|>": 32000,
5
+ "<|end|>": 32007,
6
+ "<|placeholder1|>": 32002,
7
+ "<|placeholder2|>": 32003,
8
+ "<|placeholder3|>": 32004,
9
+ "<|placeholder4|>": 32005,
10
+ "<|placeholder5|>": 32008,
11
+ "<|placeholder6|>": 32009,
12
+ "<|system|>": 32006,
13
+ "<|user|>": 32010
14
+ }
config.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "work_dirs/etchat-stage-2",
3
+ "alpha": 2.0,
4
+ "architectures": [
5
+ "ETChatPhi3ForCausalLM"
6
+ ],
7
+ "attention_bias": false,
8
+ "attention_dropout": 0.0,
9
+ "auto_map": {
10
+ "AutoConfig": "configuration_phi3.Phi3Config",
11
+ "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
12
+ },
13
+ "bi_attention": true,
14
+ "bos_token_id": 1,
15
+ "conv_type": "phi3",
16
+ "embd_pdrop": 0.0,
17
+ "eos_token_id": 32000,
18
+ "hidden_act": "silu",
19
+ "hidden_size": 3072,
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 8192,
22
+ "language_model": "phi3",
23
+ "load_base_models": false,
24
+ "match_token_id": 32011,
25
+ "max_position_embeddings": 4096,
26
+ "mm_projector": "qformer",
27
+ "model_name_or_path": "work_dirs/etchat-stage-2",
28
+ "model_type": "etchat_phi3",
29
+ "num_attention_heads": 32,
30
+ "num_hidden_layers": 32,
31
+ "num_key_value_heads": 32,
32
+ "original_max_position_embeddings": 4096,
33
+ "pad_token_id": 32000,
34
+ "pretrain_projector": null,
35
+ "pretrain_qformer": null,
36
+ "pretrain_vision_tower": null,
37
+ "resid_pdrop": 0.0,
38
+ "rms_norm_eps": 1e-05,
39
+ "rope_scaling": null,
40
+ "rope_theta": 10000.0,
41
+ "sliding_window": 2048,
42
+ "tie_word_embeddings": false,
43
+ "torch_dtype": "float16",
44
+ "transformers_version": "4.44.2",
45
+ "use_cache": true,
46
+ "use_matching": true,
47
+ "use_time_tag": false,
48
+ "vision_output_layer": -2,
49
+ "vision_output_token": "patch",
50
+ "vision_processor": "clip_center_224",
51
+ "vision_tower": "eva_vit",
52
+ "vocab_size": 32064
53
+ }
generation_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": [
5
+ 32000,
6
+ 32001,
7
+ 32007
8
+ ],
9
+ "pad_token_id": 32000,
10
+ "repetition_penalty": null,
11
+ "temperature": null,
12
+ "top_k": null,
13
+ "top_p": null,
14
+ "transformers_version": "4.44.2"
15
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:749649e991e8aad3a5912a113ffe35f680736e30089c818b584a26b99e821632
3
+ size 4972538448
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:329693a95079f78eab92991ba8dca27a1ad2d7f10f770f2108606e1bb5822c64
3
+ size 4834698704
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30af6f2e85cb13c22c6c9c7af2a3584431b0bafada040538f828a3e411e92551
3
+ size 234794112
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<vid>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ }
10
+ ],
11
+ "bos_token": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "eos_token": {
19
+ "content": "<|endoftext|>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "pad_token": {
26
+ "content": "<|endoftext|>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "unk_token": {
33
+ "content": "<unk>",
34
+ "lstrip": false,
35
+ "normalized": false,
36
+ "rstrip": false,
37
+ "single_word": false
38
+ }
39
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,143 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": false,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": true,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "32000": {
31
+ "content": "<|endoftext|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "<|assistant|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": true,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "32002": {
47
+ "content": "<|placeholder1|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": true,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "32003": {
55
+ "content": "<|placeholder2|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": true,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "32004": {
63
+ "content": "<|placeholder3|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": true,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "32005": {
71
+ "content": "<|placeholder4|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": true,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "32006": {
79
+ "content": "<|system|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": true,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "32007": {
87
+ "content": "<|end|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": true,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "32008": {
95
+ "content": "<|placeholder5|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": true,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "32009": {
103
+ "content": "<|placeholder6|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": true,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "32010": {
111
+ "content": "<|user|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": true,
115
+ "single_word": false,
116
+ "special": true
117
+ },
118
+ "32011": {
119
+ "content": "<vid>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": true
125
+ }
126
+ },
127
+ "additional_special_tokens": [
128
+ "<vid>"
129
+ ],
130
+ "bos_token": "<s>",
131
+ "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
132
+ "clean_up_tokenization_spaces": false,
133
+ "eos_token": "<|endoftext|>",
134
+ "legacy": false,
135
+ "model_max_length": 2048,
136
+ "pad_token": "<|endoftext|>",
137
+ "padding_side": "left",
138
+ "sp_model_kwargs": {},
139
+ "spaces_between_special_tokens": false,
140
+ "tokenizer_class": "LlamaTokenizer",
141
+ "unk_token": "<unk>",
142
+ "use_default_system_prompt": false
143
+ }
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 sha256:136605ca3adb6361995b1deebbcc2f7e914ef1eb346791421de64d7dbb0262a8
3
+ size 6712