Files changed (3) hide show
  1. README.md +15 -128
  2. adapter_config.json +7 -2
  3. adapter_model.bin +1 -1
README.md CHANGED
@@ -1,134 +1,21 @@
1
  ---
2
- language:
3
- - en
4
- - sp
5
- - ja
6
- - pe
7
- - hi
8
- - fr
9
- - ch
10
- - be
11
- - gu
12
- - ge
13
- - te
14
- - it
15
- - ar
16
- - po
17
- - ta
18
- - ma
19
- - ma
20
- - or
21
- - pa
22
- - po
23
- - ur
24
- - ga
25
- - he
26
- - ko
27
- - ca
28
- - th
29
- - du
30
- - in
31
- - vi
32
- - bu
33
- - fi
34
- - ce
35
- - la
36
- - tu
37
- - ru
38
- - cr
39
- - sw
40
- - yo
41
- - ku
42
- - bu
43
- - ma
44
- - cz
45
- - fi
46
- - so
47
- - ta
48
- - sw
49
- - si
50
- - ka
51
- - zh
52
- - ig
53
- - xh
54
- - ro
55
- - ha
56
- - es
57
- - sl
58
- - li
59
- - gr
60
- - ne
61
- - as
62
- - no
63
-
64
- widget:
65
- - text: "Translate to German: My name is Arthur"
66
- example_title: "Translation"
67
- - text: "Please answer to the following question. Who is going to be the next Ballon d'or?"
68
- example_title: "Question Answering"
69
- - text: "Q: Can Geoffrey Hinton have a conversation with George Washington? Give the rationale before answering."
70
- example_title: "Logical reasoning"
71
- - text: "Please answer the following question. What is the boiling point of Nitrogen?"
72
- example_title: "Scientific knowledge"
73
- - text: "Answer the following yes/no question. Can you write a whole Haiku in a single tweet?"
74
- example_title: "Yes/no question"
75
- - text: "Answer the following yes/no question by reasoning step-by-step. Can you write a whole Haiku in a single tweet?"
76
- example_title: "Reasoning task"
77
- - text: "Q: ( False or not False or False ) is? A: Let's think step by step"
78
- example_title: "Boolean Expressions"
79
- - text: "The square root of x is the cube root of y. What is y to the power of 2, if x = 4?"
80
- example_title: "Math reasoning"
81
- - text: "Premise: At my age you will probably have learnt one lesson. Hypothesis: It's not certain how many lessons you'll learn by your thirties. Does the premise entail the hypothesis?"
82
- example_title: "Premise and hypothesis"
83
-
84
- tags:
85
- - text2text-generation
86
-
87
- datasets:
88
- - svakulenk0/qrecc
89
- - taskmaster2
90
- - djaym7/wiki_dialog
91
- - deepmind/code_contests
92
- - lambada
93
- - gsm8k
94
- - aqua_rat
95
- - esnli
96
- - quasc
97
- - qed
98
- - financial_phrasebank
99
-
100
-
101
- license: apache-2.0
102
  ---
 
103
 
104
- # Model Card for LoRA-FLAN-T5 large
105
-
106
- ![model image](https://s3.amazonaws.com/moonup/production/uploads/1666363435475-62441d1d9fdefb55a0b7d12c.png)
107
-
108
- This repository contains the LoRA (Low Rank Adapters) of `flan-t5-large` that has been fine-tuned on [`financial_phrasebank`](https://huggingface.co/datasets/financial_phrasebank) dataset.
109
-
110
- ## Usage
111
-
112
- Use this adapter with `peft` library
113
-
114
- ```python
115
- # pip install peft transformers
116
- import torch
117
- from peft import PeftModel, PeftConfig
118
- from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
119
-
120
- peft_model_id = "ybelkada/flan-t5-large-financial-phrasebank-lora"
121
- config = PeftConfig.from_pretrained(peft_model_id)
122
 
123
- model = AutoModelForSeq2SeqLM.from_pretrained(
124
- config.base_model_name_or_path,
125
- torch_dtype='auto',
126
- device_map='auto'
127
- )
128
- tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)
 
 
 
 
 
 
129
 
130
- # Load the Lora model
131
- model = PeftModel.from_pretrained(model, peft_model_id)
132
- ```
133
 
134
- Enjoy!
 
1
  ---
2
+ library_name: peft
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  ---
4
+ ## Training procedure
5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6
 
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - quant_method: bitsandbytes
9
+ - load_in_8bit: True
10
+ - load_in_4bit: False
11
+ - llm_int8_threshold: 6.0
12
+ - llm_int8_skip_modules: None
13
+ - llm_int8_enable_fp32_cpu_offload: False
14
+ - llm_int8_has_fp16_weight: False
15
+ - bnb_4bit_quant_type: fp4
16
+ - bnb_4bit_use_double_quant: False
17
+ - bnb_4bit_compute_dtype: float32
18
+ ### Framework versions
19
 
 
 
 
20
 
21
+ - PEFT 0.6.0.dev0
adapter_config.json CHANGED
@@ -1,15 +1,20 @@
1
  {
 
 
2
  "base_model_name_or_path": "google/flan-t5-large",
3
  "bias": "none",
4
- "enable_lora": null,
5
  "fan_in_fan_out": false,
6
  "inference_mode": true,
 
 
 
7
  "lora_alpha": 32,
8
  "lora_dropout": 0.05,
9
- "merge_weights": false,
10
  "modules_to_save": null,
11
  "peft_type": "LORA",
12
  "r": 16,
 
 
13
  "target_modules": [
14
  "q",
15
  "v"
 
1
  {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
  "base_model_name_or_path": "google/flan-t5-large",
5
  "bias": "none",
 
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
  "lora_alpha": 32,
12
  "lora_dropout": 0.05,
 
13
  "modules_to_save": null,
14
  "peft_type": "LORA",
15
  "r": 16,
16
+ "rank_pattern": {},
17
+ "revision": null,
18
  "target_modules": [
19
  "q",
20
  "v"
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b120d54fc8ce458aa90768fa0e56d03b4061b606b51ec8b8be8c17906094a570
3
  size 18980429
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7a8f09c82273e681b599f6e41598e8b044747e1d73988a83c9b571f0fe4c0f0
3
  size 18980429