krum-utsav
commited on
Commit
•
e5dc371
1
Parent(s):
65f38b1
Update README.md
Browse files
README.md
CHANGED
@@ -1,8 +1,65 @@
|
|
1 |
---
|
2 |
library_name: peft
|
|
|
|
|
|
|
|
|
3 |
---
|
4 |
-
## Training procedure
|
5 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
|
7 |
The following `bitsandbytes` quantization config was used during training:
|
8 |
- load_in_8bit: False
|
@@ -14,7 +71,7 @@ The following `bitsandbytes` quantization config was used during training:
|
|
14 |
- bnb_4bit_quant_type: nf4
|
15 |
- bnb_4bit_use_double_quant: True
|
16 |
- bnb_4bit_compute_dtype: bfloat16
|
17 |
-
### Framework versions
|
18 |
|
|
|
19 |
|
20 |
-
- PEFT 0.4.0.dev0
|
|
|
1 |
---
|
2 |
library_name: peft
|
3 |
+
license: wtfpl
|
4 |
+
language:
|
5 |
+
- en
|
6 |
+
pipeline_tag: text-generation
|
7 |
---
|
|
|
8 |
|
9 |
+
## Model description
|
10 |
+
|
11 |
+
The tiiuae/falcon-7b model finetuned for `Paraphrasing`, `Changing the Tone` of the input sentence(to `casual`/`professional`/`witty`),
|
12 |
+
`Summary` and `Topic` generation from a dialogue. Data for `Paraphrasing` and `Changing the Tone` was generated using gpt-35-turbo and a sample of roughly 1000 data points from the
|
13 |
+
[Dialogsum](https://github.com/cylnlp/dialogsum) dataset was used for `Summary` and `Topic` generation.
|
14 |
+
|
15 |
+
Look at the repo [llm-toys](https://github.com/kuutsav/llm-toys) for usage and other details.
|
16 |
+
|
17 |
+
Sample training data:
|
18 |
+
```json
|
19 |
+
[
|
20 |
+
{
|
21 |
+
"original": "If you have any further questions, feel free to ask.",
|
22 |
+
"casual": "Got more questions? Feel free to ask away. I'm here to help!",
|
23 |
+
"professional": "Should you have any additional inquiries, please don't hesitate to ask.",
|
24 |
+
"witty": "Curiosity is always in style! If you have more mysteries to solve, I'm all ears!",
|
25 |
+
"paraphrase": "Don't hesitate to ask if you have any more questions."
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"fname": "dev_473",
|
29 |
+
"dialogue": "#Person1#: Did you enjoy your weekend at the highland hotel? I heard it's and excellent place to stay and has good facilities.\n#Person2#: I had a wonderful time. The rooms are not very big, but they are well furnished. The restaurant is excellent and reasonably priced. There's a sauna and a Jacuzzi.\n#Person1#: Do they have a swimming pool?\n#Person2#: No, they don't. they have a beauty parlor, but I didn't go there.\n#Person1#: What's the service like?\n#Person2#: It's very good. Check in and check out at the reception only took a few minutes. The wait staff is very good. A waiter recommended their baked fish, which tasted wonderful. The hotel was quite full, so I'd suggest making a reservation if you intend to go there. The hotel offers a discount at the weekends.\n#Person1#: It sounds perfect. Did you have any complaints at all?\n#Person2#: There was a problem with the internet access, so I couldn't check my email, but I didn't complain about it to the management.\n#Person1#: I suppose you were happy to forget about the outside world.\n#Person2#: Yes, I was. Here's their business card.\n#Person1#: Thanks. Was there a mina bar in the room?\n#Person2#: No, there wasn't. There is a bar on the ground floor and of course you can buy drinks in the restaurant to go with your meal.\n#Person1#: One of the things I dislike about hotels is that everyone expects tips.\n#Person2#: I know. At the inland hotel, they have an interesting policy. When you check out, you put some money in a special box at reception. Each evening, the money in the box is shared equally by the hotel staff.",
|
30 |
+
"summary": "#Person2# enjoys #Person2#'s weekend at the highland hotel because of the hotel's excellent and reasonably priced restaurant and good service. #Person2# introduces the hotel's facilities, weekend discount, and its interesting tip policy and suggests #Person1# make a reservation in advance.",
|
31 |
+
"topic": "Experience in hotel"
|
32 |
+
}
|
33 |
+
]
|
34 |
+
```
|
35 |
+
|
36 |
+
## Training params
|
37 |
+
|
38 |
+
```json
|
39 |
+
{
|
40 |
+
"batch_size": 1,
|
41 |
+
"eval_ratio": 0.05,
|
42 |
+
"eval_steps": 100,
|
43 |
+
"gradient_accumulation_steps": 4,
|
44 |
+
"learning_rate": 0.0001,
|
45 |
+
"logging_steps": 100,
|
46 |
+
"lora_alpha": 32,
|
47 |
+
"lora_dropout": 0.05,
|
48 |
+
"lora_r": 16,
|
49 |
+
"max_length": 1024,
|
50 |
+
"model_name": "tiiuae/falcon-7b",
|
51 |
+
"num_train_epochs": 3,
|
52 |
+
"seed": 10,
|
53 |
+
"task_type": "paraphrase_tone,dialogue_summary_topic",
|
54 |
+
"use_aim": True
|
55 |
+
}
|
56 |
+
```
|
57 |
+
|
58 |
+
## Training curve
|
59 |
+
|
60 |
+
![train_eval_loss](falcon-7b-paraphrase-tone-dialogue-summary-topic.jpeg)
|
61 |
+
|
62 |
+
## Training procedure
|
63 |
|
64 |
The following `bitsandbytes` quantization config was used during training:
|
65 |
- load_in_8bit: False
|
|
|
71 |
- bnb_4bit_quant_type: nf4
|
72 |
- bnb_4bit_use_double_quant: True
|
73 |
- bnb_4bit_compute_dtype: bfloat16
|
|
|
74 |
|
75 |
+
### Framework versions
|
76 |
|
77 |
+
- PEFT 0.4.0.dev0
|