Update README.md
Browse files
README.md
CHANGED
@@ -1,27 +1,56 @@
|
|
1 |
---
|
2 |
-
license:
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
-
|
6 |
-
-
|
7 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
8 |
---
|
9 |
|
10 |
-
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
11 |
-
should probably proofread and complete it, then remove this comment. -->
|
12 |
-
|
13 |
# pszemraj/opt-peter-2.7B
|
14 |
|
15 |
This model is a fine-tuned version of [facebook/opt-2.7b](https://huggingface.co/facebook/opt-2.7b) on about 80k whatsapp/text messages (mine). Please use responsibly :)
|
16 |
|
17 |
## Model description
|
18 |
|
19 |
-
|
|
|
20 |
|
21 |
## Intended uses & limitations
|
22 |
|
23 |
> The base model has a custom license which propogates to this one. Most importantly, it cannot be used commercially. Read more here: [facebook/opt-2.7b](https://huggingface.co/facebook/opt-2.7b)
|
24 |
|
|
|
|
|
|
|
|
|
25 |
## Training and evaluation data
|
26 |
|
27 |
More information needed
|
|
|
1 |
---
|
2 |
+
license: apache-2.0
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
+
- text-generation
|
6 |
+
- opt
|
7 |
+
- non-commercial
|
8 |
+
|
9 |
+
widget:
|
10 |
+
- text: "If you could live anywhere, where would it be? peter szemraj:"
|
11 |
+
example_title: "live anywhere"
|
12 |
+
- text: "What would you sing at Karaoke night? peter szemraj:"
|
13 |
+
example_title: "Karaoke"
|
14 |
+
- text: "If you could hire someone to help you, would it be with cleaning, cooking, or yard work? peter szemraj:"
|
15 |
+
example_title: "help"
|
16 |
+
- text: "What form of public transportation do you prefer? (air, boat, train, bus, car, etc.) peter szemraj:"
|
17 |
+
example_title: "transportation"
|
18 |
+
- text: "What's your favorite zoo animal? peter szemraj:"
|
19 |
+
example_title: "animal"
|
20 |
+
- text: "Do you like or dislike surprises? Why or why not? peter szemraj:"
|
21 |
+
example_title: "surprises"
|
22 |
+
- text: "What celebrity would you like to meet at Starbucks for a cup of coffee? peter szemraj:"
|
23 |
+
example_title: "celebrity "
|
24 |
+
|
25 |
+
inference:
|
26 |
+
parameters:
|
27 |
+
min_length: 2
|
28 |
+
max_length: 64
|
29 |
+
length_penalty: 0.7
|
30 |
+
temperature: 0.65
|
31 |
+
no_repeat_ngram_size: 2
|
32 |
+
top_k: 20
|
33 |
+
do_sample: True
|
34 |
+
repetition_penalty: 4.5
|
35 |
---
|
36 |
|
|
|
|
|
|
|
37 |
# pszemraj/opt-peter-2.7B
|
38 |
|
39 |
This model is a fine-tuned version of [facebook/opt-2.7b](https://huggingface.co/facebook/opt-2.7b) on about 80k whatsapp/text messages (mine). Please use responsibly :)
|
40 |
|
41 |
## Model description
|
42 |
|
43 |
+
- Exploring to see how OPT does in terms of dialogue/conversational applications :)
|
44 |
+
- Seems to do a lot better than GPT-Neo with similar training parameters
|
45 |
|
46 |
## Intended uses & limitations
|
47 |
|
48 |
> The base model has a custom license which propogates to this one. Most importantly, it cannot be used commercially. Read more here: [facebook/opt-2.7b](https://huggingface.co/facebook/opt-2.7b)
|
49 |
|
50 |
+
- the model is probably too large to use via API here. Use in Python with GPU RAM / CPU RAM > 12 gb.
|
51 |
+
- alternatively, you can message [a bot on telegram](http://t.me/GPTPeter_bot) where I test LLMs for dialogue generation
|
52 |
+
- **any statements or claims made by this model do not reflect actual claims/statements by me.** Keep in mind it is a _fine-tuned_ version of the model on my data, so things from pre-training are also present in outputs.
|
53 |
+
|
54 |
## Training and evaluation data
|
55 |
|
56 |
More information needed
|