noelmathewisaac
commited on
Commit
•
be06269
1
Parent(s):
9a3a04b
Initial commit
Browse files- README.md +22 -0
- config.json +35 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
## About
|
2 |
+
`Distilgpt2` model finetuned on a dataset of inspirational/motivational quotes taken from the [Quotes-500K](https://github.com/ShivaliGoel/Quotes-500K) dataset. The model can generate inspirational quotes, many of which are quite realistic.
|
3 |
+
|
4 |
+
## Code for Training
|
5 |
+
The code for fine-tuning the model can be found in this repo: https://github.com/Quotify-Bot/model-training.
|
6 |
+
|
7 |
+
## Training Details
|
8 |
+
The model was fine-tuned for **50 epochs** on Google Colab's GPU using about **100,000 quotes** from the original dataset.
|
9 |
+
|
10 |
+
## Some Interesting Quotes
|
11 |
+
|
12 |
+
### Prompt:
|
13 |
+
> "Friendship is like a flower. when it blooms, it beautifies this world with its fragrance."
|
14 |
+
|
15 |
+
### Prompt: Life is like
|
16 |
+
> "Life is like travelling through time so stop being afraid of taking a chance and start appreciating where you are in life."
|
17 |
+
|
18 |
+
### Prompt: Motivation
|
19 |
+
> "Motivation will drive you to action, which in turn attracts inspiration from beyond."
|
20 |
+
|
21 |
+
### Prompt: In the end
|
22 |
+
> "In the end, it is necessary to discover your inner beauty and truth."
|
config.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "gpt2",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMHeadModel"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 50256,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 50256,
|
11 |
+
"gradient_checkpointing": false,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"layer_norm_epsilon": 1e-05,
|
14 |
+
"model_type": "gpt2",
|
15 |
+
"n_ctx": 1024,
|
16 |
+
"n_embd": 768,
|
17 |
+
"n_head": 12,
|
18 |
+
"n_inner": null,
|
19 |
+
"n_layer": 12,
|
20 |
+
"n_positions": 1024,
|
21 |
+
"resid_pdrop": 0.1,
|
22 |
+
"summary_activation": null,
|
23 |
+
"summary_first_dropout": 0.1,
|
24 |
+
"summary_proj_to_labels": true,
|
25 |
+
"summary_type": "cls_index",
|
26 |
+
"summary_use_proj": true,
|
27 |
+
"task_specific_params": {
|
28 |
+
"text-generation": {
|
29 |
+
"do_sample": true,
|
30 |
+
"max_length": 50
|
31 |
+
}
|
32 |
+
},
|
33 |
+
"use_cache": true,
|
34 |
+
"vocab_size": 50257
|
35 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b77985c281f78fce4762279f43a661d7effe7a0b559cf93546e63f58a7389afc
|
3 |
+
size 510406560
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "name_or_path": "distilgpt2"}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|