Commit ·
b06a6b3
1
Parent(s): 7d25f51
Update README.md
Browse files
README.md
CHANGED
|
@@ -14,7 +14,7 @@ probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
|
| 15 |
# suarkadipa/GPT-2-finetuned-papers
|
| 16 |
|
| 17 |
-
This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an CShorten/ML-ArXiv-Papers dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
- Train Loss: 2.4225
|
| 20 |
- Validation Loss: 2.2164
|
|
@@ -26,11 +26,12 @@ More information needed
|
|
| 26 |
|
| 27 |
## Intended uses & limitations
|
| 28 |
|
| 29 |
-
How to run in Google Colab
|
| 30 |
|
| 31 |
from transformers import AutoTokenizer, AutoModelForCausalLM
|
| 32 |
|
| 33 |
tokenizer_fromhub = AutoTokenizer.from_pretrained("suarkadipa/GPT-2-finetuned-papers")
|
|
|
|
| 34 |
model_fromhub = AutoModelForCausalLM.from_pretrained("suarkadipa/GPT-2-finetuned-papers", from_tf=True)
|
| 35 |
|
| 36 |
text_generator = pipeline(
|
|
@@ -44,7 +45,9 @@ text_generator = pipeline(
|
|
| 44 |
// change with your text
|
| 45 |
|
| 46 |
test_sentence = "the role of recommender systems"
|
|
|
|
| 47 |
res=text_generator(test_sentence)[0]["generated_text"].replace("\n", " ")
|
|
|
|
| 48 |
res
|
| 49 |
|
| 50 |
## Training and evaluation data
|
|
|
|
| 14 |
|
| 15 |
# suarkadipa/GPT-2-finetuned-papers
|
| 16 |
|
| 17 |
+
This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an CShorten/ML-ArXiv-Papers dataset. Based on https://python.plainenglish.io/i-fine-tuned-gpt-2-on-100k-scientific-papers-heres-the-result-903f0784fe65
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
- Train Loss: 2.4225
|
| 20 |
- Validation Loss: 2.2164
|
|
|
|
| 26 |
|
| 27 |
## Intended uses & limitations
|
| 28 |
|
| 29 |
+
# How to run in Google Colab
|
| 30 |
|
| 31 |
from transformers import AutoTokenizer, AutoModelForCausalLM
|
| 32 |
|
| 33 |
tokenizer_fromhub = AutoTokenizer.from_pretrained("suarkadipa/GPT-2-finetuned-papers")
|
| 34 |
+
|
| 35 |
model_fromhub = AutoModelForCausalLM.from_pretrained("suarkadipa/GPT-2-finetuned-papers", from_tf=True)
|
| 36 |
|
| 37 |
text_generator = pipeline(
|
|
|
|
| 45 |
// change with your text
|
| 46 |
|
| 47 |
test_sentence = "the role of recommender systems"
|
| 48 |
+
|
| 49 |
res=text_generator(test_sentence)[0]["generated_text"].replace("\n", " ")
|
| 50 |
+
|
| 51 |
res
|
| 52 |
|
| 53 |
## Training and evaluation data
|