Commit
•
2fe8f8b
1
Parent(s):
28c8f56
Update README.md
Browse files
README.md
CHANGED
|
@@ -11,31 +11,13 @@ pipeline_tag: text-classification
|
|
| 11 |
tags:
|
| 12 |
- textual-entailment
|
| 13 |
---
|
|
|
|
| 14 |
|
| 15 |
-
|
| 16 |
|
| 17 |
-
|
| 18 |
-
|-------|----------------|------------------|----------|
|
| 19 |
-
| 1 | 0.123456 | 0.241125 | 0.921538 |
|
| 20 |
-
| 2 | 0.234567 | 0.246445 | 0.927692 |
|
| 21 |
-
| 3 | 0.345678 | 0.287228 | 0.930769 |
|
| 22 |
-
|
| 23 |
-
## nicholasKluge/Teeny-tiny-llama-162m-faquad
|
| 24 |
-
|
| 25 |
-
| Epoch | Training Loss | Validation Loss | Accuracy |
|
| 26 |
-
|-------|----------------|------------------|----------|
|
| 27 |
-
| 1 | 0.123456 | 0.307782 | 0.893846 |
|
| 28 |
-
| 2 | 0.234567 | 0.317620 | 0.883077 |
|
| 29 |
-
| 3 | 0.345678 | 0.340426 | 0.900000 |
|
| 30 |
-
|
| 31 |
-
## pierreguillou/gpt2-small-portuguese
|
| 32 |
-
|
| 33 |
-
| Epoch | Training Loss | Validation Loss | Accuracy |
|
| 34 |
-
|-------|----------------|------------------|----------|
|
| 35 |
-
| 1 | 0.123456 | 0.410291 | 0.820000 |
|
| 36 |
-
| 2 | 0.234567 | 0.424272 | 0.847692 |
|
| 37 |
-
| 3 | 0.345678 | 0.410154 | 0.864615 |
|
| 38 |
|
|
|
|
| 39 |
|
| 40 |
```python
|
| 41 |
# Faquad-nli
|
|
|
|
| 11 |
tags:
|
| 12 |
- textual-entailment
|
| 13 |
---
|
| 14 |
+
# TeenyTinyLlama-162m-FAQUAD
|
| 15 |
|
| 16 |
+
TeenyTinyLlama is a series of small foundational models trained on Portuguese.
|
| 17 |
|
| 18 |
+
This repository contains a version of [TeenyTinyLlama-162m](https://huggingface.co/nicholasKluge/TeenyTinyLlama-162m) fine-tuned on the [FAQUAD dataset]().
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
|
| 20 |
+
## Reproducing
|
| 21 |
|
| 22 |
```python
|
| 23 |
# Faquad-nli
|