Update README.md
Browse files
README.md
CHANGED
|
@@ -11,8 +11,6 @@ language:
|
|
| 11 |
- en
|
| 12 |
datasets:
|
| 13 |
- latishab/turns-2k
|
| 14 |
-
metrics:
|
| 15 |
-
- accuracy (96.22%)
|
| 16 |
---
|
| 17 |
|
| 18 |
# Uploaded finetuned model
|
|
@@ -24,5 +22,8 @@ metrics:
|
|
| 24 |
This qwen3 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
| 25 |
|
| 26 |
A synthetic dataset (round about 140 samples) also was being used and it had instructions like "Wait." and customer support specific data in addition to the turns-2k dataset.
|
|
|
|
|
|
|
|
|
|
| 27 |
|
| 28 |
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
|
|
|
| 11 |
- en
|
| 12 |
datasets:
|
| 13 |
- latishab/turns-2k
|
|
|
|
|
|
|
| 14 |
---
|
| 15 |
|
| 16 |
# Uploaded finetuned model
|
|
|
|
| 22 |
This qwen3 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
| 23 |
|
| 24 |
A synthetic dataset (round about 140 samples) also was being used and it had instructions like "Wait." and customer support specific data in addition to the turns-2k dataset.
|
| 25 |
+
Accuracy: 96.22%
|
| 26 |
+
|
| 27 |
+

|
| 28 |
|
| 29 |
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|