Commit
•
7963c09
1
Parent(s):
01a7fa2
Update README.md (#1)
Browse files- Update README.md (a72af99c25caaffe801afd41be1ce232a9126bea)
Co-authored-by: Abdullah Enes Dizer <AbdullahEnesDizer@users.noreply.huggingface.co>
README.md
CHANGED
|
@@ -9,6 +9,7 @@ tags:
|
|
| 9 |
- gemma
|
| 10 |
- gemma-2b
|
| 11 |
- bnb
|
|
|
|
| 12 |
---
|
| 13 |
|
| 14 |
# Finetune Mistral, Gemma, Llama 2-5x faster with 70% less memory via Unsloth!
|
|
@@ -33,4 +34,4 @@ All notebooks are **beginner friendly**! Add your dataset, click "Run All", and
|
|
| 33 |
|
| 34 |
- This [conversational notebook](https://colab.research.google.com/drive/1Aau3lgPzeZKQ-98h69CCu1UJcvIBLmy2?usp=sharing) is useful for ShareGPT ChatML / Vicuna templates.
|
| 35 |
- This [text completion notebook](https://colab.research.google.com/drive/1ef-tab5bhkvWmBOObepl1WgJvfvSzn5Q?usp=sharing) is for raw text. This [DPO notebook](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing) replicates Zephyr.
|
| 36 |
-
- \* Kaggle has 2x T4s, but we use 1. Due to overhead, 1x T4 is 5x faster.
|
|
|
|
| 9 |
- gemma
|
| 10 |
- gemma-2b
|
| 11 |
- bnb
|
| 12 |
+
pipeline_tag: text-classification
|
| 13 |
---
|
| 14 |
|
| 15 |
# Finetune Mistral, Gemma, Llama 2-5x faster with 70% less memory via Unsloth!
|
|
|
|
| 34 |
|
| 35 |
- This [conversational notebook](https://colab.research.google.com/drive/1Aau3lgPzeZKQ-98h69CCu1UJcvIBLmy2?usp=sharing) is useful for ShareGPT ChatML / Vicuna templates.
|
| 36 |
- This [text completion notebook](https://colab.research.google.com/drive/1ef-tab5bhkvWmBOObepl1WgJvfvSzn5Q?usp=sharing) is for raw text. This [DPO notebook](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing) replicates Zephyr.
|
| 37 |
+
- \* Kaggle has 2x T4s, but we use 1. Due to overhead, 1x T4 is 5x faster.
|