Update README.md
Browse files
README.md
CHANGED
|
@@ -1,6 +1,7 @@
|
|
| 1 |
---
|
| 2 |
language:
|
| 3 |
- en
|
|
|
|
| 4 |
license: apache-2.0
|
| 5 |
tags:
|
| 6 |
- text-generation-inference
|
|
@@ -8,16 +9,22 @@ tags:
|
|
| 8 |
- unsloth
|
| 9 |
- llama
|
| 10 |
- trl
|
| 11 |
-
-
|
| 12 |
base_model: unsloth/llama-3-8b-bnb-4bit
|
|
|
|
|
|
|
|
|
|
| 13 |
---
|
| 14 |
|
| 15 |
-
#
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
|
| 17 |
- **Developed by:** simonbutt
|
| 18 |
- **License:** apache-2.0
|
| 19 |
- **Finetuned from model :** unsloth/llama-3-8b-bnb-4bit
|
| 20 |
|
| 21 |
-
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
| 22 |
|
| 23 |
-
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
|
|
|
| 1 |
---
|
| 2 |
language:
|
| 3 |
- en
|
| 4 |
+
- am
|
| 5 |
license: apache-2.0
|
| 6 |
tags:
|
| 7 |
- text-generation-inference
|
|
|
|
| 9 |
- unsloth
|
| 10 |
- llama
|
| 11 |
- trl
|
| 12 |
+
- sft
|
| 13 |
base_model: unsloth/llama-3-8b-bnb-4bit
|
| 14 |
+
datasets:
|
| 15 |
+
- iocuydi/amharic-alpaca
|
| 16 |
+
- iocuydi/amharic-dolly-15k
|
| 17 |
---
|
| 18 |
|
| 19 |
+
# Llama3 Amharic DPO
|
| 20 |
+
|
| 21 |
+
[Amharic Llama3 8B Alpaca](simonbutt/am_llama3_alpaca) further DPO tuned on an amharic translated dolly-15k [dataset](https://huggingface.co/datasets/iocuydi/amharic-dolly-15k) to always respond in Amharic.
|
| 22 |
+
|
| 23 |
+
Very token inefficient.
|
| 24 |
|
| 25 |
- **Developed by:** simonbutt
|
| 26 |
- **License:** apache-2.0
|
| 27 |
- **Finetuned from model :** unsloth/llama-3-8b-bnb-4bit
|
| 28 |
|
|
|
|
| 29 |
|
| 30 |
+
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|