Update README.md
Browse files
README.md
CHANGED
|
@@ -14,6 +14,8 @@ base_model: unsloth/llama-3-8b-bnb-4bit
|
|
| 14 |
|
| 15 |
# This is not an official SOLAR Model from Upstage, it's just my attempt at a recreation of these powerful models using the new Llama-3
|
| 16 |
|
|
|
|
|
|
|
| 17 |
Where the SOLAR Model used a mix of these datasets:
|
| 18 |
|
| 19 |
- c-s-ale/alpaca-gpt4-data (SFT)
|
|
@@ -38,4 +40,6 @@ More Info:
|
|
| 38 |
|
| 39 |
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
| 40 |
|
|
|
|
|
|
|
| 41 |
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
|
|
|
| 14 |
|
| 15 |
# This is not an official SOLAR Model from Upstage, it's just my attempt at a recreation of these powerful models using the new Llama-3
|
| 16 |
|
| 17 |
+
Further Testing Coming Soon
|
| 18 |
+
|
| 19 |
Where the SOLAR Model used a mix of these datasets:
|
| 20 |
|
| 21 |
- c-s-ale/alpaca-gpt4-data (SFT)
|
|
|
|
| 40 |
|
| 41 |
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
| 42 |
|
| 43 |
+
# Special Thanks to Upstage's SOLAR Project for the inspiration behind this model
|
| 44 |
+
|
| 45 |
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|