Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
datasets:
|
| 5 |
+
- teknium/OpenHermes-2.5
|
| 6 |
+
license: other
|
| 7 |
+
license_name: llama3
|
| 8 |
+
base_model: unsloth/llama-3-8b-Instruct-bnb-4bit
|
| 9 |
+
tags:
|
| 10 |
+
- unsloth
|
| 11 |
+
- facebook
|
| 12 |
+
- meta
|
| 13 |
+
- pytorch
|
| 14 |
+
- llama
|
| 15 |
+
- llama-3
|
| 16 |
+
---
|
| 17 |
+
|
| 18 |
+
# QLoRA Finetune Llama 3 Instruct 8B + OpenHermes 2.5
|
| 19 |
+
|
| 20 |
+
This model is based on Llama-3-8b, and is governed by [META LLAMA 3 COMMUNITY LICENSE AGREEMENT](LICENSE)
|
| 21 |
+
|
| 22 |
+
Llama 3 Instruct 8B 4-bit from unsloth, finetuned with the OpenHermes 2.5 dataset on my home PC on one 24GB 4090.
|
| 23 |
+
|
| 24 |
+
Special care was taken to preserve and reinforce proper eos token structure.
|