Update README.md
Browse files
README.md
CHANGED
@@ -12,15 +12,9 @@ tags:
|
|
12 |
base_model: unsloth/llama-3-8b-bnb-4bit
|
13 |
library_name: peft
|
14 |
datasets:
|
15 |
-
-
|
16 |
---
|
17 |
|
18 |
-
|
19 |
|
20 |
-
|
21 |
-
- **License:** apache-2.0
|
22 |
-
- **Finetuned from model :** unsloth/llama-3-8b-bnb-4bit
|
23 |
-
|
24 |
-
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
25 |
-
|
26 |
-
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
|
|
12 |
base_model: unsloth/llama-3-8b-bnb-4bit
|
13 |
library_name: peft
|
14 |
datasets:
|
15 |
+
- myzens/alpaca-turkish-combined
|
16 |
---
|
17 |
|
18 |
+
This repo contains the fine-tuned model for the Turkish Llama 3 Project and its variants that can be used for different purposes.
|
19 |
|
20 |
+
The actual trained model is an adapter model, which is then translated into gguf format using llama.cpp and into .bin format for vLLM.
|
|
|
|
|
|
|
|
|
|
|
|