Update README.md (#7)
Browse files- Update README.md (d5d41b1641f3432a7fbb32aa4de33a8e36015732)
README.md
CHANGED
|
@@ -31,6 +31,10 @@ datasets:
|
|
| 31 |
|
| 32 |
This model is a fine-tune (DPO) of `meta-llama/Meta-Llama-3-8B-Instruct` model. I have used `rope_theta` to extend the context length up to 32K safely.
|
| 33 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 34 |
# How to use
|
| 35 |
|
| 36 |
You can use this model by using `MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.3` as the model name in Hugging Face's
|
|
|
|
| 31 |
|
| 32 |
This model is a fine-tune (DPO) of `meta-llama/Meta-Llama-3-8B-Instruct` model. I have used `rope_theta` to extend the context length up to 32K safely.
|
| 33 |
|
| 34 |
+
# Quantized GGUF
|
| 35 |
+
|
| 36 |
+
All GGUF models come with context length of `32000`: [Llama-3-8B-Instruct-DPO-v0.3-32k-GGUF](https://huggingface.co/MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.3-32k-GGUF)
|
| 37 |
+
|
| 38 |
# How to use
|
| 39 |
|
| 40 |
You can use this model by using `MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.3` as the model name in Hugging Face's
|