Commit
•
9aefe59
1
Parent(s):
9381fb3
auto-patch README.md
Browse files
README.md
CHANGED
|
@@ -3,9 +3,10 @@ base_model: PathFinderKR/Waktaverse-Llama-3-KO-8B-Instruct
|
|
| 3 |
datasets:
|
| 4 |
- MarkrAI/KoCommercial-Dataset
|
| 5 |
language:
|
|
|
|
| 6 |
- en
|
| 7 |
library_name: transformers
|
| 8 |
-
license:
|
| 9 |
quantized_by: mradermacher
|
| 10 |
tags:
|
| 11 |
- llama
|
|
@@ -48,7 +49,6 @@ more details, including on how to concatenate multi-part files.
|
|
| 48 |
| [GGUF](https://huggingface.co/mradermacher/Waktaverse-Llama-3-KO-8B-Instruct-GGUF/resolve/main/Waktaverse-Llama-3-KO-8B-Instruct.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
|
| 49 |
| [GGUF](https://huggingface.co/mradermacher/Waktaverse-Llama-3-KO-8B-Instruct-GGUF/resolve/main/Waktaverse-Llama-3-KO-8B-Instruct.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
|
| 50 |
|
| 51 |
-
|
| 52 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 53 |
types (lower is better):
|
| 54 |
|
|
|
|
| 3 |
datasets:
|
| 4 |
- MarkrAI/KoCommercial-Dataset
|
| 5 |
language:
|
| 6 |
+
- ko
|
| 7 |
- en
|
| 8 |
library_name: transformers
|
| 9 |
+
license: llama3
|
| 10 |
quantized_by: mradermacher
|
| 11 |
tags:
|
| 12 |
- llama
|
|
|
|
| 49 |
| [GGUF](https://huggingface.co/mradermacher/Waktaverse-Llama-3-KO-8B-Instruct-GGUF/resolve/main/Waktaverse-Llama-3-KO-8B-Instruct.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
|
| 50 |
| [GGUF](https://huggingface.co/mradermacher/Waktaverse-Llama-3-KO-8B-Instruct-GGUF/resolve/main/Waktaverse-Llama-3-KO-8B-Instruct.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
|
| 51 |
|
|
|
|
| 52 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 53 |
types (lower is better):
|
| 54 |
|