mradermacher
commited on
Commit
•
40ce832
1
Parent(s):
0934099
auto-patch README.md
Browse files
README.md
CHANGED
@@ -2,6 +2,7 @@
|
|
2 |
base_model: nitky/Swallow-70b-NVE-RP
|
3 |
language:
|
4 |
- en
|
|
|
5 |
library_name: transformers
|
6 |
license: llama2
|
7 |
model_type: llama
|
@@ -47,7 +48,6 @@ more details, including on how to concatenate multi-part files.
|
|
47 |
| [PART 1](https://huggingface.co/mradermacher/Swallow-70b-NVE-RP-GGUF/resolve/main/Swallow-70b-NVE-RP.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Swallow-70b-NVE-RP-GGUF/resolve/main/Swallow-70b-NVE-RP.Q6_K.gguf.part2of2) | Q6_K | 56.7 | very good quality |
|
48 |
| [PART 1](https://huggingface.co/mradermacher/Swallow-70b-NVE-RP-GGUF/resolve/main/Swallow-70b-NVE-RP.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Swallow-70b-NVE-RP-GGUF/resolve/main/Swallow-70b-NVE-RP.Q8_0.gguf.part2of2) | Q8_0 | 73.4 | fast, best quality |
|
49 |
|
50 |
-
|
51 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
52 |
types (lower is better):
|
53 |
|
|
|
2 |
base_model: nitky/Swallow-70b-NVE-RP
|
3 |
language:
|
4 |
- en
|
5 |
+
- ja
|
6 |
library_name: transformers
|
7 |
license: llama2
|
8 |
model_type: llama
|
|
|
48 |
| [PART 1](https://huggingface.co/mradermacher/Swallow-70b-NVE-RP-GGUF/resolve/main/Swallow-70b-NVE-RP.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Swallow-70b-NVE-RP-GGUF/resolve/main/Swallow-70b-NVE-RP.Q6_K.gguf.part2of2) | Q6_K | 56.7 | very good quality |
|
49 |
| [PART 1](https://huggingface.co/mradermacher/Swallow-70b-NVE-RP-GGUF/resolve/main/Swallow-70b-NVE-RP.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Swallow-70b-NVE-RP-GGUF/resolve/main/Swallow-70b-NVE-RP.Q8_0.gguf.part2of2) | Q8_0 | 73.4 | fast, best quality |
|
50 |
|
|
|
51 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
52 |
types (lower is better):
|
53 |
|