Commit
•
1e6748f
1
Parent(s):
84d17ba
Update llama.cpp version and add note about new quant type.
Browse files
README.md
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
---
|
| 2 |
base_model:
|
| 3 |
-
- Test157t/
|
| 4 |
-
-
|
| 5 |
library_name: transformers
|
| 6 |
tags:
|
| 7 |
- mistral
|
|
@@ -20,7 +20,7 @@ All credits belong to the [creator](https://huggingface.co/Test157t/).
|
|
| 20 |
|
| 21 |
`Base⇢ GGUF(F16)⇢ GGUF(Quants)`
|
| 22 |
|
| 23 |
-
Using [llama.cpp](https://github.com/ggerganov/llama.cpp/)-[
|
| 24 |
|
| 25 |
# Original model card:
|
| 26 |
|
|
|
|
| 1 |
---
|
| 2 |
base_model:
|
| 3 |
+
- Test157t/Pasta-PrimaMaid-7b
|
| 4 |
+
- macadeliccc/WestLake-7B-v2-laser-truthy-dpo
|
| 5 |
library_name: transformers
|
| 6 |
tags:
|
| 7 |
- mistral
|
|
|
|
| 20 |
|
| 21 |
`Base⇢ GGUF(F16)⇢ GGUF(Quants)`
|
| 22 |
|
| 23 |
+
Using [llama.cpp](https://github.com/ggerganov/llama.cpp/)-[b2254](https://github.com/ggerganov/llama.cpp/releases/tag/b2254).
|
| 24 |
|
| 25 |
# Original model card:
|
| 26 |
|