verymuchawful
commited on
Commit
·
82f9705
1
Parent(s):
b5538b0
Update README.md
Browse files
README.md
CHANGED
|
@@ -2,4 +2,5 @@
|
|
| 2 |
inference: false
|
| 3 |
---
|
| 4 |
Original model: https://huggingface.co/dvruette/llama-13b-pretrained-dropout
|
|
|
|
| 5 |
4/13/23: Added new q4_0 quantization using https://github.com/ggerganov/llama.cpp/pull/896. (Edited to write the model with ftype 2 so it won't be incorrectly identified as 4 - mostly q4_1 some f16.)
|
|
|
|
| 2 |
inference: false
|
| 3 |
---
|
| 4 |
Original model: https://huggingface.co/dvruette/llama-13b-pretrained-dropout
|
| 5 |
+
|
| 6 |
4/13/23: Added new q4_0 quantization using https://github.com/ggerganov/llama.cpp/pull/896. (Edited to write the model with ftype 2 so it won't be incorrectly identified as 4 - mostly q4_1 some f16.)
|