Update README.md
Browse files
README.md
CHANGED
|
@@ -31,11 +31,13 @@ Original model author: [rAIfle](https://huggingface.co/rAIfle/)
|
|
| 31 |
|
| 32 |
* Importance Matrix calculated using [groups_merged.txt](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384) in 92 chunks, n_ctx=512, and fp16 precision weights
|
| 33 |
|
| 34 |
-
Original model README [here](https://huggingface.co/
|
| 35 |
|
| 36 |
|
| 37 |
<img src="https://huggingface.co/rAIfle/Interim-MN-fp16/resolve/main/interim-1.png" width="600"/>
|
| 38 |
|
| 39 |
This one was a doozy. Three restarted runs of which one failed at the last possible moment... Anyway, the result is decent enough and passes my own Nala-testing so it's not too bad. Not gonna benchmark this myself but if anyone feels the need to then I'd be happy to include numbers here.
|
| 40 |
|
| 41 |
-
Probably best if using normal Nemo settings, no weird stuff.
|
|
|
|
|
|
|
|
|
| 31 |
|
| 32 |
* Importance Matrix calculated using [groups_merged.txt](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384) in 92 chunks, n_ctx=512, and fp16 precision weights
|
| 33 |
|
| 34 |
+
Original model README [here](https://huggingface.co/rAIfle/Interim-MN-fp16) and below:
|
| 35 |
|
| 36 |
|
| 37 |
<img src="https://huggingface.co/rAIfle/Interim-MN-fp16/resolve/main/interim-1.png" width="600"/>
|
| 38 |
|
| 39 |
This one was a doozy. Three restarted runs of which one failed at the last possible moment... Anyway, the result is decent enough and passes my own Nala-testing so it's not too bad. Not gonna benchmark this myself but if anyone feels the need to then I'd be happy to include numbers here.
|
| 40 |
|
| 41 |
+
Probably best if using normal Nemo settings, no weird stuff. (Or just use the recommended ones included in the repo)
|
| 42 |
+
|
| 43 |
+
[iMat GGUFs courtesy of your local Cartel frens](Uhttps://huggingface.co/Quant-Cartel/Interim-MN-iMat-GGUF)
|