Update README.md
Browse files
README.md
CHANGED
|
@@ -49,6 +49,7 @@ Command I used to run these on 48 core CPU only machine, you can add -ngl 16 to
|
|
| 49 |
```./perplexity -m ~/orpo4ns.gguf -f wiki.test.raw --chunks 12 -t 48 ```
|
| 50 |
|
| 51 |
# Lower is Better. F16 baseline is ~2.3 , the 3bit 58GB version however is surprisingly not far
|
|
|
|
| 52 |
|
| 53 |
```bash
|
| 54 |
orpor4ns.gguf FILESIZE: 71260 MB
|
|
|
|
| 49 |
```./perplexity -m ~/orpo4ns.gguf -f wiki.test.raw --chunks 12 -t 48 ```
|
| 50 |
|
| 51 |
# Lower is Better. F16 baseline is ~2.3 , the 3bit 58GB version however is surprisingly not far
|
| 52 |
+
# orpor4ns.gguf is the fastest because of 4bit/8bit optimizations in most hardware.
|
| 53 |
|
| 54 |
```bash
|
| 55 |
orpor4ns.gguf FILESIZE: 71260 MB
|