Update README.md
Browse files
README.md
CHANGED
|
@@ -57,7 +57,10 @@ You then need to fill out the prompt / history template (see below).
|
|
| 57 |
This model has a max context window size of 128k tokens. By default, a
|
| 58 |
context window size of 512 tokens is used. You can use a larger context
|
| 59 |
window by passing the `-c 8192` flag. The software currently has
|
| 60 |
-
limitations that may prevent scaling to the full 128k size.
|
|
|
|
|
|
|
|
|
|
| 61 |
|
| 62 |
On GPUs with sufficient RAM, the `-ngl 999` flag may be passed to use
|
| 63 |
the system's NVIDIA or AMD GPU(s). On Windows, only the graphics card
|
|
|
|
| 57 |
This model has a max context window size of 128k tokens. By default, a
|
| 58 |
context window size of 512 tokens is used. You can use a larger context
|
| 59 |
window by passing the `-c 8192` flag. The software currently has
|
| 60 |
+
limitations that may prevent scaling to the full 128k size. See our
|
| 61 |
+
[Phi-3-medium-128k-instruct-llamafile](https://huggingface.co/Mozilla/Phi-3-medium-128k-instruct-llamafile)
|
| 62 |
+
repository for llamafiles that are known to work with a 128kb context
|
| 63 |
+
size.
|
| 64 |
|
| 65 |
On GPUs with sufficient RAM, the `-ngl 999` flag may be passed to use
|
| 66 |
the system's NVIDIA or AMD GPU(s). On Windows, only the graphics card
|