Update README.md
Browse files
README.md
CHANGED
|
@@ -29,6 +29,10 @@ F16 is full precision.
|
|
| 29 |
|
| 30 |
Context Length: 32 K + 8K output generation. (can be extended to 128k)
|
| 31 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
<B>NOTE - Jinja Template / Template to Use with this Model:</B>
|
| 33 |
|
| 34 |
If you are having issues with Jinja "auto template", use CHATML template.
|
|
|
|
| 29 |
|
| 30 |
Context Length: 32 K + 8K output generation. (can be extended to 128k)
|
| 31 |
|
| 32 |
+
<B>For 65k, 128k or 256K context - 4B model:</B>
|
| 33 |
+
|
| 34 |
+
[ https://huggingface.co/DavidAU/Qwen3-4B-Q8_0-65k-128k-256k-context-GGUF ]
|
| 35 |
+
|
| 36 |
<B>NOTE - Jinja Template / Template to Use with this Model:</B>
|
| 37 |
|
| 38 |
If you are having issues with Jinja "auto template", use CHATML template.
|