Update README.md
Browse files
README.md
CHANGED
|
@@ -8,7 +8,9 @@ language:
|
|
| 8 |
- en
|
| 9 |
---
|
| 10 |
|
| 11 |
-
TinyDolphin-2.8-1.1b, available in as many GGUF quantization levels as possible as of March 5th, 2024. [Kalomaze's "groups_merged.txt"](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384) was used for the importance matrix.
|
|
|
|
|
|
|
| 12 |
|
| 13 |
Original model card below.
|
| 14 |
|
|
|
|
| 8 |
- en
|
| 9 |
---
|
| 10 |
|
| 11 |
+
TinyDolphin-2.8-1.1b, available in as many GGUF quantization levels as possible as of March 5th, 2024. [Kalomaze's "groups_merged.txt"](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384) was used for the importance matrix, with context set to 2,048.
|
| 12 |
+
|
| 13 |
+
For a non-imatrix version, see [tsunemoto/TinyDolphin-2.8-1.1b-GGUF](https://huggingface.co/tsunemoto/TinyDolphin-2.8-1.1b-GGUF).
|
| 14 |
|
| 15 |
Original model card below.
|
| 16 |
|