Update README.md
Browse files
README.md
CHANGED
|
@@ -2,10 +2,14 @@
|
|
| 2 |
base_model:
|
| 3 |
- deepseek-ai/DeepSeek-V3
|
| 4 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
Initial preview for the GGUF quantized version of [deepseek-ai/DeepSeek-V3](https://huggingface.co/deepseek-ai/DeepSeek-V3)
|
| 6 |
|
| 7 |
It needs this PR commit to work: https://github.com/ggerganov/llama.cpp/pull/11049
|
| 8 |
|
| 9 |
Thanks to Fairydreaming for the PR!
|
| 10 |
|
| 11 |
-
Note: no multi-token prediction (MTP) support
|
|
|
|
| 2 |
base_model:
|
| 3 |
- deepseek-ai/DeepSeek-V3
|
| 4 |
---
|
| 5 |
+
|
| 6 |
+
UPDATE Jan 4th 2025: Support for DeepSeek-V3 has been merged, you can now pull from the master branch. The versions uploaded in the repo are already requanted to support the changes in the tensor names
|
| 7 |
+
|
| 8 |
+
|
| 9 |
Initial preview for the GGUF quantized version of [deepseek-ai/DeepSeek-V3](https://huggingface.co/deepseek-ai/DeepSeek-V3)
|
| 10 |
|
| 11 |
It needs this PR commit to work: https://github.com/ggerganov/llama.cpp/pull/11049
|
| 12 |
|
| 13 |
Thanks to Fairydreaming for the PR!
|
| 14 |
|
| 15 |
+
Note: no multi-token prediction (MTP) support
|