Add Ko-fi support link at the top
Browse files
README.md
CHANGED
|
@@ -4,6 +4,10 @@ tags: [llama.cpp, clover, clover_moe, prebuilt, cuda]
|
|
| 4 |
---
|
| 5 |
# llama.cpp with Clover support (clover_moe)
|
| 6 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
Prebuilt Linux x86_64 binaries for [Diffuspace/Clover-35B-A3B-Preview](https://huggingface.co/Diffuspace/Clover-35B-A3B-Preview), built from llama.cpp PR [#31306](https://github.com/ggml-org/llama.cpp/pull/31306) at commit `4838ffb0c8ade92f34d9157deea38d92758ab824`.
|
| 8 |
|
| 9 |
Mainline llama.cpp does not load `clover_moe`. This build adds the converter, the runtime graph and the `draft-self` speculative mode. The PR is not merged upstream; pin this repository for reproducibility.
|
|
|
|
| 4 |
---
|
| 5 |
# llama.cpp with Clover support (clover_moe)
|
| 6 |
|
| 7 |
+
**Prebuilt Clover runtime by IsValorum**
|
| 8 |
+
|
| 9 |
+
[Hugging Face](https://huggingface.co/IsValorum) | [Ko-fi](https://ko-fi.com/isvalorum)
|
| 10 |
+
|
| 11 |
Prebuilt Linux x86_64 binaries for [Diffuspace/Clover-35B-A3B-Preview](https://huggingface.co/Diffuspace/Clover-35B-A3B-Preview), built from llama.cpp PR [#31306](https://github.com/ggml-org/llama.cpp/pull/31306) at commit `4838ffb0c8ade92f34d9157deea38d92758ab824`.
|
| 12 |
|
| 13 |
Mainline llama.cpp does not load `clover_moe`. This build adds the converter, the runtime graph and the `draft-self` speculative mode. The PR is not merged upstream; pin this repository for reproducibility.
|