Update README.md
Browse files
README.md
CHANGED
|
@@ -7,6 +7,8 @@ license: llama3.2
|
|
| 7 |
|
| 8 |
Ampere® optimized build of [llama.cpp](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#llamacpp) with full support for rich collection of GGUF models available at HuggingFace: [GGUF models](https://huggingface.co/models?search=gguf)
|
| 9 |
|
|
|
|
|
|
|
| 10 |
This Docker image can be run on bare metal Ampere® CPUs and Ampere® based VMs available in the cloud.
|
| 11 |
|
| 12 |
Release notes and binary executables are available on our [GitHub](https://github.com/AmpereComputingAI/llama.cpp/releases)
|
|
|
|
| 7 |
|
| 8 |
Ampere® optimized build of [llama.cpp](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#llamacpp) with full support for rich collection of GGUF models available at HuggingFace: [GGUF models](https://huggingface.co/models?search=gguf)
|
| 9 |
|
| 10 |
+
**For best results we recommend using models in our custom quantization formats available here: [AmpereComputing HF](https://huggingface.co/AmpereComputing)**
|
| 11 |
+
|
| 12 |
This Docker image can be run on bare metal Ampere® CPUs and Ampere® based VMs available in the cloud.
|
| 13 |
|
| 14 |
Release notes and binary executables are available on our [GitHub](https://github.com/AmpereComputingAI/llama.cpp/releases)
|