Update README.md
Browse files
README.md
CHANGED
@@ -31,7 +31,7 @@ GGML files are for CPU + GPU inference using [llama.cpp](https://github.com/gger
|
|
31 |
## Repositories available
|
32 |
|
33 |
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/llama-30B-GGML)
|
34 |
-
* [
|
35 |
|
36 |
<!-- compatibility_ggml start -->
|
37 |
## Compatibility
|
|
|
31 |
## Repositories available
|
32 |
|
33 |
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/llama-30B-GGML)
|
34 |
+
* [huggyllama's unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/huggyllama/llama-30b)
|
35 |
|
36 |
<!-- compatibility_ggml start -->
|
37 |
## Compatibility
|