Initial GGML model commit
Browse files
README.md
CHANGED
@@ -42,7 +42,8 @@ GGML files are for CPU + GPU inference using [llama.cpp](https://github.com/gger
|
|
42 |
|
43 |
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Kimiko-13B-GPTQ)
|
44 |
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/Kimiko-13B-GGML)
|
45 |
-
* [
|
|
|
46 |
|
47 |
## Prompt template: Kimiko
|
48 |
|
|
|
42 |
|
43 |
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Kimiko-13B-GPTQ)
|
44 |
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/Kimiko-13B-GGML)
|
45 |
+
* [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/TheBloke/Kimiko-13B-fp16)
|
46 |
+
* [nRuaif's original LoRA adapter, which can be merged on to the base model.](https://huggingface.co/nRuaif/Kimiko_13B)
|
47 |
|
48 |
## Prompt template: Kimiko
|
49 |
|