Update README.md
Browse files
README.md
CHANGED
|
@@ -34,7 +34,9 @@ Please read carefully below to see how to use it.
|
|
| 34 |
## Repositories available
|
| 35 |
|
| 36 |
* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/Guanaco-33B-SuperHOT-8K-GPTQ)
|
| 37 |
-
* [
|
|
|
|
|
|
|
| 38 |
|
| 39 |
## How to easily download and use this model in text-generation-webui
|
| 40 |
|
|
|
|
| 34 |
## Repositories available
|
| 35 |
|
| 36 |
* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/Guanaco-33B-SuperHOT-8K-GPTQ)
|
| 37 |
+
* [Panchovix's unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/Panchovix/Guanaco-33B-SuperHOT-8k)
|
| 38 |
+
|
| 39 |
+
GGML quants are not yet provided, as there is not yet support for SuperHOT in llama.cpp. This is being investigated and will hopefully come soon.
|
| 40 |
|
| 41 |
## How to easily download and use this model in text-generation-webui
|
| 42 |
|