Update README.md
Browse files
README.md
CHANGED
@@ -34,9 +34,9 @@ To use the increased context with KoboldCpp, simply use `--contextsize` to set t
|
|
34 |
|
35 |
## Repositories available
|
36 |
|
37 |
-
* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/WizardLM-7B-V1-0-SuperHOT-8K-GPTQ)
|
38 |
-
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU inference](https://huggingface.co/TheBloke/WizardLM-7B-V1-0-SuperHOT-8K-GGML)
|
39 |
-
* [Unquantised SuperHOT fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/TheBloke/WizardLM-7B-V1-0-SuperHOT-8K-fp16)
|
40 |
* [Unquantised base fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/ehartford/WizardLM-7B-V1.0-Uncensored)
|
41 |
|
42 |
<!-- compatibility_ggml start -->
|
|
|
34 |
|
35 |
## Repositories available
|
36 |
|
37 |
+
* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/WizardLM-7B-V1-0-Uncensored-SuperHOT-8K-GPTQ)
|
38 |
+
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU inference](https://huggingface.co/TheBloke/WizardLM-7B-V1-0-Uncensored-SuperHOT-8K-GGML)
|
39 |
+
* [Unquantised SuperHOT fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/TheBloke/WizardLM-7B-V1-0-Uncensored-SuperHOT-8K-fp16)
|
40 |
* [Unquantised base fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/ehartford/WizardLM-7B-V1.0-Uncensored)
|
41 |
|
42 |
<!-- compatibility_ggml start -->
|