Hugging Face's logo

TheBloke
/
Wizard-Vicuna-30B-Superhot-8K-GPTQ

Text Generation
Transformers
Safetensors
English
llama
uncensored
custom_code
text-generation-inference
4-bit precision
gptq
Model card Files Community
1
TheBloke commited on
Commit
3913cce
•
1 Parent(s): 0ef6ee6

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -48,7 +48,7 @@ GGML versions are not yet provided, as there is not yet support for SuperHOT in
48
  ## Repositories available
49
 
50
  * [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/Wizard-Vicuna-30B-Superhot-8K-GPTQ)
51
- * [Unquantised SuperHOT fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/TheBloke/Wizard-Vicuna-30B-Superhot-8K-GPTQ)
52
  * [Eric's base unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/ehartford/Wizard-Vicuna-30B-Uncensored)
53
 
54
  ## How to easily download and use this model in text-generation-webui with ExLlama
 
48
  ## Repositories available
49
 
50
  * [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/Wizard-Vicuna-30B-Superhot-8K-GPTQ)
51
+ * [Unquantised SuperHOT fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/TheBloke/Wizard-Vicuna-30B-Superhot-8K-fp16)
52
  * [Eric's base unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/ehartford/Wizard-Vicuna-30B-Uncensored)
53
 
54
  ## How to easily download and use this model in text-generation-webui with ExLlama