Svak commited on
Commit
fc949f7
·
verified ·
1 Parent(s): d4aca34

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +0 -7
README.md CHANGED
@@ -15,13 +15,6 @@ tags:
15
 
16
  An auto-regressive causal LM created by combining 2x finetuned [Llama-2 70B](https://huggingface.co/meta-llama/llama-2-70b-hf) into one.
17
 
18
- Please check out the quantized formats provided by [@TheBloke](https:///huggingface.co/TheBloke) and [@Panchovix](https://huggingface.co/Panchovix):
19
-
20
- - [GGUF](https://huggingface.co/TheBloke/goliath-120b-GGUF) (llama.cpp)
21
- - [GPTQ](https://huggingface.co/TheBloke/goliath-120b-GPTQ) (KoboldAI, TGW, Aphrodite)
22
- - [AWQ](https://huggingface.co/TheBloke/goliath-120b-AWQ) (TGW, Aphrodite, vLLM)
23
- - [Exllamav2](https://huggingface.co/Panchovix/goliath-120b-exl2) (TGW, KoboldAI)
24
-
25
  # Prompting Format
26
 
27
  Both Vicuna and Alpaca will work, but due the initial and final layers belonging primarily to Xwin, I expect Vicuna to work the best.
 
15
 
16
  An auto-regressive causal LM created by combining 2x finetuned [Llama-2 70B](https://huggingface.co/meta-llama/llama-2-70b-hf) into one.
17
 
 
 
 
 
 
 
 
18
  # Prompting Format
19
 
20
  Both Vicuna and Alpaca will work, but due the initial and final layers belonging primarily to Xwin, I expect Vicuna to work the best.