Quant-Cartel
/

Llama-3-8B-Instruct-DADA-exl2-rpcal

Model card Files Files and versions Community

rAIfle commited on Apr 26

Commit

a06ae9e

•

1 Parent(s): 18bc52e

Update README.md

Files changed (1) hide show

README.md +2 -0

README.md CHANGED Viewed

@@ -26,6 +26,8 @@ Quantized using 200 samples of 8192 tokens from an RP-oriented [PIPPA](https://h
 Branches:
 - `main` -- `measurement.json`
 - `8b8h` -- 8bpw, 8bit lm_head
 Original model link: [Envoid/Llama-3-8B-Instruct-DADA](https://huggingface.co/Envoid/Llama-3-8B-Instruct-DADA)

 Branches:
 - `main` -- `measurement.json`
 - `8b8h` -- 8bpw, 8bit lm_head
+- `6b6h` -- 6bpw, 6bit lm_head
+- `4b6h` -- 4bpw, 6bit lm_head
 Original model link: [Envoid/Llama-3-8B-Instruct-DADA](https://huggingface.co/Envoid/Llama-3-8B-Instruct-DADA)