Sinensis
/

Psyonic-Cetacean-Ultra-Quality-20b-4.0bpw-h6-exl2

Text Generation

Not-For-All-Audiences

text-generation-inference

4-bit precision

Model card Files Files and versions

Sinensis commited on Jun 1, 2024

Commit

b30b68d

·

verified ·

1 Parent(s): c3c6759

Update README.md

Files changed (1) hide show

README.md +3 -4

README.md CHANGED Viewed

@@ -1,4 +1,3 @@
 ---
 source_model: DavidAU/Psyonic-Cetacean-full-precision
 original_merge: jebcarter/psyonic-cetacean-20B
@@ -11,9 +10,9 @@ quantized_by: Absurd
 ---
-<h3> static exl2 quants of https://huggingface.co/DavidAU/Psyonic-Cetacean-full-precision </h3>
-<h2> original merge https://huggingface.co/jebcarter/psyonic-cetacean-20B </h2>
-Used original model's tokenizer to fix a small issue with DavidAU's f32 repo.

 ---
 source_model: DavidAU/Psyonic-Cetacean-full-precision
 original_merge: jebcarter/psyonic-cetacean-20B
 ---
+<h3> 4bpw h6 exl2 quant of https://huggingface.co/DavidAU/Psyonic-Cetacean-full-precision </h3>
+Original merge model: https://huggingface.co/jebcarter/psyonic-cetacean-20B
+Used the original model tokenizer to fix an issue with DavidAU's f32 remake.