DavidAU
/

Reka-Flash-3-21B-Reasoning-Uncensored-MAX-NEO-Imatrix-GGUF

Text Generation

DeepSeek-R1-Distill

function calling

problem solving

fiction writing

plot generation

sub-plot generation

story generation

Model card Files Files and versions Community

DavidAU commited on 20 days ago

Commit

d591380

·

verified ·

1 Parent(s): 60e7503

Update README.md

Files changed (1) hide show

README.md +5 -0

README.md CHANGED Viewed

@@ -31,6 +31,11 @@ Re-optimizing quants, found a better mixture. Uploading shortly.
 Mixture is strong enough that lower quants can now solve/reasoning and come up with a solution whereas NON-optimized
 may not be able to solve or take a lot longer (a lot more tokens!).
 ---
 Reka's excellent reasoning model with MAXed quants, and NEO Imatrix dataset.

 Mixture is strong enough that lower quants can now solve/reasoning and come up with a solution whereas NON-optimized
 may not be able to solve or take a lot longer (a lot more tokens!).
+Quick testing shows optimized can:
+  - Answer/solve at lower quant.
+  - Come up with a better answer/stronger reasoning
+  - Use less tokens to "reason" ... up to 50% less.
 ---
 Reka's excellent reasoning model with MAXed quants, and NEO Imatrix dataset.