Update README.md

README.md

@@ -39,11 +39,34 @@ and
 
 In one MASSSIVE 52B merge.
 
-In two configs...
+In two configs... too.
 
-Quants Q4KS (two) uploading...
+CONFIGS:
+- #1 -> Qwen2.5-Coder-32B-Instruct primary/start, with OlympicCoder-32B as "finalizer".
+- #1 -> OlympicCoder-32B as primary/start, with Qwen2.5-Coder-32B-Instruct as "finalizer".
 
-Source / full quanting to follow.
+Quants Q4_K_S (two - one of each config) uploading...
 
-Model is fully operational at Q2k.
+Each config/version will be very different from each other.
 
+Source(s) / full quanting to follow.
+
+NOTE: Model is fully operational at Q2k.
+
+---
+
+Config / Settings
+
+---
+
+Model is set at 32k/32768 context for these GGUFS, full quants/full repos will be 128k/131072.
+
+Requirements:
+- Temp .5 to .7 (or lower)
+- topk: 20, topp: .8, minp: .04
+- rep pen: 1.1 (can be lower)
+- Jinja Template (embedded) or CHATML template.
+
+Refer to either "Qwen2.5-Coder-32B-Instruct" and/or "OlympicCoder-32B" for additional settings, benchmarks and usage.
+
+---