Create README.md

README.md

@@ -0,0 +1,78 @@
+---
+license: apache-2.0
+language:
+- en
+base_model:
+- Qwen/Qwen2.5-Coder-32B
+- open-r1/OlympicCoder-32B
+pipeline_tag: text-generation
+tags:
+- merge
+- programming
+- code generation
+- code
+- qwen2
+- codeqwen
+- chat
+- qwen
+- qwen-coder
+library_name: transformers
+---
+
+<h2>Qwen2.5-Godzilla-Coder-51B-gguf</h2>
+
+<img src="godzilla-coder.jpg" style="float:right; width:300px; height:500px; padding:10px;">
+
+"It will pound your programming problems into the pavement... perfectly."
+
+Tipping the scales at 101 layers and 1215 tensors... the monster lives.
+
+Two monsters in fact.
+
+Each model generates stronger, more compact code with an enhanced understanding of your instructions and follows what you tell them to the letter.
+
+And then some.
+
+These overpowered CODING ENGINEs are based on two of the best coder AIs:
+
+"Qwen2.5-Coder-32B-Instruct" 
+
+[ https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct ]
+
+and
+
+"OlympicCoder-32B"
+
+[ https://huggingface.co/open-r1/OlympicCoder-32B ]
+
+These two models are stuffed into one MASSSIVE 51B merge that is stronger in performance and understanding than both donor models.
+
+CONFIGS:
+- #1 -> Qwen2.5-Coder-32B-Instruct primary/start, with OlympicCoder-32B as "finalizer". 
+- #2 -> OlympicCoder-32B as primary/start, with Qwen2.5-Coder-32B-Instruct as "finalizer".
+
+NOTES: 
+- Each config/version will be very different from each other.
+- Tool Calling is supported in both versions.
+- Source(s) / full quanting to follow // full repos to follow.
+- Model is fully operational at Q2k - both versions - and stronger than the base donor models in terms of raw performance.
+- Final model size (including layers/tensors) / config subject to change.
+
+---
+
+Config / Settings
+
+---
+
+Model is set at 32k/32768 context for these GGUFS, full quants/full repos will be 128k/131072.
+
+Requirements [Qwen 2.5 32B Coder default settings]:
+- Temp .5 to .7 (or lower)
+- topk: 20, topp: .8, minp: .05
+- rep pen: 1.1 (can be lower)
+- Jinja Template (embedded) or CHATML template.
+- A System Prompt is not required. (ran tests with blank system prompt)
+
+Refer to either "Qwen2.5-Coder-32B-Instruct" and/or "OlympicCoder-32B" repos (above) for additional settings, benchmarks and usage.
+
+---