Update README.md

README.md

@@ -20,6 +20,34 @@ pipeline_tag: text-generation
 
 # GPT-OSS-Code-Reasoning-20B-qx86-hi-mlx
 
+This is an experimental quant with mixed precision selective layers, rendered with group size 32
+
+Side effects of quanting with the qx86-hi formula
+```bash
+I needed Haskell code. 
+The q6 starts with Haskell, 10k token down the road writes Python, and finishes with React
+The q6-hi, encoded with group size 32, writes some haskell, and stops somewhere at 20k tokens
+The qx86-hi worked for 40k tokens, reasoning around the Haskell solution without skipping a beat
+```
+
+From the original model card:
+
+Overview
+```bash
+Base model: openai/gpt-oss-20b
+Objective: Supervised fine-tuning for competitive programming and algorithmic reasoning
+Dataset: nvidia/OpenCodeReasoning-2 (OCR-2), combining python and cpp splits. 
+Each sample reconstructs the upstream question and uses the dataset's r1_generation as the assistant response
+Context length: 4096 tokens
+Training method: LoRA SFT via TRL SFTTrainer
+```
+
+Intended Use
+```bash
+Intended: Generating Python/C++ solutions and reasoning for competitive programming tasks
+Out of scope: Safety-critical applications. May hallucinate or produce incorrect/inefficient code
+```
+
 This model [GPT-OSS-Code-Reasoning-20B-qx86-hi-mlx](https://huggingface.co/GPT-OSS-Code-Reasoning-20B-qx86-hi-mlx) was
 converted to MLX format from [GetSoloTech/GPT-OSS-Code-Reasoning-20B](https://huggingface.co/GetSoloTech/GPT-OSS-Code-Reasoning-20B)
 using mlx-lm version **0.26.4**.