Update README.md

Updated to really explain what this is, what I was trying to do, and where I failed.

README.md

@@ -13,31 +13,98 @@ tags:
 - qwen3moe
 - quantized
 - code
+- frontend
+- react
+- fine-tuned
 ---
 
-# qwen3-coder-30b-a3b-codemonkey-GGUF
+# Qwen3-CodeMonkey v1
 
-GGUF exports of the `qwen3-coder-30b-a3b-codemonkey` fine-tune.
+A fine-tuned version of [qwen3-coder-30b-a3b](https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct), optimized for frontend development patterns and DHH-inspired simplicity.
 
-These files were produced by merging the LoRA adapter into the base weights,
-exporting a BF16 GGUF, and quantizing from that BF16 source.
+**TL;DR:** I made Qwen ***faster* but dumber**. Q4_K_M hits 137 tps (63% faster gen than base) but drops 10 accuracy points. Your mileage may vary.
 
-## Files
+## 🎯 Motivation
 
-- `qwen3-coder-30b-a3b-codemonkey.Q4_K_M.gguf`: recommended release artifact
-- `qwen3-coder-30b-a3b-codemonkey.Q8_0.gguf`: larger reference GGUF
-- `qwen3-coder-30b-a3b-codemonkey.BF16.gguf`: optional full-size BF16 GGUF source
+I wanted a model that *thinks* like I do about frontend code:
+- **Simplicity over cleverness** — boring tech that works beats clever abstractions
+- **Convention over configuration** — follow patterns, don't invent new ones
+- **DHH/Ryan Florence-inspired** — majestic monolith vibes for the frontend stack
 
-## Use with llama.cpp
+I work heavily in React/Preact + TanStack Query + Tailwind, and needed a model that could:
+- Write clean, maintainable component code
+- Avoid TypeScript ceremony and over-abstraction
+- Default to proven patterns (no "clever" state management hacks)
+- Generate code that a junior dev can understand 6 months later
+
+## 📊 The Numbers (Honest Edition)
+
+Benchmarked with [scaffold-bench](https://github.com/1337hero/scaffold-bench) 
+My own eval suite that tests real agentic coding work, not trivia or math puzzles. It throws 23 scenarios at the model (surgical edits, audits, scope discipline, verify-and-repair, implementation tasks) with actual tool use and real codebases.
+
+**Results (mean of 2 runs, 50-task subset):**
+
+| Model | Score | Gen TPS | Prompt TPS | Notes |
+|-------|-------|---------|------------|-------|
+| **qwen3-code-monkey (Q4_K_M)** | **66.0%** (33/50) | **137.3** | **1219** | Fastest, but -10pts accuracy |
+| qwen3-coder-next (base) | 76.0% (38/50) | 84.4 | 953 | Baseline |
+| qwen3-code-monkey-q8 | 33.0% (16.5/50) | 109.6 | 1444 | One run collapsed early — needs investigation |
+
+**Translation:** Q4 is **63% faster at generation** but lost 10 accuracy points. If you're latency bound and can tolerate the trade-off, this might be your jam. If you need max accuracy, stick with base.
+
+**What scaffold-bench tests:** 
+- **No LLM judge** - deterministic code-driven checks only
+- **Real tool use** - read, ls, grep, glob, edit, write, bash
+- **Real scenarios** - surgical edits, audits, scope discipline, implementation tasks against actual codebases
+- Categories include: surgical edit, audit, scope discipline, read only analysis, verify and repair, implementation, responsiveness, long context
+
+**Sample categories where code-monkey struggled vs base:**
+- **verify-and-repair** - iterating through failing tests to green
+- **implementation** - multi-file spec-to-code against existing stacks (wanted to rewrite everything my way instead of following the existing patterns)
+- **scope-discipline** - "make this one change and nothing else" (my training data emphasized refactoring, which backfired)
+
+**Q8 caveat:** One of the Q8 runs cratered to 8/50 after 64 requests - might be a harness issue, overfit collapse under tighter quantization, or early model failure. Take those numbers with salt until I re-run it.
+
+**Full benchmark details:** Check out [scaffold-bench](https://github.com/1337hero/scaffold-bench) if you want to run your own evals. All results/*.json files from my runs are in the codemonkey repo.
+
+🛠️  Training Process (And Where I Screwed Up)
+
+  - Dataset: ~20,000 Q&A pairs pulled from my frontend philosophy docs (DHH's "majestic monolith"
+  stuff + Ryan Florence's React patterns)
+  - Fine-tuning: LoRA adapter via Unsloth on Qwen3-Coder-30B-A3B-Instruct
+  - What I did wrong: Built the whole dataset as plain [question] → [answer] pairs. No reasoning
+  shown, no "wait, should I even do this?" step in the middle. Turns out the model learned the shape
+  of my answers without learning how I got there.
+  - How it showed up: v1 benched at 32–34/50 vs the base model's 37–40/50. Worse than what I started
+  with. The failures were the giveaway — it would edit files when I asked read-only questions, jump
+  straight to edits without reading anything first, skip searching before acting. Not a knowledge
+  problem. A "doesn't stop to think" problem.
+  - The speed trap that fooled me: 138 tok/s vs base 84 tok/s looked like a win at first. It wasn't.
+  It was faster because it was thinking less. Trinity-mini sits at the end of that road - blazing
+  fast, fails everything, useless.
+  - What I'm doing for v2: Q&A alone teaches outputs, not process. Need explicit <think>...</think>
+  traces in the dataset - short, 2–4 sentences, enough to encode the taboos ("read-only means
+  read-only", "search before you edit", "don't re-add a feature that already exists"). Response-only
+  supervision. Less distilled CoT cosplay, more structural alignment.
+
+**Lessons learned:**
+1. Unsloth works great once you get past the docs
+2. 20k rows might've been overkill for the domain specificity I wanted
+3. Need to balance domain adaptation with general capability retention
+4. Benchmarking early would've saved me a re-train (and $47)
+
+## 📦 Files
+
+- `qwen3-coder-30b-a3b-codemonkey.Q4_K_M.gguf` — **recommended** release artifact (fastest)
+- `qwen3-coder-30b-a3b-codemonkey.Q8_0.gguf` — larger reference GGUF (see caveat above)
+- `qwen3-coder-30b-a3b-codemonkey.BF16.gguf` — optional full-size BF16 source
+
+All quantized from the merged BF16 GGUF (not requantized from Q8).
+
+## 🚀 Usage with llama.cpp
 
 ```bash
 llama-cli \
   --model qwen3-coder-30b-a3b-codemonkey.Q4_K_M.gguf \
   --jinja \
-  -p "Write a Python script that tails a log file and highlights errors."
-```
-
-## Notes
-
-- The `Q4_K_M` file in this repo was quantized from the merged BF16 GGUF, not requantized from Q8.
-- If you want the adapter-only release, use the companion adapter repo: `1337Hero/qwen3-coder-30b-a3b-codemonkey`
+  -p "Write a React component that fetches user data with TanStack Query and displays it in a card."