Upload README.md with huggingface_hub

README.md

@@ -9,29 +9,62 @@ tags:
 - code
 - compression
 - qwen
-- lora
+- expert-model
+- domain-specific
+- task-specialized
 pipeline_tag: text-generation
 base_model: Qwen/Qwen3-1.7B
 ---
 
-# distill-1.7B
+# distill-1.7B — Expert Language Model for CLI Output
 
-Built for **[distill](https://github.com/samuelfaj/distill)** — a CLI output compression and classification tool.
+**distill-1.7B** is a **domain-specific Expert Language Model** — not a general-purpose chatbot. It does exactly one thing: compress and classify raw terminal output into structured, actionable summaries.
 
-**distill-1.7B** takes raw terminal output and distills it down to a structured, concise summary.
+Built for the **[distill](https://github.com/samuelfaj/distill)** engine — an open-source CLI output compression tool.
 
-## Tasks (8 skills)
+## What is distill?
 
-| Task | Description | Format |
-|------|-------------|--------|
-| `pass_fail` | Decide PASS or FAIL with error message | `PASS\n...` or `FAIL Error: ...` |
-| `safe_review` | Safety classification | `SAFE ` / `UNSAFE ` / `REVIEW ` |
-| `terraform_plan` | Extract create/change/destroy counts | `{"create": N, "change": N, "destroy": N}` |
-| `json_extraction` | Extract JSON from log output | `[{...}, {...}]` |
-| `security_audit` | Severity and count of vulnerabilities | `[{"severity":"...","count":N}]` |
-| `test_result` | Test suite outcome | `PASS\n...` or `FAIL\n...` |
-| `typescript_check` | TypeScript compiler errors | `error TS2741: ...` |
-| `generic` | Free-form summary | Any format |
+[distill](https://github.com/samuelfaj/distill) is a tool that takes arbitrary command-line output and reduces it to only what matters. Instead of scrolling through 500 lines of `npm install` logs, you get:
+
+```
+PASS
+24 packages installed, 0 vulnerabilities
+```
+
+Instead of parsing a wall of Terraform plan output, you get:
+
+```json
+{"create": 3, "change": 12, "destroy": 0}
+```
+
+**distill-1.7B is the brain behind distill** — it's the model that understands CLI output and knows what's signal vs noise.
+
+## Why "Expert Language Model"?
+
+Unlike general-purpose LLMs (ChatGPT, Claude, etc.) that can talk about anything, distill-1.7B is:
+
+| Trait | General LLM | distill-1.7B |
+|-------|-------------|--------------|
+| **Scope** | Any topic | CLI output only |
+| **Size** | 70-400B params | 1.7B params |
+| **Training data** | Web crawl (trillions of tokens) | 100k synthetic CLI outputs |
+| **Strengths** | Conversation, reasoning, code | CLI compression, classification |
+| **Weaknesses** | — | Can't chat, can't code, can't reason |
+
+It's an **expert** in the same way a radiologist is an expert — highly skilled in one narrow domain, not trying to be a general practitioner.
+
+## 8 Specialized Tasks
+
+| Task | What it does | Example output |
+|------|-------------|----------------|
+| `pass_fail` | Did the command succeed or fail? | `PASS` / `FAIL Error: ...` |
+| `safe_review` | Is this Terraform plan safe? | `SAFE` / `UNSAFE` / `REVIEW` |
+| `terraform_plan` | Count resources created/changed/destroyed | `{"create":3,"change":12,"destroy":0}` |
+| `json_extraction` | Pull JSON from noisy logs | `[{"name":"app","version":"2.1.0"}]` |
+| `security_audit` | Count vulns by severity | `[{"severity":"high","count":2}]` |
+| `test_result` | Test suite pass/fail? | `PASS\n4 passed, 0 failed` |
+| `typescript_check` | Extract TS compiler errors | `error TS2741: Property 'x' is missing` |
+| `generic` | Free-form summary of any CLI output | `24 packages installed` |
 
 ## Performance
 
@@ -40,8 +73,20 @@ Built for **[distill](https://github.com/samuelfaj/distill)** — a CLI output c
 | Overall accuracy | **95%** |
 | Tasks at 100% | 6 of 8 |
 | Base model | Qwen3-1.7B |
-| Fine-tuning | LoRA rank 32, 4000 iterations |
+| Training | LoRA rank 32, 4000 iterations |
 | Dataset | 100k synthetic CLI outputs |
+| Training hardware | Apple M4 Max, 128 GB RAM |
+
+## Available Formats
+
+| Repo | Format | Size | Platform |
+|------|--------|------|----------|
+| **distill-1.7B-MLX** | MLX fp16 | 3.2 GB | macOS (Apple Silicon) |
+| [distill-1.7B-4bit-MLX](https://huggingface.co/samuelfaj/distill-1.7B-4bit-MLX) | MLX 4-bit | 1.0 GB | macOS (Apple Silicon) |
+| [distill-1.7B-GGUF](https://huggingface.co/samuelfaj/distill-1.7B-GGUF) | GGUF fp16 | 4.1 GB | Cross-platform |
+| [distill-1.7B-4bit-GGUF](https://huggingface.co/samuelfaj/distill-1.7B-4bit-GGUF) | GGUF Q4_K_M | 1.2 GB | Cross-platform |
+
+All formats achieve **identical 95% accuracy** — pick based on your platform and size preference.
 
 ## Usage
 
@@ -59,16 +104,8 @@ result = generate(model, tokenizer, prompt=prompt, max_tokens=256)
 print(result)
 ```
 
-## Variants
-
-| Repo | Format | Size | Platform |
-|------|--------|------|----------|
-| [distill-1.7B-MLX](https://huggingface.co/samuelfaj/distill-1.7B-MLX) | MLX fp16 | 3.2 GB | macOS (Apple Silicon) |
-| [distill-1.7B-GGUF](https://huggingface.co/samuelfaj/distill-1.7B-GGUF) | GGUF | 4.1 GB | Windows / Linux / macOS |
-| distill-1.7B-2bit-MLX | MLX 2-bit | ~500 MB | macOS (Apple Silicon) — *coming soon* |
-
 ## Project
 
-This model is part of the **[distill](https://github.com/samuelfaj/distill)** project — a CLI output compression engine.
+This model powers [distill](https://github.com/samuelfaj/distill) — a CLI output compression engine. The training code and dataset generation pipeline are available in the repository.
 
-Training code at [github.com/samuelfaj/distill](https://github.com/samuelfaj/distill).
+[Full Distill Collection](https://huggingface.co/collections/samuelfaj/distill-6a0606f9b131c289025659fc)