Instructions to use enwrit/writ-lint-0.8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use enwrit/writ-lint-0.8B with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="enwrit/writ-lint-0.8B",
	filename="writ-lint-0.8B-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

llama-cpp-python

How to use enwrit/writ-lint-0.8B with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="enwrit/writ-lint-0.8B",
	filename="writ-lint-0.8B-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use enwrit/writ-lint-0.8B with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf enwrit/writ-lint-0.8B:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf enwrit/writ-lint-0.8B:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf enwrit/writ-lint-0.8B:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf enwrit/writ-lint-0.8B:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf enwrit/writ-lint-0.8B:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf enwrit/writ-lint-0.8B:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf enwrit/writ-lint-0.8B:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf enwrit/writ-lint-0.8B:Q4_K_M

Use Docker

docker model run hf.co/enwrit/writ-lint-0.8B:Q4_K_M

LM Studio
Jan

vLLM

How to use enwrit/writ-lint-0.8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "enwrit/writ-lint-0.8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "enwrit/writ-lint-0.8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/enwrit/writ-lint-0.8B:Q4_K_M

Ollama
How to use enwrit/writ-lint-0.8B with Ollama:
```
ollama run hf.co/enwrit/writ-lint-0.8B:Q4_K_M
```

Unsloth Studio new

How to use enwrit/writ-lint-0.8B with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for enwrit/writ-lint-0.8B to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for enwrit/writ-lint-0.8B to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for enwrit/writ-lint-0.8B to start chatting

Pi new

How to use enwrit/writ-lint-0.8B with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf enwrit/writ-lint-0.8B:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "enwrit/writ-lint-0.8B:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use enwrit/writ-lint-0.8B with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf enwrit/writ-lint-0.8B:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default enwrit/writ-lint-0.8B:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use enwrit/writ-lint-0.8B with Docker Model Runner:
```
docker model run hf.co/enwrit/writ-lint-0.8B:Q4_K_M
```

Lemonade

How to use enwrit/writ-lint-0.8B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull enwrit/writ-lint-0.8B:Q4_K_M

Run and chat with the model

lemonade run user.writ-lint-0.8B-Q4_K_M

List all available models

lemonade list

writ-lint-0.8B

A fine-tuned Qwen3.5-0.8B model that evaluates the quality of AI agent instructions and generates actionable improvement feedback.

Part of the Tier 2.5 hybrid architecture in enwrit -- the communication layer for AI agents.

How It Works

This model is one half of a hybrid scoring system:

LightGBM (bundled in the enwrit CLI) predicts headline + 6 dimension scores (~1ms)
writ-lint-0.8B (this model) generates issues (ERROR/WARNING/INFO) and improvement suggestions, using the instruction text and LightGBM-predicted scores as context

The model focuses entirely on generating actionable feedback, not scores. Scores from LightGBM are passed in the prompt so the model can target weak dimensions.

Usage

Via the enwrit CLI (recommended)

pip install enwrit
pip install llama-cpp-python  # CPU inference, ~10s per instruction

writ lint AGENTS.md --deep-local

The model is auto-downloaded to ~/.writ/models/ on first use.

Direct inference with llama-cpp-python

from llama_cpp import Llama
import json

model = Llama(
    model_path="writ-lint-0.8B-Q4_K_M.gguf",
    n_ctx=4096,
    n_gpu_layers=-1,  # GPU acceleration (0 for CPU-only)
    verbose=False,
)

prompt = """<|im_start|>system
You are an expert instruction quality evaluator. Given an instruction and its quality scores, generate specific issues and improvement suggestions.<|im_end|>
<|im_start|>user
## Instruction to evaluate

{instruction_text}

## Quality scores (predicted)

Headline: 52/100
Clarity: 58 | Structure: 65 | Coverage: 42 | Brevity: 71 | Examples: 28 | Verification: 35

Analyze the instruction. Return JSON with "issues" (level + message) and "suggestions".<|im_end|>
<|im_start|>assistant
"""

output = model.create_completion(
    prompt,
    max_tokens=1024,
    temperature=0.3,
    response_format={"type": "json_object"},
)

feedback = json.loads(output["choices"][0]["text"])
print(json.dumps(feedback, indent=2))

Output Format

{
  "issues": [
    {"level": "ERROR", "message": "Missing concrete code examples for error handling patterns."},
    {"level": "WARNING", "message": "Verification steps are subjective rather than binary."},
    {"level": "INFO", "message": "Consider adding a 'Rules' section for behavioral constraints."}
  ],
  "suggestions": [
    "Add a 'Code Examples' section with 'Good vs Bad' patterns for the most critical rules.",
    "Replace subjective verification with specific CLI commands (e.g., `pytest`, `ruff check`).",
    "Include numeric thresholds for measurable constraints (e.g., 'max 100 lines per function')."
  ]
}

Training Details

Parameter	Value
Base model	Qwen/Qwen3.5-0.8B
Method	LoRA (r=32, alpha=64, dropout=0) via Unsloth
Training data	6,536 Tier 3 AI evaluations (Gemini-scored instructions)
Issues in training data	30,830 (avg 4.7 per instruction)
Suggestions in training data	19,602 (avg 3.0 per instruction)
Non-coding examples	145 seed instructions across 15 domains
Epochs	1
Batch size	1 (gradient accumulation: 16, effective batch: 16)
Max sequence length	4096 tokens
Learning rate	2e-4 (cosine schedule, 10% warmup)
Precision	bf16
Quantization	Q4_K_M (GGUF)
Training hardware	NVIDIA RTX 5090 (32GB VRAM)
Training time	~5.5 hours

Evaluation

Compared against retrieval-based approaches (v1/v2/v3) on a held-out validation set:

Approach	Relevance	All-Feedback Specificity	Issues/Instruction	Type
v1_shap_knn	0.157	0.129	N/A	retrieval
v2_hybrid	0.266	0.136	N/A	retrieval
v3_tfidf	0.262	0.144	N/A	retrieval
writ-lint-0.8B	0.236	0.364	4.7	generative

Key strengths:

100% JSON parse success (via constrained decoding)
Generates novel, context-specific feedback (not limited to seen examples)
Weak-dimension targeting: 0.47 (issues correlate with low-scoring dimensions)
Low domain mismatch: 0.014 (doesn't give coding feedback to non-coding instructions)

Scoring Dimensions

The 6 quality dimensions (scored by LightGBM, targeted by this model):

Dimension	What it measures
Clarity	Unambiguous language, precise terminology, defined jargon
Structure	Logical sections, hierarchy, scannable formatting
Coverage	Completeness of rules, edge cases, responsibilities
Brevity	Concise without sacrificing meaning, no redundancy
Examples	Code samples, input/output patterns, good vs bad
Verification	Testable criteria, CLI commands, specific thresholds

Files

writ-lint-0.8B-Q4_K_M.gguf -- Quantized model for inference (504 MB)

License

MIT

Downloads last month: 3

GGUF

Model size

0.8B params

Architecture

qwen35

Hardware compatibility

4-bit

Model tree for enwrit/writ-lint-0.8B

Base model

Qwen/Qwen3.5-0.8B-Base

Finetuned

Qwen/Qwen3.5-0.8B

Quantized

(110)

this model

enwrit
/

writ-lint-0.8B