D0minuZ/jq-coder

D0minuZ/ jq-coder

Updated 3 hours ago

Translate natural language to jq filters, 100% offline. Trained on execution-verified data; also understands Brazilian Portuguese.

ollama run D0minuZ/jq-coder

curl http://localhost:11434/api/chat \
  -d '{
    "model": "D0minuZ/jq-coder",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='D0minuZ/jq-coder',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'D0minuZ/jq-coder',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Models

Name

1 model

Size / Usage

Context

Input

jq-coder:latest

639MB · 32K context window · Text · 3 hours ago

jq-coder:latest

639MB

32K

Text

Readme

Type what you want in plain English, get an executable jq filter — without your JSON ever leaving your machine. Built for the JSON you can’t send to a cloud API: production payloads, logs with PII, anything under NDA. Also understands Brazilian Portuguese.

Usage

The system prompt and temperature come preconfigured — just type your request followed by a small JSON sample (the model reads field names and shapes from it):

ollama run D0minuZ/jq-coder
>>> get the id of every order
... JSON sample: {"orders":[{"id":1,"status":"done"}]}
.orders[] | .id

More examples, all verified by executing the generated filter with real jq:

“get the id of every order” → .orders[] | .id
“keep only the orders whose status is done” → [.orders[] | select(.status == "done")]
“some o total de todos os pedidos” → [.orders[].total] | add
“remova o campo total de cada pedido” → del(.orders[].total)

Good to know

Always include a JSON sample — the model was trained to copy field names from it; without one it will hallucinate fields.
It outputs a jq filter, not a shell command: pipe it into jq yourself, or use the jqc CLI — a single binary that generates the filter and runs it for you.
Review destructive filters (del, assignments) before applying them to data you care about.

Links

0.6B full fine-tune of Qwen3-0.6B-Base · weights CC BY 4.0

Type what you want in plain English, get an executable jq filter — without your JSON ever leaving your machine. Built for the JSON you can't send to a cloud API: production payloads, logs with PII, anything under NDA. Also understands Brazilian Portuguese.

## Usage

The system prompt and temperature come preconfigured — just type your request followed by a small JSON sample (the model reads field names and shapes from it):

```
ollama run D0minuZ/jq-coder
>>> get the id of every order
... JSON sample: {"orders":[{"id":1,"status":"done"}]}
.orders[] | .id
```

More examples, all verified by executing the generated filter with real jq:

- "get the id of every order" → `.orders[] | .id`
- "keep only the orders whose status is done" → `[.orders[] | select(.status == "done")]`
- "some o total de todos os pedidos" → `[.orders[].total] | add`
- "remova o campo total de cada pedido" → `del(.orders[].total)`

## Good to know

- **Always include a JSON sample** — the model was trained to copy field names from it; without one it will hallucinate fields.
- It outputs a jq **filter**, not a shell command: pipe it into `jq` yourself, or use the [jqc CLI](https://github.com/EdelmarSchneider/jq-coder-cli) — a single binary that generates the filter and runs it for you.
- Review destructive filters (`del`, assignments) before applying them to data you care about.

## Links

- [Model card, GGUF files and full evaluation](https://huggingface.co/DominuZ/jq-coder-0.6B)
- [jq-bench — execution-verified benchmark](https://huggingface.co/datasets/DominuZ/jq-bench)
- [jqc CLI — prebuilt binaries for Windows, Linux and macOS](https://github.com/EdelmarSchneider/jq-coder-cli)

0.6B full fine-tune of Qwen3-0.6B-Base · weights CC BY 4.0

Paste, drop or click to upload images (.png, .jpeg, .jpg, .svg, .gif)