tarioch/qwen2.5-coder-bql

tarioch/ qwen2.5-coder-bql

58 Downloads Updated 6 days ago

Turns questions about your Beancount ledger into BQL (beanquery) queries.

3b 7b

ollama run tarioch/qwen2.5-coder-bql

curl http://localhost:11434/api/chat \
  -d '{
    "model": "tarioch/qwen2.5-coder-bql",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='tarioch/qwen2.5-coder-bql',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'tarioch/qwen2.5-coder-bql',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Models

Name

3 models

Size / Usage

Context

Input

qwen2.5-coder-bql:latest

1.9GB · 32K context window · Text · 6 days ago

qwen2.5-coder-bql:latest

1.9GB

32K

Text

qwen2.5-coder-bql:3b

1.9GB · 32K context window · Text · 6 days ago

qwen2.5-coder-bql:3b latest

1.9GB

32K

Text

qwen2.5-coder-bql:7b

4.7GB · 32K context window · Text · 6 days ago

qwen2.5-coder-bql:7b

4.7GB

32K

Text

Readme

A fine-tune of Qwen2.5-Coder for the Beancount Query Language (BQL), the query language of beanquery used with Beancount v3. Ask a question about your ledger in plain English and get a BQL query back.

Which tag to use

:7b: more accurate, recommended if you have the resources for it.
:3b: smaller and faster, matches :7b closely on in-scope questions, but more likely to invent plausible-looking table or column names for questions outside BQL’s scope.
latest points to :3b.

Usage

ollama run tarioch/qwen2.5-coder-bql "How much did I spend on groceries in 2024?"

Send just the question. The model replies with a sql block holding the BQL query. No system prompt is needed and it works with any system prompt or none. The Modelfile sets temperature 0; clients that use Ollama’s OpenAI-compatible /v1 API should send temperature: 0 themselves.

Accounts, payees, tags and currencies you name are used exactly as written. Natural words are matched by keyword (“groceries” becomes account ~ 'Groceries'), and generic wording like “all expenses” by account root (account ~ '^Expenses').

Example questions:

What is the total spending on insurance?
Provide both the cost and the value of assets and liabilities.
Which expense accounts have a total above 500 CAD?
Show all transactions tagged trip-rome-2024.

Notes

Double-check the query before trusting the result. A wrong account regex or date range can return an empty or incomplete answer without an error.
State the currency when a query needs one, the model doesn’t know your ledger’s operating currency.

Updates

The tags above are updated in place when a new version of the model is trained. Run ollama pull tarioch/qwen2.5-coder-bql:7b (or :3b) to get the latest one. What changed in each version is listed in the GitHub releases.

More

Training data, methodology and license (GPL-2.0-only): github.com/tarioch/bql-lora

A fine-tune of Qwen2.5-Coder for the Beancount Query Language (BQL), the query language of [beanquery](https://github.com/beancount/beanquery) used with Beancount v3. Ask a question about your ledger in plain English and get a BQL query back.

## Which tag to use

- `:7b`: more accurate, recommended if you have the resources for it.
- `:3b`: smaller and faster, matches `:7b` closely on in-scope questions, but more likely to invent plausible-looking table or column names for questions outside BQL's scope.
- `latest` points to `:3b`.

## Usage

```
ollama run tarioch/qwen2.5-coder-bql "How much did I spend on groceries in 2024?"
```

Send just the question. The model replies with a `sql` block holding the BQL query. No system prompt is needed and it works with any system prompt or none. The Modelfile sets `temperature 0`; clients that use Ollama's OpenAI-compatible `/v1` API should send `temperature: 0` themselves.

Accounts, payees, tags and currencies you name are used exactly as written. Natural words are matched by keyword ("groceries" becomes `account ~ 'Groceries'`), and generic wording like "all expenses" by account root (`account ~ '^Expenses'`).

Example questions:

- What is the total spending on insurance?
- Provide both the cost and the value of assets and liabilities.
- Which expense accounts have a total above 500 CAD?
- Show all transactions tagged trip-rome-2024.

## Notes

- Double-check the query before trusting the result. A wrong account regex or date range can return an empty or incomplete answer without an error.
- State the currency when a query needs one, the model doesn't know your ledger's operating currency.

## Updates

The tags above are updated in place when a new version of the model is trained. Run `ollama pull tarioch/qwen2.5-coder-bql:7b` (or `:3b`) to get the latest one. What changed in each version is listed in the [GitHub releases](https://github.com/tarioch/bql-lora/releases).

## More

Training data, methodology and license (GPL-2.0-only): [github.com/tarioch/bql-lora](https://github.com/tarioch/bql-lora)

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