Downloads · 30 days
161
25% of all-time downloads
auswm85/flowbee-cut
flowbee-cut is a text generation model from auswm85. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.
Fine-tune of Qwen3-4B-Instruct-2507 that cleans raw speech-to-text transcripts for Flowbee, a local-first macOS dictation utility. It removes fillers and stutters, resolves self-corrections, and writes technical speec…
Downloads · 30 days
161
25% of all-time downloads
All-time downloads
633
Public
Repo size
22.5 GB
Likes
0
Public
Click a slice to open those files.
.gguf22.5 GB · 100%
From the Hugging Face model README
Fine-tune of Qwen3-4B-Instruct-2507 that cleans raw speech-to-text transcripts for Flowbee, a local-first macOS dictation utility. It removes fillers and stutters, resolves self-corrections, and writes technical speech in its correct form:
| spoken | written |
|---|---|
| "rename it to camel case get user data" | Rename it to getUserData. |
| "run cargo test dash dash release" | Run cargo test --release. |
| "open main dot rs" | Open main.rs. |
| "we deploy behind engine x" | We deploy behind nginx. |
This is not a chat model. It was trained to do exactly one thing under one system prompt, and it will clean — never answer — instruction-shaped transcripts ("write a unit test for the auth module" comes back as cleaned text, not a unit test).
The model expects the exact Flowbee Cut system prompt it was trained with
(the coder prompt in scripts/cut-eval/prompts.mjs of the Flowbee repo),
with the raw transcript as the sole user message, temperature 0. Behavior
under other prompts is untested. Serve with llama.cpp:
llama-server -m flowbee-cut-<version>.Q4_K_M.gguf -ngl 99 -c 4096
flowbee-cut-<version>.Q4_K_M.gguf — versioned releases (~2.5 GB).latest.json — machine-read manifest (version, file, sha256, eval score).
The Flowbee app checks it on startup and downloads new releases, verifying
the sha256 before the file touches a GGUF parser. Do not rename or delete
these files by hand.Apache-2.0