Downloads · 30 days
7
4% of all-time downloads
YoozLabs/Yooz-Light-v2-Qwen2.5-0.5B-LoRA
Yooz-Light-v2-Qwen2.5-0.5B-LoRA is a text generation model from YoozLabs. Use it when you need the model to write or continue text. It is set up for mlx. The card lists the license as apache-2.0.
Special-purpose model. This checkpoint does exactly one job: cleaning up speech-to-text output under the fixed system prompts and JSON output contract documented below. It is not a general-purpose chat or instruction…
Downloads · 30 days
7
4% of all-time downloads
All-time downloads
181
Public
Parameters
494M
289 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors278 MB · 96%
How the weights are stored.
U32494M · 100%
From the Hugging Face model README
Special-purpose model. This checkpoint does exactly one job: cleaning up speech-to-text output under the fixed system prompts and JSON output contract documented below. It is not a general-purpose chat or instruction model; off-task use (open-ended chat, question answering) is unsupported and will underperform the base model. All Yooz task models are collected in Yooz Working Models; for general-purpose local LLMs see Lean QAT MLX.
Speech-to-text touchup model from Yooz Labs.
Takes raw STT output and returns a cleaned-up version, either lightly proofread
or more aggressively rewritten, as a single JSON object: {"result": "..."}.
This is the Light tier of the Yooz Engine touchup stack — the fast-path companion to Yooz-Quality-v2. It runs fully on-device on Apple Silicon via MLX, in the privacy-first Yooz tradition: no cloud, no logging, no leak.
{"result": "<cleaned text>"}. No explanation, no markdown.mlx-community/Qwen2.5-0.5B-Instruct-4bit (Apache 2.0).mlx-swift-lm consumers.Light is optimized for the fast, low-latency path — short utterances and mechanical fixes where the user wants surface cleanup without semantic rewriting. Use Quality for longer dictation where you want intent-preserving rewrites, self-correction handling, and tone preservation.
Pull via mlx-lm:
from mlx_lm import load, generate
model, tokenizer = load("YoozLabs/Yooz-Light-v2-Qwen2.5-0.5B-LoRA")
system_prompt = """Fix grammar, capitalize properly, and convert spoken numbers
to digits. Keep ALL sentences. Return the fixed text as JSON.
Always respond with ONLY a JSON object. Never remove sentences. Never include
explanations."""
raw = "the meeting is at two pm on march fifteenth"
response = generate(
model, tokenizer,
prompt=tokenizer.apply_chat_template(
[{"role": "system", "content": system_prompt},
{"role": "user", "content": raw}],
tokenize=False, add_generation_prompt=True,
),
max_tokens=256,
)
# {"result": "The meeting is at 2 PM on March 15th."}
Apache 2.0 (same as the base model).
YoozLabs/Yooz-Quality-v2-Qwen3.5-0.8B-LoRA — the Quality tier sibling.yooz-engine — runtime that consumes these checkpoints.