Downloads · 30 days
21
9% of all-time downloads
powerliftme/coach-qwen3-1.7b
coach-qwen3-1.7b is a text generation model from powerliftme. Use it when you need the model to write or continue text. It is set up for gguf. The card lists the license as apache-2.0.
On-device coach for free-form training questions in the PowerliftME app — effort (RPE/RIR), recovery and readiness, technique cues, basic training nutrition, and on-topic refusals.
Downloads · 30 days
21
9% of all-time downloads
All-time downloads
225
Public
Repo size
1.1 GB
Likes
0
Public
Click a slice to open those files.
.gguf1.1 GB · 100%
From the Hugging Face model README
On-device coach for free-form training questions in the PowerliftME app — effort (RPE/RIR), recovery and readiness, technique cues, basic training nutrition, and on-topic refusals.
Program-specific facts (today's prescribed load, peak timing, weeks to meet, on-track status, …) are answered by a deterministic rules engine inside the app, never by this model. The LLM handles the open-ended advice around it and replies in the athlete's own language.
llama-server -m coach-qwen3-1.7b-q4.gguf -c 2048 --reasoning-budget 0
Reply style: 1–3 plain sentences, no markdown. The model never invents plan numbers — anything program-specific comes from the app's engine.
Apache 2.0, inherited from Qwen3-1.7B. No usage restrictions.