Downloads · 30 days
10
23% of all-time downloads
marctheshark/meditation-planner-qwen2.5-3b-lora
meditation-planner-qwen2.5-3b-lora is a text generation model from marctheshark. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as apache-2.0.
A LoRA fine-tune of Qwen/Qwen2.5-3B-Instruct that generates structured meditation and pranayama session plans in JSON. Given a user request (goal, duration, experience level, modality), the model outputs a complete, s…
Downloads · 30 days
10
23% of all-time downloads
All-time downloads
44
Public
Repo size
131 MB
Likes
0
Public
Click a slice to open those files.
.safetensors120 MB · 88%
From the Hugging Face model README
A LoRA fine-tune of Qwen/Qwen2.5-3B-Instruct that generates structured meditation and pranayama session plans in JSON. Given a user request (goal, duration, experience level, modality), the model outputs a complete, stage-by-stage session plan with breath patterns, pacing notes, and safety considerations.
Part of the OpenClaw project.
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer
base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-3B-Instruct", device_map="auto")
model = PeftModel.from_pretrained(base, "marctheshark/meditation-planner-qwen2.5-3b-lora")
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-3B-Instruct")
prompt = """Generate a meditation session plan as JSON.
Request:
- Goal: calm
- Duration: 10 minutes
- Experience level: beginner
- Modality: breath_awareness
- Tone: warm
- Intensity: gentle
Output JSON:"""
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=1024, temperature=0.7)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
| Parameter | Value |
|---|---|
| Base model | Qwen/Qwen2.5-3B-Instruct |
| Method | SFT + QLoRA (4-bit) |
| LoRA rank | 16 |
| LoRA alpha | 32 |
| LoRA dropout | 0.05 |
| Target modules | q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj |
| Learning rate | 2e-4 |
| Epochs | 3 |
| Batch size | 2 (x4 gradient accumulation) |
| Max sequence length | 2048 |
| Training examples | 72 (stage 1 curated set) |
The model outputs structured JSON session plans with these fields:
title, intention — session framingduration_minutes, goal, modality, experience_level, tone, intensity — echo of request parameterssetup — posture, props, environment notessafety_notes — relevant cautions (empty if none needed)stages[] — ordered session stages, each with name, minutes, purpose, instructions, breath_pattern, pacing_notesclosing_message — transition guidanceSee the dataset repo for the full schema spec and example outputs.
Evaluated using a 16-dimension rubric covering:
The model is trained with safety boundaries enforced in the data:
The structured JSON output is designed to feed a text-to-speech pipeline that renders guided audio meditation sessions. The breath_pattern and pacing_notes fields provide the timing information needed for realistic audio pacing.