Reinforcement Learning
English
openenv
grpo
unsloth
qwen2.5
indian-wedding
wedding-planning
curriculum-learning
long-horizon-planning
Instructions to use shivanandh033/wedding-planner-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Local Apps
- Unsloth Studio new
How to use shivanandh033/wedding-planner-7b with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for shivanandh033/wedding-planner-7b to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for shivanandh033/wedding-planner-7b to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for shivanandh033/wedding-planner-7b to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="shivanandh033/wedding-planner-7b", max_seq_length=2048, )
| import json | |
| import matplotlib.pyplot as plt | |
| from pathlib import Path | |
| state_path = "/teamspace/studios/this_studio/wedding-model/checkpoint-300/trainer_state.json" | |
| with open(state_path) as f: | |
| state = json.load(f) | |
| history = state.get("log_history", []) | |
| steps = [] | |
| rewards = [] | |
| for entry in history: | |
| if "reward" in entry and "step" in entry: | |
| steps.append(entry["step"]) | |
| rewards.append(entry["reward"]) | |
| plt.figure(figsize=(10,4)) | |
| plt.plot(steps, rewards, marker='o', color='b') | |
| plt.xlabel("Training step") | |
| plt.ylabel("Episode reward") | |
| plt.title("Wedding Planner Agent — reward over training") | |
| plt.grid(True) | |
| out_dir = Path("/teamspace/studios/this_studio/wedding-planner-env/assets") | |
| out_dir.mkdir(exist_ok=True) | |
| out_path = out_dir / "reward_curve.png" | |
| plt.savefig(out_path, dpi=150) | |
| print(f"Plot saved to {out_path}") | |