policy

ALCHEMY

SandroHub013 · PyTorch

or hover any field below to flag it

Overview

Name
ALCHEMY
Author
SandroHub013
Framework
PyTorch
License
NOASSERTION
Skill type
other
Evidence level
untested
Task description
🧪 Advanced LLM fine-tuning framework with Reinforcement Learning (GRPO/DPO), Multi-Agent Swarm Training, Adaptive Optimization, and Unsloth integration (2x faster, 70% less VRAM). Train 1.5B-70B+ models on 8GB+ GPUs with QLoRA, PEFT, LUFFY off-policy reasoning, and Search-R1. RAG-enabled with smart

Spaces

Action space
other · 0-dim · 0Hz
Observation space
  • type: other

Links

HuggingFace repo
null
Paper (arXiv)
null

Compatible robots

3+17 mentioned but not in catalog yet

Compatible environments

0

No environments list ALCHEMY yet.

Datasets that reference this policy

0

No datasets reference ALCHEMY yet.