Drop unsloth: use standard bitsandbytes 4-bit + peft LoRA + TRL GRPOTrainer

Pin transformers <4.52 and unsloth_zoo==2025.11.1 for API compat

Pin TRL <0.16 for unsloth 2025.11.1 GRPO API compatibility

Add torchvision and hf_transfer

Fix: install torchao 0.8.0 separately, unsloth --no-deps to avoid torchao>=0.13 conflict

Pin compatible versions: torch 2.6.0 + torchao <0.9 + transformers <5.0

GRPO training with CUDA + results in UI

fix: transformers>=4.51.3 to resolve unsloth dep conflict

fix: add unsloth back with pinned versions to avoid dep backtracking

fix: lean Dockerfile + remove unsloth from training deps

Add GRPO training runner for HF Spaces GPU