orpo
Qwen2.5-Lumen-14B-i1-GGUF
- 8
- 843
- apache-2.0
- 2 y ago
Qwen2.5-Lumen-14B-GGUF
- 5
- 1.8k
- apache-2.0
- 2 y ago
agentic-post-training
Async agent pipeline for LLM post-training: PyTorch preference losses (DPO/ORPO/GRPO) + simulated runs
- 2
- Python
- 2 wk ago
Llama-3.1-8B-toxic-dpo-NoWarning-i1-GGUF
- 0
- 1.1k
- apache-2.0
- 2 y ago
Llama-3.1-8B-toxic-dpo-NoWarning-GGUF
- 0
- 399
- apache-2.0
- 2 y ago