OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models
Paper • 2308.13137 • Published • 19
3-bit OmniQuant quantized version of DeepSeek-R1-Distill-Llama-70B-abliterated for inference with the Private LLM app.
- Downloads last month
- -
Model tree for numen-tech/DeepSeek-R1-Distill-Llama-70B-abliterated-w3a16g40sym
Base model
deepseek-ai/DeepSeek-R1-Distill-Llama-70B