OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models
Paper
• 2308.13137 • Published
• 19
4-bit OmniQuant quantized version of DeepSeek-R1-Distill-Llama-8B-abliterated for inference with the Private LLM app.
- Downloads last month
- -
Model tree for numen-tech/DeepSeek-R1-Distill-Llama-8B-abliterated-w4a16g128asym
Base model
deepseek-ai/DeepSeek-R1-Distill-Llama-8B