diff --git a/air_llm/README.md b/air_llm/README.md index 1031d01..481c03f 100644 --- a/air_llm/README.md +++ b/air_llm/README.md @@ -1,4 +1,4 @@ -AirLLM optimizes inference memory usage, allowing 70B large language models to run inference on a single 4GB GPU card. No quantization, distillation, pruning or other model compression techniques that would result in degraded model performance are needed. +![airllm_logo](https://github.com/lyogavin/Anima/blob/main/assets/airllm_logo_sm.png?v=2&raw=true)AirLLM optimizes inference memory usage, allowing 70B large language models to run inference on a single 4GB GPU card. No quantization, distillation, pruning or other model compression techniques that would result in degraded model performance are needed. AirLLM优化inference内存，4GB单卡GPU可以运行70B大语言模型推理。不需要任何损失模型性能的量化和蒸馏，剪枝等模型压缩。 diff --git a/assets/airllm_logo.png b/assets/airllm_logo.png new file mode 100644 index 0000000..5693eba Binary files /dev/null and b/assets/airllm_logo.png differ diff --git a/assets/airllm_logo_sm.png b/assets/airllm_logo_sm.png new file mode 100644 index 0000000..c93cead Binary files /dev/null and b/assets/airllm_logo_sm.png differ