AirLLM 2.8T LLM inference with single 4GB GPU
Python chinese-llmchinese-nlpfinetunegenerative-aiinstruct-gptinstruction-setllamallmloraopen-modelsopen-sourceopen-source-modelsqlora
update readme
Yu Li6eb999fbcd13
diff --git a/README.md b/README.mdindex 81199d4..997a21c 100644--- a/README.md+++ b/README.md@@ -21,6 +21,8 @@ This is the first open source 33B Chinese LLM, we also support DPO alignment tra[](https://static.aicompose.cn/static/wecom_barcode.png?t=1671918938)[](https://huggingface.co/lyogavin/Anima33B-merged)[](https://huggingface.co/lyogavin/Anima-7B-100K)+[](https://img.shields.io/discord/1175437549783760896)+</div>## π ζ΄ζ° Updatesdiff --git a/air_llm/setup.py b/air_llm/setup.pyindex 1730565..acb74dc 100644--- a/air_llm/setup.py+++ b/air_llm/setup.py@@ -5,7 +5,7 @@ with open("README.md", "r") as fh:setuptools.setup(name="airllm",- version="0.9.3",+ version="0.9.4",author="Gavin Li",author_email="[email protected]",description="AirLLM allows single 4GB GPU card to run 70B large language models without quantization, distillation or pruning.",