AirLLM 2.8T LLM inference with single 4GB GPU
Python chinese-llmchinese-nlpfinetunegenerative-aiinstruct-gptinstruction-setllamallmloraopen-modelsopen-sourceopen-source-modelsqlora
update readme
Yu Li953490ed81e1
diff --git a/air_llm/README.md b/air_llm/README.mdindex b7c1749..e0c58f5 100644--- a/air_llm/README.md+++ b/air_llm/README.md@@ -92,9 +92,9 @@ We just added model compression based on block-wise quantization based model com* Step 3. when initialize the model, passing the argument compression ('4bit' or '8bit'):```python-model = AirLLMLlama2("garage-bAInd/Platypus2-70B-instruct"- compression='4bit' # specify '8bit' for 8-bit block-wise quantization- )+model = AirLLMLlama2("garage-bAInd/Platypus2-70B-instruct",+ compression='4bit' # specify '8bit' for 8-bit block-wise quantization+ )```### 4. All supported configurations