rungalileo
/

Llama-3.1-8B-QServe-g128

Model card Files Files and versions Community

rungalileo commited on Jan 3

Commit

10d5f66

·

verified ·

1 Parent(s): 88c454f

Update README.md

Files changed (1) hide show

README.md +2 -1

README.md CHANGED Viewed

@@ -15,5 +15,6 @@ rm -rf runs ~/Meta-Llama-3.1-8B-Instruct-QServe-g128
 python -m deepcompressor.app.llm.ptq configs/qoq-g128.yaml --model-name llama-3.1-8b-instruct --model-path ~/Meta-Llama-3.1-8B-Instruct --save-model ~/Meta-Llama-3.1-8B-Instruct-QServe-g128
 cd ~/Meta-Llama-3.1-8B-Instruct-QServe-g128/
-huggingface-cli upload rungalileo/Llama-3.1-8B-QServe-g128 . --commit-message "update"
 ```

 python -m deepcompressor.app.llm.ptq configs/qoq-g128.yaml --model-name llama-3.1-8b-instruct --model-path ~/Meta-Llama-3.1-8B-Instruct --save-model ~/Meta-Llama-3.1-8B-Instruct-QServe-g128
 cd ~/Meta-Llama-3.1-8B-Instruct-QServe-g128/
+huggingface-cli upload rungalileo/Llama-3.1-8B-QServe-g128 model.pt --commit-message "Update model.pt"
+huggingface-cli upload rungalileo/Llama-3.1-8B-QServe-g128 scale.pt --commit-message "Update scale.pt"
 ```