sakhan10
/

quantized_open_llama_3b_v2

Model card Files Files and versions Community

sakhan10 commited on Aug 27, 2024

Commit

e8d51ad

·

verified ·

1 Parent(s): 85315ee

Update README.md

Files changed (1) hide show

README.md +4 -1

README.md CHANGED Viewed

@@ -1,8 +1,11 @@
 ---
 metrics:
 - precision
 - accuracy
-base_model: openlm-research/open_llama_3b_v2
 ---
 # Model Card for Model ID

 ---
+#I have tried Quantizing an open source Open-Llama Float 32 model to INT8 and reduced the size. Now I want to check if there is any improvement in the average score.
+base_model: openlm-research/open_llama_3b_v2
 metrics:
 - precision
 - accuracy
+task:
+- Text-generation
 ---
 # Model Card for Model ID