brunopio
/

Llama-3.2-1B-Instruct-nbits4-GS64-Axis1-HQQ

Model card Files Files and versions Community

brunopio commited on about 14 hours ago

Commit

771a690

•

1 Parent(s): 87f166d

Update README.md

Files changed (1) hide show

README.md +1 -0

README.md CHANGED Viewed

@@ -1,6 +1,7 @@
 ---
 base_model:
 - meta-llama/Llama-3.2-1B-Instruct
 ---
 This is a version of the Llama-3.2-1B-Instruct model quantized to 4-bit via Half-Quadratic Quantization (HQQ): https://mobiusml.github.io/hqq_blog/

 ---
 base_model:
 - meta-llama/Llama-3.2-1B-Instruct
+base_model_relation: quantized
 ---
 This is a version of the Llama-3.2-1B-Instruct model quantized to 4-bit via Half-Quadratic Quantization (HQQ): https://mobiusml.github.io/hqq_blog/