winstxnhdw
/

Meta-Llama-3.1-8B-Instruct-AWQ

Model card Files Files and versions Community

winstxnhdw commited on Oct 17

Commit

75780d5

•

1 Parent(s): 2e92f37

Update README.md

Files changed (1) hide show

README.md +5 -6

README.md CHANGED Viewed

@@ -3,10 +3,9 @@
 The following command was used to produce this model.
 ```bash
-python quantize.py
-  --model_dir /Meta-Llama-3-8B-Instruct \
-  --output_dir /Meta-Llama-3-8B-Instruct-AWQ \
-  --dtype bfloat16 \
-  --qformat int4_awq \
-  --awq_block_size 64 \
 ```

 The following command was used to produce this model.
 ```bash
+python quantize.py --model_dir /Meta-Llama-3-8B-Instruct \
+                   --output_dir /Meta-Llama-3-8B-Instruct-AWQ \
+                   --dtype bfloat16 \
+                   --qformat int4_awq \
+                   --awq_block_size 64
 ```