Spaces:

open-llm-leaderboard
/

open_llm_leaderboard

Running on CPU Upgrade

Clémentine commited on Aug 29, 2023

Commit

3994f5a

•

1 Parent(s): bbd101d

added gptq model submission

Files changed (1) hide show

app.py CHANGED Viewed

@@ -483,6 +483,7 @@ with demo:
                             "bfloat16",
                             "8bit (LLM.int8)",
                             "4bit (QLoRA / FP4)",
                         ],
                         label="Precision",
                         multiselect=False,

                             "bfloat16",
                             "8bit (LLM.int8)",
                             "4bit (QLoRA / FP4)",
+                            "GPTQ"
                         ],
                         label="Precision",
                         multiselect=False,