From e19dee7474350a421e1a54062eee8d6d80968aac Mon Sep 17 00:00:00 2001 From: Daniel Han Date: Wed, 25 Sep 2024 17:55:42 -0700 Subject: [PATCH] Update llama.py --- unsloth/models/llama.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/unsloth/models/llama.py b/unsloth/models/llama.py index 07bb5505ef..c187449902 100644 --- a/unsloth/models/llama.py +++ b/unsloth/models/llama.py @@ -1388,7 +1388,7 @@ def _wrap_fast_inference(generate, device_type, dtype, model): pass # For newer HF - kwargs["cache_implementation"] = "dynamic" + # kwargs["cache_implementation"] = "dynamic" # For num_logits_to_keep kwargs["num_logits_to_keep"] = 1