From 033f6ee5399a1e24e5585d894557d28821cd08a7 Mon Sep 17 00:00:00 2001 From: Emmanuel <91394589+lainey1570@users.noreply.github.com> Date: Tue, 13 Aug 2024 00:32:30 -0700 Subject: [PATCH] Update onnxruntime/python/tools/transformers/models/llama/llama_torch.py committed suggestion Co-authored-by: kunal-vaishnavi <115581922+kunal-vaishnavi@users.noreply.github.com> --- .../python/tools/transformers/models/llama/llama_torch.py | 1 - 1 file changed, 1 deletion(-) diff --git a/onnxruntime/python/tools/transformers/models/llama/llama_torch.py b/onnxruntime/python/tools/transformers/models/llama/llama_torch.py index 6fcf0a517258d..643b21ce61343 100644 --- a/onnxruntime/python/tools/transformers/models/llama/llama_torch.py +++ b/onnxruntime/python/tools/transformers/models/llama/llama_torch.py @@ -29,7 +29,6 @@ def setup_torch_model(args, location, auth, torch_dtype=torch.float32, device=No ) l_config.use_cache = True l_config._attn_implementation = "eager" # "eager" uses LlamaAttention for attention layer - # l_config.num_hidden_layers = 1 llama = AutoModelForCausalLM.from_pretrained( location, use_auth_token=auth,