From 6f66a8f41b29d8a521275beb1f6790b6ba33c2cc Mon Sep 17 00:00:00 2001 From: leopck Date: Fri, 13 Dec 2024 15:29:43 +0200 Subject: [PATCH 1/3] Fix for runnning falcon model --- examples/text-generation/run_generation.py | 1 + 1 file changed, 1 insertion(+) diff --git a/examples/text-generation/run_generation.py b/examples/text-generation/run_generation.py index 4b2ab96842..dfb423ea98 100755 --- a/examples/text-generation/run_generation.py +++ b/examples/text-generation/run_generation.py @@ -463,6 +463,7 @@ def generate(size=None, reduce_recompile=False): padding="max_length", max_length=args.max_input_tokens, truncation=True, + return_token_type_ids=False, ) def compute_valid_sequence_lengths_tensor(input_tokens): From 3164d97655fc8dd8ae9da8e52601841a9718f2bf Mon Sep 17 00:00:00 2001 From: Alexey Fadeev Date: Mon, 16 Dec 2024 13:25:06 +0000 Subject: [PATCH 2/3] Adjusting logic for other models --- examples/text-generation/run_generation.py | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/examples/text-generation/run_generation.py b/examples/text-generation/run_generation.py index dfb423ea98..87ecffbad8 100755 --- a/examples/text-generation/run_generation.py +++ b/examples/text-generation/run_generation.py @@ -457,13 +457,18 @@ def generate(size=None, reduce_recompile=False): encode_t0 = time.perf_counter() # Tokenization if args.max_input_tokens > 0: + if hasattr(model.config, "type_vocab_size") and model.config.type_vocab_size > 0: + return_token_type_ids = True + else: + return_token_type_ids = False + input_tokens = tokenizer.batch_encode_plus( input_sentences, return_tensors="pt", padding="max_length", max_length=args.max_input_tokens, truncation=True, - return_token_type_ids=False, + return_token_type_ids=return_token_type_ids, ) def compute_valid_sequence_lengths_tensor(input_tokens): From 55802d139905c7acffadc08eb240c9f90d37e4fc Mon Sep 17 00:00:00 2001 From: regisss <15324346+regisss@users.noreply.github.com> Date: Wed, 18 Dec 2024 06:54:14 +0000 Subject: [PATCH 3/3] Make style --- examples/text-generation/run_generation.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/examples/text-generation/run_generation.py b/examples/text-generation/run_generation.py index 87ecffbad8..5355ceb1b6 100755 --- a/examples/text-generation/run_generation.py +++ b/examples/text-generation/run_generation.py @@ -461,7 +461,7 @@ def generate(size=None, reduce_recompile=False): return_token_type_ids = True else: return_token_type_ids = False - + input_tokens = tokenizer.batch_encode_plus( input_sentences, return_tensors="pt",