update torch and tensorflow version (#979)

examples/huggingface/pytorch/image-classification/deployment/imagenet/vit/requirements.txt

@@ -4,7 +4,7 @@ accelerate
 datasets >= 1.8.0
 sentencepiece != 0.1.92
 protobuf
-torch==1.13.1
+torch==2.0.0
 torchvision
 onnx>=1.12
 onnxruntime==1.13.1

examples/huggingface/pytorch/image-classification/quantization/requirements.txt

@@ -3,7 +3,7 @@ accelerate
 datasets >= 1.8.0
 sentencepiece != 0.1.92
 protobuf
-torch==1.13.1
+torch==2.0.0
 torchvision
 onnx>=1.12
 onnxruntime==1.13.1

examples/huggingface/pytorch/language-modeling/deployment/fill-mask/electra_base_chinese/requirements.txt

@@ -1,2 +1,2 @@
 transformers==4.28.1
-torch==1.13.1
+torch==2.0.0

examples/huggingface/pytorch/language-modeling/distillation/requirements.txt

@@ -1,5 +1,5 @@
 datasets
 nltk
 torch>=1.10.0
-transformers>=4.12.0
+transformers<=4.29.1
 wandb

examples/huggingface/pytorch/language-modeling/nas/requirements.txt

@@ -1,5 +1,5 @@
 datasets
 nltk
 torch>=1.10.0
-transformers>=4.12.0
+transformers<=4.29.1
 wandb

examples/huggingface/pytorch/language-modeling/pruning/requirements.txt

@@ -1,5 +1,5 @@
 accelerate
 datasets
-transformers
+transformers<=4.29.1
 torch
 tqdm

examples/huggingface/pytorch/language-modeling/quantization/requirements.txt

@@ -3,7 +3,7 @@ protobuf
 sentencepiece != 0.1.92
 datasets >= 1.1.3
 torch >= 1.10
-transformers
+transformers<=4.29.1
 wandb
 git+https://github.com/intel/neural-compressor.git
 git+https://github.com/EleutherAI/lm-evaluation-harness.git@83dbfbf6070324f3e5872f63e49d49ff7ef4c9b3

examples/huggingface/pytorch/multiple-choice/quantization/requirements.txt

@@ -2,6 +2,6 @@ datasets >= 1.1.3
 sentencepiece != 0.1.92
 protobuf
 torch >= 1.10.0
-transformers
+transformers<=4.29.1
 wandb
 accelerate

examples/huggingface/pytorch/question-answering/deployment/squad/bert_large/requirements.txt

@@ -4,7 +4,7 @@ accelerate
 datasets >= 1.8.0
 sentencepiece != 0.1.92
 protobuf
-torch==1.13.1
+torch==2.0.0
 onnx>=1.12
 onnxruntime==1.13.1
 

examples/huggingface/pytorch/question-answering/deployment/squad/ipex/bert_large/requirements.txt

@@ -1,5 +1,5 @@
 datasets >= 1.8.0
 torch == 1.13.1
 transformers==4.19.0
-intel-extension-for-pytorch==1.13.0
+intel-extension-for-pytorch==2.0.0
 wandb

examples/huggingface/pytorch/question-answering/deployment/squad/ipex/distilbert_base_uncased/requirements.txt

@@ -1,5 +1,5 @@
 datasets >= 1.8.0
 torch == 1.13.1
 transformers==4.19.0
-intel-extension-for-pytorch==1.13.0
+intel-extension-for-pytorch==2.0.0
 wandb

examples/huggingface/pytorch/question-answering/deployment/squad/ipex/distilbert_base_uncased_sparse/requirements.txt

@@ -1,5 +1,5 @@
 datasets >= 1.8.0
 torch == 1.13.1
 transformers==4.19.0
-intel-extension-for-pytorch==1.13.0
+intel-extension-for-pytorch==2.0.0
 wandb

examples/huggingface/pytorch/question-answering/deployment/squad/length_adaptive_transformer/requirements.txt

@@ -4,7 +4,7 @@ accelerate
 datasets >= 1.8.0
 sentencepiece != 0.1.92
 protobuf
-torch==1.13.1
+torch==2.0.0
 onnx>=1.12
 onnxruntime==1.12.1
 

examples/huggingface/pytorch/question-answering/distillation/requirements.txt

@@ -1,4 +1,4 @@
 datasets >= 1.8.0
 torch >= 1.10.0
-transformers>=4.12.0
+transformers<=4.29.1
 wandb

examples/huggingface/pytorch/question-answering/dynamic/requirements.txt

@@ -1,4 +1,4 @@
-transformers
+transformers<=4.29.1
 datasets
 torchprofile
 torch

examples/huggingface/pytorch/question-answering/orchestrate_optimizations/requirements.txt

@@ -1,4 +1,4 @@
 datasets >= 1.8.0
 torch >= 1.10.0
-transformers >= 4.12.0
+transformers<=4.29.1
 wandb

examples/huggingface/pytorch/question-answering/pruning/basic_magnitude/requirements.txt

@@ -1,4 +1,4 @@
 datasets >= 1.8.0
 torch >= 1.10.0
-transformers >= 4.12.0
+transformers<=4.29.1
 wandb

examples/huggingface/pytorch/question-answering/pruning/longformer_triviaqa/requirements.txt

@@ -1,5 +1,5 @@
 accelerate
 datasets
-transformers
+transformers<=4.29.1
 torch
 neural-compressor==2.0

examples/huggingface/pytorch/question-answering/quantization/requirements.txt

@@ -1,5 +1,5 @@
 datasets >= 1.1.3
 torch >= 1.10
-transformers
+transformers<=4.29.1
 wandb
 accelerate

examples/huggingface/pytorch/text-classification/deployment/emotion/distilbert_base_uncased/requirements.txt

@@ -4,7 +4,7 @@ accelerate
 datasets >= 1.8.0
 sentencepiece != 0.1.92
 protobuf
-torch==1.13.1
+torch==2.0.0
 onnx>=1.12
 onnxruntime==1.13.1
 

examples/huggingface/pytorch/text-classification/deployment/mrpc/bert_base/requirements.txt

@@ -4,7 +4,7 @@ accelerate
 datasets >= 1.8.0
 sentencepiece != 0.1.92
 protobuf
-torch==1.13.1
+torch==2.0.0
 onnx>=1.12
 onnxruntime==1.13.1
 

examples/huggingface/pytorch/text-classification/deployment/mrpc/bert_base_cased/requirements.txt

@@ -4,7 +4,7 @@ accelerate
 datasets >= 1.8.0
 sentencepiece != 0.1.92
 protobuf
-torch==1.13.1
+torch==2.0.0
 onnx>=1.12
 onnxruntime==1.13.1
 

examples/huggingface/pytorch/text-classification/deployment/mrpc/bert_mini/requirements.txt

@@ -4,7 +4,7 @@ accelerate
 datasets >= 1.8.0
 sentencepiece != 0.1.92
 protobuf
-torch==1.13.1
+torch==2.0.0
 onnx>=1.12
 onnxruntime==1.13.1
 

examples/huggingface/pytorch/text-classification/deployment/mrpc/distilbert_base_uncased/requirements.txt

@@ -4,7 +4,7 @@ accelerate
 datasets >= 1.8.0
 sentencepiece != 0.1.92
 protobuf
-torch==1.13.1
+torch==2.0.0
 onnx>=1.12
 onnxruntime==1.13.1
 

examples/huggingface/pytorch/text-classification/deployment/mrpc/roberta_base/requirements.txt

@@ -4,7 +4,7 @@ accelerate
 datasets >= 1.8.0
 sentencepiece != 0.1.92
 protobuf
-torch==1.13.1
+torch==2.0.0
 onnx>=1.12
 onnxruntime==1.13.1
 

examples/huggingface/pytorch/text-classification/deployment/sparse/bert_mini/requirements.txt

@@ -4,7 +4,7 @@ accelerate
 datasets >= 1.8.0
 sentencepiece != 0.1.92
 protobuf
-torch==1.13.1
+torch==2.0.0
 onnx>=1.12
 onnxruntime==1.13.1
 

examples/huggingface/pytorch/text-classification/deployment/sparse/distilbert_base_uncased/requirements.txt

@@ -4,7 +4,7 @@ accelerate
 datasets >= 1.8.0
 sentencepiece != 0.1.92
 protobuf
-torch==1.13.1
+torch==2.0.0
 onnx>=1.12
 onnxruntime==1.13.1
 

examples/huggingface/pytorch/text-classification/deployment/sst2/bert_mini/requirements.txt

@@ -4,7 +4,7 @@ accelerate
 datasets >= 1.8.0
 sentencepiece != 0.1.92
 protobuf
-torch==1.13.1
+torch==2.0.0
 onnx>=1.12
 onnxruntime==1.13.1
 

examples/huggingface/pytorch/text-classification/deployment/sst2/distilbert_base_uncased/requirements.txt

@@ -4,7 +4,7 @@ accelerate
 datasets >= 1.8.0
 sentencepiece != 0.1.92
 protobuf
-torch==1.13.1
+torch==2.0.0
 onnx>=1.12
 onnxruntime==1.13.1
 

examples/huggingface/pytorch/text-classification/deployment/sst2/minilm_l6_h384_uncased/requirements.txt

@@ -4,7 +4,7 @@ accelerate
 datasets >= 1.8.0
 sentencepiece != 0.1.92
 protobuf
-torch==1.13.1
+torch==2.0.0
 onnx>=1.12
 onnxruntime==1.13.1
 

examples/huggingface/pytorch/text-classification/distillation/requirements.txt

@@ -3,5 +3,5 @@ datasets >= 1.1.3
 sentencepiece != 0.1.92
 protobuf
 torch >= 1.10.0
-transformers>=4.12.0
+transformers<=4.29.1
 wandb

examples/huggingface/pytorch/text-classification/distillation_for_quantization/requirements.txt

@@ -2,6 +2,6 @@ accelerate
 torch >= 1.10
 datasets >= 1.1.3
 sentencepiece != 0.1.92
-transformers >= 4.12.0
+transformers<=4.29.1
 protobuf
 wandb

examples/huggingface/pytorch/text-classification/new_pruning/requirements.txt

@@ -1,5 +1,5 @@
 datasets
-transformers
+transformers<=4.29.1
 accelerate
 datasets
 sentencepiece

examples/huggingface/pytorch/text-classification/orchestrate_optimizations/requirements.txt

@@ -2,6 +2,6 @@ accelerate
 torch >= 1.10
 datasets >= 1.1.3
 sentencepiece != 0.1.92
-transformers >= 4.12.0
+transformers<=4.29.1
 protobuf
 wandb

examples/huggingface/pytorch/text-classification/pruning/requirements.txt

@@ -3,5 +3,5 @@ datasets >= 1.1.3
 sentencepiece != 0.1.92
 protobuf
 torch >= 1.10.0
-transformers>=4.12.0
+transformers<=4.29.1
 wandb

examples/huggingface/pytorch/text-classification/quantization/ptq/requirements.txt

@@ -3,5 +3,5 @@ datasets >= 1.1.3
 sentencepiece != 0.1.92
 protobuf
 torch >= 1.10
-transformers >= 4.12.0
+transformers<=4.29.1
 wandb

examples/huggingface/pytorch/text-classification/quantization/requirements.txt

@@ -3,5 +3,5 @@ datasets >= 1.1.3
 sentencepiece != 0.1.92
 protobuf
 torch >= 1.10
-transformers >= 4.12.0
+transformers<=4.29.1
 wandb

examples/huggingface/pytorch/text-generation/README.md

@@ -0,0 +1,37 @@
+# Text Generation
+Text generation is a common task in natural language processing field. It leverages knowledge in computational linguistics and artificial intelligence to automatically generate natural language texts, which can satisfy certain communicative requirements.
+
+We provide quantizatioin script [run_generation.py](./quantization/run_generation.py) for [EleutherAI/gpt-j-6B](https://huggingface.co/EleutherAI/gpt-j-6B),  [decapoda-research/llama-7b-hf](https://huggingface.co/decapoda-research/llama-7b-hf), [decapoda-research/llama-13b-hf](https://huggingface.co/decapoda-research/llama-13b-hf), [databricks/dolly-v2-3b](https://huggingface.co/databricks/dolly-v2-3b), [bigscience/bloom-7b1](https://huggingface.co/bigscience/bloom-7b1), [facebook/opt-1.3b](https://huggingface.co/facebook/opt-1.3b), [facebook/opt-2.7b](https://huggingface.co/facebook/opt-2.7b) and [facebook/opt-6.7b](https://huggingface.co/facebook/opt-6.7b) .
+
+
+We also provide Neural Engine Inference for [EleutherAI/gpt-j-6B](https://huggingface.co/EleutherAI/gpt-j-6B) and [decapoda-research/llama-7b-hf](https://huggingface.co/decapoda-research/llama-7b-hf)
+
+
+## Validated Models
+Neural Compressor: 2.1
+
+IPEX (Intel Extension for PyTorch): 2.0
+
+Dataset: lambada-openai
+
+
+| Model\Last token accuracy |  smoothquant config  | FP32  | BF16 | INT8 (mixed precision) |
+|---------------------|:------:|:----------------------:|-----------------------|-----------------------------------|
+| EleutherAI/gpt-j-6B | alpha 1.0/folding=False | 68.31% | 67.86% | 68.21% (w/o BF16) |
+| decapoda-research/llama-7b-hf | alpha 0.8 | 73.61% | 73.26% | 73.57% (w/ FP32) |
+| decapoda-research/llama-13b-hf | alpha 0.7 | 76.27% | 76.01% | 75.90% (w/ FP32) |
+| decapoda-research/llama-30b-hf | alpha 0.7 | 77.57% | 77.53% | 78.40% (w/ FP32) |
+| facebook/opt-125m   | alpha 0.5/folding=False | 37.9% | 37.63% | 37.57% (w/o BF16) |
+| facebook/opt-350m   | alpha 0.8/folding=False | 45.16% | 45.06% | 45.53% (w/o BF16) |
+| facebook/opt-2.7b   | alpha 0.5/folding=False | 63.65% | 63.23% | 64.04% (w/ BF16) |
+| facebook/opt-6.7b   | alpha 0.5/folding=False | 67.69% | 67.36% | 68.04% (w/ BF16) |
+| facebook/opt-13b   | alpha 0.5/folding=False | 68.72% | 67.84% | 68.14% (w/o BF16) |
+| facebook/opt-30b   | alpha 0.5/folding=False | 71.49% | 70.87% | 71.28% (w/o BF16) |
+| bigscience/bloom-560m   | alpha 0.5/folding=False | 35.4% | 25.56% | 35.36% (w/o BF16) |
+| bigscience/bloom-1b7   | alpha 0.5/folding=False | 46.34% | 45.7% | 49.06% (w/ BF16) |
+| bigscience/bloom-3b   | alpha 0.8/folding=False | 51.8% | 51.35% | 51.85% (w/o BF16) |
+| bigscience/bloom-7b1   | alpha 0.5/folding=False | 57.64% | 57.23% | 59.77% (w/ BF16) |
+| databricks/dolly-v1-6b   | alpha 0.8/folding=False | 68.66% | 67.96% | 68.95% (w/o BF16) |
+| databricks/dolly-v2-3b   | alpha 0.5/folding=False | 62.97% | 60.86% | 62.47% (w/o BF16) |
+
+

examples/huggingface/pytorch/text-to-image/deployment/stable_diffusion/requirements.txt

@@ -4,7 +4,7 @@ accelerate
 datasets >= 1.8.0
 sentencepiece != 0.1.92
 protobuf
-torch==1.13.1
+torch==2.0.0
 onnx>=1.12
 onnxruntime==1.13.1
 diffusers==0.12.1

examples/huggingface/pytorch/textual-inversion/quantization/textual_inversion/requirements.txt

@@ -1,9 +1,9 @@
 diffusers==0.4.1
 accelerate
-torch==1.13.1
+torch==2.0.0
 torchvision
-transformers>=4.21.0
+transformers<=4.29.1
 ftfy
 tensorboard
 modelcards
-intel_extension_for_pytorch==1.13.100
+intel_extension_for_pytorch==2.0.0

examples/huggingface/pytorch/token-classification/quantization/requirements.txt

@@ -2,5 +2,5 @@ accelerate
 seqeval
 datasets >= 1.1.3
 torch >= 1.10
-transformers
+transformers<=4.29.1
 wandb

examples/huggingface/tensorflow/language-modeling/quantization/ptq/requirements.txt

@@ -1,6 +1,6 @@
 datasets >= 1.17
 sentencepiece != 0.1.92
 protobuf
-intel-tensorflow == 2.10.0
-transformers >= 4.12.0
+intel-tensorflow
+transformers<=4.29.1
 scikit-learn

examples/huggingface/tensorflow/multiple-choice/quantization/requirements.txt

@@ -1,5 +1,5 @@
 datasets >= 1.17
 sentencepiece != 0.1.92
 protobuf
-intel-tensorflow == 2.10.0
-transformers >= 4.12.0
+intel-tensorflow
+transformers<=4.29.1

examples/huggingface/tensorflow/text-classification/distillation/auto_distillation/requirements.txt

@@ -2,4 +2,4 @@ datasets >= 1.17
 sentencepiece != 0.1.92
 protobuf
 intel-tensorflow
-transformers>=4.12.0
+transformers<=4.29.1

examples/huggingface/tensorflow/text-classification/distillation/requirements.txt

@@ -2,4 +2,4 @@ datasets >= 1.17
 sentencepiece != 0.1.92
 protobuf
 intel-tensorflow
-transformers>=4.12.0
+transformers<=4.29.1

examples/huggingface/tensorflow/text-classification/pruning/requirements.txt

@@ -1,5 +1,5 @@
 datasets >= 1.17
 sentencepiece != 0.1.92
 protobuf
-intel-tensorflow == 2.10.0
-transformers>=4.12.0
+intel-tensorflow
+transformers<=4.29.1