huggingface / optimum

🚀 Accelerate training and inference of 🤗 Transformers and 🤗 Diffusers with easy to use hardware optimization tools

https://huggingface.co/docs/optimum/main/

huggingface/optimum Issues

Unable to Export Chatglm3 Model to ONNX Format in Optimum
Updated 6 days ago2
why does ORTModelForCausalLM assume new input length is 1 when past_key_values is passed
Updated 6 days ago
Quantizing from cli using config file fails
Updated 7 days ago
Pushing to the hub with a token
Updated 9 days ago
Llama 3 Support
Updated 9 days ago
The transformation of the model Blip2ForConditionalGeneration to BetterTransformer failed
Updated 10 days ago
Phi3 support
Updated 11 days ago2
Support Transformers >=4.40.0
Closed 13 days ago2
Idefics2 Support in Optimum for ONNX export
Updated 13 days ago1
ORTOptimizer for the model type table-transformer
Updated 16 days ago2
AttributeError: '_ORTModelForWhisper' object has no attribute '_retrieve_segment'
Closed 16 days ago
Request for ONNX Export Support for Blip Model in Optimum
Updated 18 days ago
Unable to Export Whisper-Large-V3 Model to ONNX Format in Optimum
Closed 19 days ago1
Issue Report: Unable to Export Gemma 7b Model to ONNX Format in Optimum
Updated 19 days ago1
Support Llava ONNX export
Updated 19 days ago1
Exporting tinyllama-1.1b using onnxruntime bf16 crashes
Updated 23 days ago4
[Tracking] TorchDynamo ONNX exporter issues
Updated 23 days ago
Cannot export jinaai models to onnx format because the model is > 2Gb
Updated 25 days ago4
The exported ONNX model of Qwen/Qwen1.5-0.5B-Chat does not produce a cache-enabled model.
Closed a month ago3
HF_HUB_OFFLINE not supported
Closed 25 days ago4
advice for simple onnxruntime script for ORTModelForVision2Seq (or separate encoder/decoder)
Updated a month ago
[VitMatte] Cannot export VitMatte model to ONNX
Closed a month ago3
Issue Report: Unable to Export Qwen Model to ONNX Format in Optimum
Updated a month ago
Documentation for exporting openai/whisper-large-v3 to ONNX
Updated a month ago10
Bettertransformers not working with TFAutomodelforsequenceclassification model
Closed a month ago2
There is a significant difference between using method 1 to export the onnx model and using method 2 to export the onnx model, while relying on optimus.
Closed a month ago3
CallbackManager error
Updated a month ago
Llava ONNX export
Updated a month ago1
NotImplementedError: The model type esm is not yet supported to be used with BetterTransformer.
Updated a month ago
Downloading model from Huggingface Hub does not download ort_config.json
Updated a month ago
support for sfr embedding mistral & nomic models
Updated a month ago
Unable to export Table Transformer
Closed a month ago4
How to convert a model(tf_model.h5) with tokenizer folder to the onnx format
Updated a month ago5
DummyTextInputGenerator doesn't take into account type_vocab_size model config parameter
Updated a month ago1
Accuracy change with BetterTransformer
Updated a month ago6
Please Add HelpingAI to it
Updated a month ago2
ONNX conversion of google/gemma-2b-it logits values are very different
Updated a month ago9
How to tell whether the backend of ONNXRuntime accelerator is Intel VINO.
Closed 2 months ago2
NoSuchFile: [ONNXRuntimeError] : 3 : NO_SUCHFILE : Load model from data/data_onnx/model.onnx failed:Load model data/data_onnx/model.onnx failed. File doesn't exist
Updated 2 months ago1
[BUG] Cannot export Gemma/Mistral to ONNX/TensorRT using INT8
Closed 2 months ago9
Cannot download from private repository on Hugging Face using optimum 1.17
Closed 2 months ago3
Performance with ORTModelForSequenceClassification is worse than with the original model
Closed 2 months ago3
Missing `token_type_ids` when different tokenizer and model
Updated 2 months ago
Training fails because of accelerate configure settings.
Closed 2 months ago1
Mixtral-8x7B-Instruct-v0.1-GPTQ AssertionError
Updated 2 months ago6
OnnxSlim support
Updated 2 months ago
Cannot download ONNX external data file from Hugging Face Hub
Closed 2 months ago4
onnx model issue for zeroshot facebook/bart-large-mnli
Closed 2 months ago1
[BUG] Mistral feature extraction export to ONNX is broken
Closed 2 months ago5
[BUG] Mistral feature extraction export to ONNX is broken
Closed 2 months ago