Spaces:
Running
Running
isExpanded: false | |
sections: | |
local: tasks/idefics | |
title: Image tasks with IDEFICS | |
local: tasks/prompting | |
title: LLM prompting guide | |
title: Prompting | |
title: Task Guides | |
sections: | |
local: fast_tokenizers | |
title: Use fast tokenizers from π€ Tokenizers | |
local: multilingual | |
title: Run inference with multilingual models | |
local: create_a_model | |
title: Use model-specific APIs | |
local: custom_models | |
title: Share a custom model | |
local: chat_templating | |
title: Templates for chat models | |
local: trainer | |
title: Trainer | |
local: sagemaker | |
title: Run training on Amazon SageMaker | |
local: serialization | |
title: Export to ONNX | |
local: tflite | |
title: Export to TFLite | |
local: torchscript | |
title: Export to TorchScript | |
local: benchmarks | |
title: Benchmarks | |
local: notebooks | |
title: Notebooks with examples | |
local: community | |
title: Community resources | |
local: troubleshooting | |
title: Troubleshoot | |
local: gguf | |
title: Interoperability with GGUF files | |
title: Developer guides | |
sections: | |
local: quantization/overview | |
title: Getting started | |
local: quantization/bitsandbytes | |
title: bitsandbytes | |
local: quantization/gptq | |
title: GPTQ | |
local: quantization/awq | |
title: AWQ | |
local: quantization/aqlm | |
title: AQLM | |
local: quantization/quanto | |
title: Quanto | |
local: quantization/eetq | |
title: EETQ | |
local: quantization/hqq | |
title: HQQ | |
local: quantization/optimum | |
title: Optimum | |
local: quantization/contribute | |
title: Contribute new quantization method | |
title: Quantization Methods | |
sections: | |
local: performance | |
title: Overview | |
local: llm_optims | |
title: LLM inference optimization | |
sections: | |
local: perf_train_gpu_one | |
title: Methods and tools for efficient training on a single GPU | |
local: perf_train_gpu_many | |
title: Multiple GPUs and parallelism | |
local: fsdp | |
title: Fully Sharded Data Parallel | |
local: deepspeed | |
title: DeepSpeed | |
local: perf_train_cpu | |
title: Efficient training on CPU | |
local: perf_train_cpu_many | |
title: Distributed CPU training | |
local: perf_train_tpu_tf | |
title: Training on TPU with TensorFlow | |
local: perf_train_special | |
title: PyTorch training on Apple silicon | |
local: perf_hardware | |
title: Custom hardware for training | |
local: hpo_train | |
title: Hyperparameter Search using Trainer API | |
title: Efficient training techniques | |
sections: | |
local: perf_infer_cpu | |
title: CPU inference | |
local: perf_infer_gpu_one | |
title: GPU inference | |
title: Optimizing inference |