Sparsebit
nncf
| Sparsebit | nncf | |
|---|---|---|
| 1 | 2 | |
| 320 | 830 | |
| 1.3% | 8.4% | |
| 5.9 | 9.7 | |
| 4 months ago | 1 day ago | |
| Python | Python | |
| Apache License 2.0 | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Sparsebit
nncf
- FLaNK Stack Weekly 06 Nov 2023
-
NN mixed-precision quantization framework that supports TF?
I am aware of NNCF (https://github.com/openvinotoolkit/nncf), but it doesn't support mixed precision quantization for TF. What other frameworks support that for TF? (implement HAWQ or AutoQ algorithms for example)
What are some alternatives?
LLaMA-8bit-LoRA - Repository for Chat LLaMA - training a LoRA for the LLaMA (1 or 2) models on HuggingFace with 8-bit or 4-bit quantization. Research only.
gpt-llm-trainer
sparsegpt-for-LLaMA - Code for the paper "SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot" with LLaMA implementation.
model-optimization - A toolkit to optimize ML models for deployment for Keras and TensorFlow, including quantization and pruning.
tabmat - Efficient matrix representations for working with tabular data
json-masker - High-performance JSON masker library in Java with no runtime dependencies
FQ-ViT - [IJCAI 2022] FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformer
Open3D-ML - An extension of Open3D to address 3D Machine Learning tasks
text-generation-webui - A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.
deepsparse - Sparsity-aware deep learning inference runtime for CPUs
alpaca-lora - Instruct-tune LLaMA on consumer hardware
open_model_zoo - Pre-trained Deep Learning models and demos (high quality and extremely fast)