davisyoshida / easy-lora-and-gptqLinks
JAX notebook showing how to LoRA + GPTQ arbitrary models
☆10Updated 2 years ago
Alternatives and similar repositories for easy-lora-and-gptq
Users that are interested in easy-lora-and-gptq are comparing it to the libraries listed below
Sorting:
- Experiments with generating opensource language model assistants☆97Updated 2 years ago
- Exploring finetuning public checkpoints on filter 8K sequences on Pile☆116Updated 2 years ago
- JAX implementation of the Llama 2 model☆216Updated last year
- Code repository for the c-BTM paper☆108Updated 2 years ago
- Code for the paper "The Impact of Positional Encoding on Length Generalization in Transformers", NeurIPS 2023☆138Updated last year
- ☆94Updated 2 years ago
- Large scale 4D parallelism pre-training for 🤗 transformers in Mixture of Experts *(still work in progress)*☆87Updated last year
- Multi-Domain Expert Learning☆67Updated last year
- ☆50Updated last year
- some common Huggingface transformers in maximal update parametrization (µP)☆87Updated 3 years ago
- HomebrewNLP in JAX flavour for maintable TPU-Training☆51Updated last year
- ☆20Updated 2 years ago
- ☆53Updated last year
- Inference code for LLaMA models in JAX☆120Updated last year
- Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limit☆63Updated 2 years ago
- ☆82Updated last year
- QLoRA with Enhanced Multi GPU Support☆37Updated 2 years ago
- Collection of autoregressive model implementation☆85Updated 7 months ago
- Train very large language models in Jax.☆210Updated 2 years ago
- Amos optimizer with JEstimator lib.☆82Updated last year
- Functional local implementations of main model parallelism approaches☆95Updated 2 years ago
- Repo for training MLMs, CLMs, or T5-type models on the OLM pretraining data, but it should work with any hugging face text dataset.☆96Updated 2 years ago
- Official Repository of Pretraining Without Attention (BiGS), BiGS is the first model to achieve BERT-level transfer learning on the GLUE …☆115Updated last year
- Supercharge huggingface transformers with model parallelism.☆77Updated 4 months ago
- Genalog is an open source, cross-platform python package allowing generation of synthetic document images with custom degradations and te…☆44Updated last year
- QAmeleon introduces synthetic multilingual QA data using PaLM, a 540B large language model. This dataset was generated by prompt tuning P…☆35Updated 2 years ago
- Experiments for efforts to train a new and improved t5☆76Updated last year
- Multipack distributed sampler for fast padding-free training of LLMs☆202Updated last year
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training☆132Updated last year
- Comprehensive analysis of difference in performance of QLora, Lora, and Full Finetunes.☆83Updated 2 years ago