Search Results for "parallel language" - Page 2
Sort By:
Showing 46 open source projects for "parallel language"
View related business solutions-
Earn up to 15% annual interest with Nexo.Put idle assets to work with competitive interest rates, borrow without selling, and trade with precision. All in one platform. Geographic restrictions, eligibility, and terms apply.
-
Earn up to 15% annual interest with Nexo.Generate interest, borrow against your crypto, and trade a range of cryptocurrencies — all in one platform. Geographic restrictions, eligibility, and terms apply.
-
1
Petals
Run 100B+ language models at home, BitTorrent-style
Parallel inference reaches hundreds of tokens/sec. Beyond classic language model APIs — you can employ any fine-tuning and sampling methods, execute custom paths through the model, or see its hidden states. You get the comforts of an API with the flexibility of PyTorch. You can also host BLOOMZ, a version of BLOOM fine-tuned to follow human instructions in the zero-shot regime — just replace bloom-petals with bloomz-petals. -
2
Graph of Thoughts
Official Implementation of "Graph of Thoughts
...The framework executes these operations using a large language model as the reasoning engine while evaluating intermediate results to guide the search process. This approach enables models to explore multiple reasoning strategies in parallel and choose the most promising solutions during problem solving. -
3
Medusa
Framework for Accelerating LLM Generation with Multiple Decoding Heads
Medusa is a framework aimed at accelerating the generation capabilities of Large Language Models (LLMs) by employing multiple decoding heads. This approach allows for parallel processing during text generation, significantly enhancing throughput and reducing response times. Medusa is designed to be simple to implement and integrates with existing LLM infrastructures, making it a practical solution for scaling LLM applications. -
4
text-dedup
All-in-one text de-duplication
...This is especially useful for NLP tasks where duplicated training data can skew model performance. text-dedup scales to billions of documents and offers tools for chunking, hashing, and comparing text efficiently with low memory usage. It supports Jaccard similarity thresholding, parallel execution, and flexible deduplication strategies, making it ideal for cleaning web-scraped data, language model training datasets, or document archives. -
Build innovative business apps powered by process automationManage your business as a unified system of interacting processes. Use BPMN 2.0 for low-code process modeling by business people. Follow your strategic goals with process architecture that always corresponds to the structure of an actual business.
-
5
GPT-NeoX
Implementation of model parallel autoregressive transformers on GPUs
This repository records EleutherAI's library for training large-scale language models on GPUs. Our current framework is based on NVIDIA's Megatron Language Model and has been augmented with techniques from DeepSpeed as well as some novel optimizations. We aim to make this repo a centralized and accessible place to gather techniques for training large-scale autoregressive language models, and accelerate research into large-scale training. For those looking for a TPU-centric codebase, we... -
6
TextBox
A text generation library with pre-trained language models github.com
TextBox 2.0 is an up-to-date text generation library based on Python and PyTorch focusing on building a unified and standardized pipeline for applying pre-trained language models to text generation. From a task perspective, we consider 13 common text generation tasks such as translation, story generation, and style transfer, and their corresponding 83 widely-used datasets. From a model perspective, we incorporate 47 pre-trained language models/modules covering the categories of general, translation, Chinese, dialogue, controllable, distilled, prompting, and lightweight models (modules). ... -
7
Fairseq
Facebook AI Research Sequence-to-Sequence Toolkit written in Python
Fairseq(-py) is a sequence modeling toolkit that allows researchers and developers to train custom models for translation, summarization, language modeling and other text generation tasks. We provide reference implementations of various sequence modeling papers. Recent work by Microsoft and Google has shown that data parallel training can be made significantly more efficient by sharding the model parameters and optimizer state across data parallel workers. These ideas are encapsulated in the new FullyShardedDataParallel (FSDP) wrapper provided by fairscale. ... -
8
GPT Neo
An implementation of model parallel GPT-2 and GPT-3-style models
An implementation of model & data parallel GPT3-like models using the mesh-tensorflow library. If you're just here to play with our pre-trained models, we strongly recommend you try out the HuggingFace Transformer integration. Training and inference is officially supported on TPU and should work on GPU as well. This repository will be (mostly) archived as we move focus to our GPU-specific repo, GPT-NeoX. NB, while neo can technically run a training step at 200B+ parameters, it is very... -
9
FARM
Fast & easy transfer learning for NLP
...With FARM you can build fast proofs-of-concept for tasks like text classification, NER or question answering and transfer them easily into production. Easy fine-tuning of language models to your task and domain language. AMP optimizers (~35% faster) and parallel preprocessing (16 CPU cores => ~16x faster). Modular design of language models and prediction heads. Switch between heads or combine them for multitask learning. Full Compatibility with HuggingFace Transformers' models and model hub. Smooth upgrading to newer language models. ... -
Awardco Employee RecognitionEverything you love about Amazon is now available for rewards and recognition. Awardco has partnered with Amazon Business to bring millions of reward choices, lower vendor fees and dollar-for-dollar recognition spend to your organization. More choice, more capability, and less spend - all in one simple platform.
-
10
XLM (Cross-lingual Language Model)
PyTorch original implementation of Cross-lingual Language Model
XLM (Cross-lingual Language Model) is a family of multilingual pretraining methods that align representations across languages to enable strong zero-shot transfer. It popularized objectives like Masked Language Modeling (MLM) across many languages and Translation Language Modeling (TLM) that jointly trains on parallel sentence pairs to tighten cross-lingual alignment. -
11
UnsupervisedMT
Phrase-Based & Neural Unsupervised Machine Translation
...The project also provides scripts to fetch and preprocess monolingual data, learn BPE codes, and train cross-lingual embeddings that bootstrap unsupervised alignment between languages. Beyond the core EMNLP 2018 setup, the codebase exposes additional, optional capabilities such as multi-language training, language model pretraining with shared parameters, and adversarial training. -
12
Pipelines
An experimental programming language for data flow
Pipelines is a language and runtime for crafting massively parallel pipelines. Unlike other languages for defining data flow, the Pipeline language requires the implementation of components to be defined separately in the Python scripting language. This allows the details of implementations to be separated from the structure of the pipeline while providing access to thousands of active libraries for machine learning, data analysis, and processing. -
13
OpenSeq2Seq
Toolkit for efficient experimentation with Speech Recognition
...Its core goal is to give researchers a flexible, modular framework for building and training encoder–decoder architectures while fully leveraging distributed and mixed-precision training. The toolkit includes ready-made models for neural machine translation, automatic speech recognition, speech synthesis, language modeling, and additional NLP tasks such as sentiment analysis. It supports multi-GPU and multi-node data-parallel training, and integrates with Horovod to scale out across large GPU clusters. Mixed-precision support (float16) is optimized for NVIDIA Volta and Turing GPUs, allowing significant speedups and memory savings without sacrificing model quality. ... -
14
TensorFlow-ZH
Chinese version of the official document of TensorFlow
The tensorflow-zh repository is a Chinese translation of the official TensorFlow documentation, organized to make the core guides, tutorials, and reference material accessible to Chinese speakers. It was initiated shortly after TensorFlow’s open-sourcing, with translation and proofreading contributions from a community of volunteers who aimed to bridge the language barrier for learners in China and other Mandarin communities. The repo mirrors the structure of the original English docs:... -
15
Hierarchical cluster engine HCE
Hierarchical Cluster Engine project
The main idea of this project – to implement the solution that can be used to: construct custom network mesh or distributed network cluster structure with several relations types between nodes, formalize the data flow processing goes from upper node level central source point to down nodes and backward, formalize the management requests handling from multiple source points, support native reducing of multiple nodes results (aggregation, duplicates elimination, sorting and so on), internally support powerful full-text search engine and data storage, provide transactions-less and transactional requests processing, support flexible run-time changes of cluster infrastructure, have many languages bindings for client-side integration APIs in one product build on C++ language... Also, HCE includes the highlighter application. This is utility to get fast parallel multi-algorithmic textual patterns highlighting. It provides cli UI, works as filter console tool and uses json format of prot -
16
AWK~plus is the next generation script practice environment. The AWK Language specifications and a main extension of GNU GAWK. Combination of Dynamic and Static typing. Parallel computing that a lock is free, and is thread safe at a language level.
-
17
Cca-forum unifies the Common Component Architecture tools and tutorial. It includes the CCA specifications, the Ccaffeine framework for HPC, and related tools. These support multilanguage scientific and parallel computing.
-
18
Originally made to crack /etc/passwd files from *nix utilizing the GPU. Uses GLSL and OpenGL. Acts as a parallel to John the Ripper, but for the GPU. Supports both ATI and nVidia, anywhere OpenGL can run.
-
19
The PyAALib-JyAALib project is a Python-Java/Jython implementation of the Asynchronous Action Framework based on Pure Object Oriented Concepts. The Massive Parallel Framework in Python Language - Full Compatible with Jython-JAVA
-
20
Simple Distributed Job Management Tools facilitates parallel, distributed execution of simple commands, on a network of UNIX-like machines. Components include a job dependency/exclusivity language and load-balanced remote execution facility.
-
21
The Minions programming language makes it easy to write performant, highly parallel programs. Minions are especially good at web apps. Minions like the web.
