Search Results for "bloom"

An elegant PyTorch implement of transformers.

Easy-to-use LLM fine-tuning framework (LLaMA-2, BLOOM, Falcon, Baichuan, Qwen, ChatGLM2)

Huatuo-Llama-Med-Chinese is an open-source project that develops medical-domain large language models by instruction-tuning existing models using Chinese medical knowledge. The project builds specialized models by fine-tuning architectures such as LLaMA, Alpaca-Chinese, and Bloom with curated medical datasets. These datasets are constructed from medical knowledge graphs, academic literature, and question-answer pairs designed to teach models how to respond accurately to healthcare-related queries. The goal of the project is to improve the reliability and domain expertise of language models when answering medical questions or assisting with healthcare-related tasks. ...

Machine Learning Engineering Open Book is an open “living book” that captures practical methodologies, tooling advice, and operational knowledge for successfully training and deploying large language models and multimodal systems. The repository functions as a field guide compiled from real-world experience, particularly from work on large-scale models such as BLOOM-176B and IDEFICS-80B. It is heavily oriented toward practitioners who need hands-on solutions, including copy-paste commands, infrastructure comparisons, and performance tuning strategies. The material spans the full ML lifecycle, from hardware selection and distributed training to inference optimization and debugging. Rather than focusing purely on theory, the project emphasizes engineering tradeoffs and production realities that often determine success at scale. ...

CTranslate2 is a C++ and Python library for efficient inference with Transformer models. The project implements a custom runtime that applies many performance optimization techniques such as weights quantization, layers fusion, batch reordering, etc., to accelerate and reduce the memory usage of Transformer models on CPU and GPU. The execution is significantly faster and requires less resources than general-purpose deep learning frameworks on supported models and tasks thanks to many...

MII makes low-latency and high-throughput inference possible, powered by DeepSpeed. The Deep Learning (DL) open-source community has seen tremendous growth in the last few months. Incredibly powerful text generation models such as the Bloom 176B, or image generation model such as Stable Diffusion are now available to anyone with access to a handful or even a single GPU through platforms such as Hugging Face. While open-sourcing has democratized access to AI capabilities, their application is still restricted by two critical factors: inference latency and cost. DeepSpeed-MII is a new open-source python library from DeepSpeed, aimed towards making low-latency, low-cost inference of powerful models not only feasible but also easily accessible. ...

YAYI is an open-source large language model project developed to provide a multilingual conversational AI system capable of performing a wide variety of natural language processing tasks. The model is trained on diverse datasets covering multiple languages and domains so that it can support applications ranging from dialogue systems to text analysis and knowledge retrieval. The architecture is based on transformer-style language models optimized for conversational understanding and...

...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. Petals runs large language models like BLOOM-176B collaboratively — you load a small part of the model, then team up with people serving the other parts to run inference or fine-tuning.

...It is designed for large-scale inference and supports both left-to-right generation and blank filling, making it versatile across NLP tasks. Trained on over 400 billion tokens (200B English, 200B Chinese), it achieves performance surpassing GPT-3 175B, OPT-175B, and BLOOM-176B on multiple benchmarks, while also showing significant improvements on Chinese datasets compared to other large models. The model supports efficient inference via INT8 and INT4 quantization, reducing hardware requirements from 8× A100 GPUs to as little as a single server with 4× RTX 3090s. Built on the SwissArmyTransformer (SAT) framework and compatible with DeepSpeed and FasterTransformer, it supports high-speed inference (up to 2.5× faster) and reproducible evaluation across 30+ benchmark tasks.