Search Results for "run length encoding"

tiktoken is a high-performance, tokenizer library (based on byte-pair encoding, BPE) designed for use with OpenAI’s models. It handles encoding and decoding text to token IDs efficiently, with minimal overhead. Because tokenization is a fundamental step in preparing text for models, tiktoken is optimized for speed, memory, and correctness in model contexts (e.g. matching OpenAI’s internal tokenization). The repo supports multiple encodings (e.g. “cl100k_base”) and lets users switch encoding...

...It integrates cutting-edge generative techniques—such as diffusion-based synthesis combined with compressed autoencoders and lightweight transformer elements—to produce high-quality full-length music tracks with rapid inference times, capable of generating a complete song in seconds on modern GPUs while remaining efficient enough to run on consumer-grade hardware with minimal memory requirements. Beyond straightforward text-to-music synthesis, ACE-Step 1.5 enables flexible creative workflows, including tasks like cover generation, editing existing tracks, transforming vocals to background accompaniment, and stylistic personalization using low-rank adaptation from just a few example songs.

MiniMax-01 is the official repository for two flagship models: MiniMax-Text-01, a long-context language model, and MiniMax-VL-01, a vision-language model built on top of it. MiniMax-Text-01 uses a hybrid attention architecture that blends Lightning Attention, standard softmax attention, and Mixture-of-Experts (MoE) routing to achieve both high throughput and long-context reasoning. It has 456 billion total parameters with 45.9 billion activated per token and is trained with advanced parallel...

Chinese-LLaMA-Alpaca-3 is an open-source project that provides Mandarin-focused large language models based on Meta’s LLaMA-3 architecture, with both foundational and instruction-tuned variants to support high-quality Chinese natural language understanding and generation. It extends the original LLaMA models with expanded Chinese vocabularies and additional pretraining on Chinese corpora to improve semantic encoding and decoding specifically for Chinese text. Alongside the base models, the project also releases Chinese Alpaca models that are fine-tuned on instruction datasets so they behave more like conversational and instruction-following AI assistants. It includes scripts and tooling that let researchers or developers run training, fine-tuning, quantization, and deployment on local machines (CPU or GPU), making experimentation and testing accessible without requiring large clusters.

Bert-VITS2 is a neural text-to-speech project that combines a VITS2 backbone with a multilingual BERT front-end to produce high-quality speech in multiple languages. The core idea is to use BERT-style contextual embeddings for text encoding while relying on a refined VITS2 architecture for acoustic generation and vocoding. The repository includes everything needed to train, fine-tune, and run the model, from configuration files to preprocessing scripts, spectrogram utilities, and training entrypoints for multi-GPU and multi-node setups. It provides emotional modeling through “emo embeddings,” allowing voices to be conditioned on different affective states during synthesis. ...

“Llama” is the repository from Meta (formerly Facebook/Meta Research) containing the inference code for LLaMA (Large Language Model Meta AI) models. It provides utilities to load pre-trained LLaMA model weights, run inference (text generation, chat, completions), and work with tokenizers. Tokenizer utilities, download scripts, shell helpers to fetch model weights with correct licensing/permissions. Includes example scripts for chat completions and text completions to show how to call the...

...The main idea was to retain just enough code to allow training a simple diffusion model and generating samples, remove image-related terms, and make it easier to use. To train a model, run scripts/train.sh. By default, this will train a model on the simple corpus. However, you can change this to any text file using the --train_data argument. Note that you may have to increase the sequence length (--seq_len) if your corpus is longer than the simple corpus. The other default arguments are set to match the best setting I found for the simple corpus.