Rajdeep Borgohain's repositories
Llama-2-7b-chat
Llama 2 7B Chat is the smallest chat model in the Llama 2 family of large language models developed by Meta AI. This model has 7 billion parameters and was pretrained on 2 trillion tokens of data from publicly available sources. It has been fine-tuned on over one million human-annotated instruction datasets
stable-diffusion-2-1
This stable-diffusion-2-1 model is fine-tuned from stable-diffusion-2 (768-v-ema.ckpt) with an additional 55k steps on the same dataset (with punsafe=0.1), and then fine-tuned for another 155k extra steps with punsafe=0.98.
stable-diffusion-xl
SDXL consists of an ensemble of experts pipeline for latent diffusion: In a first step, the base model is used to generate (noisy) latents, which are then further processed with a refinement model (available here: https://huggingface.co/stabilityai/stable-diffusion-xl-refiner-1.0/) specialized for the final denoising steps.
stable-diffusion-xl-turbo
SDXL-Turbo, developed by Stability AI, is a fast generative text-to-image model capable creating very realistic images from written prompts in just few steps.
Llama-3
Llama 3 is an auto-regressive language model, leveraging a refined transformer architecture.It incorporate supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to ensure alignment with human preferences.
vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
Gemma-2B-it
Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. They are text-to-text, decoder-only large language models, available in English, with open weights, pre-trained variants, and instruction-tuned variants.
pyannote-speaker-diarization-3.1
Pyannote/speaker-diarization-3.1 is an open-source toolkit written in Python for speaker diarization, which is the task of determining "who spoke when" in an audio recording. It is based on the PyTorch machine learning framework and provides a set of trainable end-to-end neural building blocks that can be combined and jointly optimized.
TinyLlama-1.1B-Chat-v1.0
The TinyLlama project aims to train a compact 1.1B model on 3 trillion tokens. It shares architecture and tokenizer with Llama 2, making it compatible with many existing projects. With only 1.1B parameters, it's suitable for applications with limited computational and memory resources.
Phi-3
Phi-2 is a Transformer with 2.7 billion parameters. It was trained using the same data sources as Phi-1.5, augmented with a new data source that consists of various NLP synthetic texts and filtered websites (for safety and educational value).
ai-infra-landscape
This is a landscape of the infrastructure that powers the generative AI ecosystem
whisper-large-v3-1
Whisper is a pre-trained model for automatic speech recognition (ASR) and speech translation. Trained on 680k hours of labelled data, Whisper models demonstrate a strong ability to generalise to many datasets and domains without the need for fine-tuning.
bark
Bark is a transformer-based text-to-audio model created by Suno. Bark can generate highly realistic, multilingual speech as well as other audio - including music, background noise and simple sound effects. The model can also produce nonverbal communications like laughing, sighing and crying.
stable-video-diffusion
(SVD) Image-to-Video is a latent diffusion model trained to generate short video clips from an image conditioning. This model was trained to generate 25 frames at resolution 576x1024 given a context frame of the same size, finetuned from SVD Image-to-Video [14 frames]. We also finetune the widely used f8-decoder for temporal consistency.
Llama-2-13b-hf
Llama 2 is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. This is the repository for the 7B fine-tuned model, optimized for dialogue use cases and converted for the Hugging Face Transformers format. Links to other models can be found in the index at the bottom.
mistral-7B
The Mistral-7B-v0.1 Large Language Model (LLM) is a pretrained generative text model with 7 billion parameters. Mistral-7B-v0.1 outperforms Llama 2 13B on all benchmarks we tested.
Mixtral-8x7B-v0.1
The Mixtral-8x7B Large Language Model (LLM) is a pretrained generative Sparse Mixture of Experts. The Mistral-8x7B outperforms Llama 2 70B on most benchmarks we tested.
sentence-embedings
This is a sentence-transformers model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
OpenHermes-2.5-Mistral-7B
OpenHermes 2.5 Mistral 7B is an advanced version of the OpenHermes 2 model, This enhancement has led to improvements in several non-code benchmarks such as TruthfulQA, AGIEval, and the GPT4All suite.