mesolitica / multimodal-LLM
Multi-Modal Language Modeling with Image, Audio and Text Integration, included multi-images and multi-audio in a single multiturn.
β13Updated 8 months ago
Related projects β
Alternatives and complementary repositories for multimodal-LLM
- DPO, but faster πβ21Updated 2 weeks ago
- A public implementation of the ReLoRA pretraining method, built on Lightning-AI's Pytorch Lightning suite.β33Updated 8 months ago
- β26Updated 4 months ago
- Learning to Retrieve by Trying - Source code for Grounding by Trying: LLMs with Reinforcement Learning-Enhanced Retrievalβ24Updated 2 weeks ago
- β21Updated last week
- β57Updated last month
- SCREWS: A Modular Framework for Reasoning with Revisionsβ26Updated last year
- Code for NeurIPS LLM Efficiency Challengeβ53Updated 7 months ago
- QLoRA for Masked Language Modelingβ20Updated last year
- Using multiple LLMs for ensemble Forecastingβ16Updated 9 months ago
- β40Updated last week
- Collection of autoregressive model implementationβ66Updated last week
- Code for Paper: Harnessing Webpage Uis For Text Rich Visual Understandingβ37Updated 3 weeks ago
- Code for the examples presented in the talk "Training a Llama in your backyard: fine-tuning very large models on consumer hardware" givenβ¦β14Updated last year
- Implementation of the Mamba SSM with hf_integration.β55Updated 2 months ago
- β33Updated 6 months ago
- Fast approximate inference on a single GPU with sparsity aware offloadingβ38Updated 10 months ago
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignmentβ46Updated 2 months ago
- NeurIPS 2023 - Cappy: Outperforming and Boosting Large Multi-Task LMs with a Small Scorerβ36Updated 7 months ago
- A list of language models with permissive licenses such as MIT or Apache 2.0β22Updated last week
- Official repository for RAGVIZ: Diagnose and Visualize Retrieval-Augmented Generationβ21Updated this week
- Repository containing the SPIN experiments on the DIBT 10k ranked promptsβ22Updated 8 months ago
- β24Updated last year
- β35Updated last year
- Index of URLs to pdf files all over the internet and scriptsβ21Updated last year
- β20Updated 9 months ago
- Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limitβ63Updated last year
- Tools for merging pretrained large language models.β19Updated 5 months ago
- Finetune any model on HF in less than 30 secondsβ56Updated last week
- QAmeleon introduces synthetic multilingual QA data using PaLM, a 540B large language model. This dataset was generated by prompt tuning Pβ¦β34Updated last year