leloykun / mmsgLinks
Generate interleaved text and image content in a structured format you can directly pass to downstream APIs.
☆29Updated last year
Alternatives and similar repositories for mmsg
Users that are interested in mmsg are comparing it to the libraries listed below
Sorting:
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment☆60Updated last year
- ☆39Updated last year
- ☆34Updated last year
- Repository containing the SPIN experiments on the DIBT 10k ranked prompts☆24Updated last year
- Code, results and other artifacts from the paper introducing the WildChat-50m dataset and the Re-Wild model family.☆31Updated 7 months ago
- Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limit☆62Updated 2 years ago
- ☆63Updated last year
- ☆86Updated last year
- A repository for research on medium sized language models.☆78Updated last year
- Experiments for efforts to train a new and improved t5☆75Updated last year
- Code for PHATGOOSE introduced in "Learning to Route Among Specialized Experts for Zero-Shot Generalization"☆90Updated last year
- Fork of Flame repo for training of some new stuff in development☆18Updated 3 weeks ago
- GoldFinch and other hybrid transformer components☆45Updated last year
- Training code for Sparse Autoencoders on Embedding models☆38Updated 8 months ago
- ☆50Updated last year
- A dashboard for exploring timm learning rate schedulers☆19Updated 11 months ago
- Training hybrid models for dummies.☆27Updated 2 weeks ago
- ☆55Updated 11 months ago
- Engineering the state of RNN language models (Mamba, RWKV, etc.)☆32Updated last year
- Triton Implementation of HyperAttention Algorithm☆48Updated last year
- Official Repository of Pretraining Without Attention (BiGS), BiGS is the first model to achieve BERT-level transfer learning on the GLUE …☆114Updated last year
- Mixture of A Million Experts☆48Updated last year
- Collection of autoregressive model implementation☆86Updated 6 months ago
- ☆24Updated 2 months ago
- ☆81Updated last year
- A public implementation of the ReLoRA pretraining method, built on Lightning-AI's Pytorch Lightning suite.☆35Updated last year
- ☆26Updated last year
- ☆21Updated 11 months ago
- Minimum Description Length probing for neural network representations☆20Updated 9 months ago
- [WIP] Transformer to embed Danbooru labelsets☆13Updated last year