epoch-research / training-cost-trendsLinks
☆18Updated 2 weeks ago
Alternatives and similar repositories for training-cost-trends
Users that are interested in training-cost-trends are comparing it to the libraries listed below
Sorting:
- PyTorch Implementation of the paper "MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training"☆24Updated 2 weeks ago
- ☆23Updated 3 months ago
- Open sourced predictions, execution logs, trajectories, and results from model inference + evaluation runs on the SWE-bench task.☆15Updated 11 months ago
- Implementation of SelfExtend from the paper "LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning" from Pytorch and Zeta☆13Updated 9 months ago
- CLaMR: Contextualized Late-Interaction for Multimodal Content Retrieval☆18Updated last month
- Code for paper: "Privately generating tabular data using language models".☆15Updated 2 years ago
- A sample pattern for running CI tests on Modal☆18Updated 4 months ago
- ☆54Updated 9 months ago
- Official repository for "BLEUBERI: BLEU is a surprisingly effective reward for instruction following"☆25Updated 2 months ago
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆55Updated 6 months ago
- Exploration using DSPy to optimize modules to maximize performance on the OpenToM dataset☆18Updated last year
- Lottery Ticket Adaptation☆39Updated 9 months ago
- This library supports evaluating disparities in generated image quality, diversity, and consistency between geographic regions.☆20Updated last year
- NeurIPS 2023 - Cappy: Outperforming and Boosting Large Multi-Task LMs with a Small Scorer☆43Updated last year
- ☆20Updated last year
- Experiments to assess SPADE on different LLM pipelines.☆17Updated last year
- Zeus LLM Trainer is a rewrite of Stanford Alpaca aiming to be the trainer for all Large Language Models☆70Updated 2 years ago
- code for training and using chess embeddings models☆12Updated last year
- ☆39Updated last year
- Tools for merging pretrained large language models.☆19Updated last year
- Visual RAG using less than 300 lines of code.☆28Updated last year
- Matrix (Multi-Agent daTa geneRation Infra and eXperimentation framework) is a versatile engine for multi-agent conversational data genera…☆88Updated this week
- ☆49Updated 11 months ago
- ☆24Updated 3 months ago
- ReBase: Training Task Experts through Retrieval Based Distillation☆29Updated 6 months ago
- Using multiple LLMs for ensemble Forecasting☆16Updated last year
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment☆60Updated 11 months ago
- MPI Code Generation through Domain-Specific Language Models☆14Updated 9 months ago
- QAlign is a new test-time alignment approach that improves language model performance by using Markov chain Monte Carlo methods.☆22Updated last week
- OLMost every training recipe you need to perform data interventions with the OLMo family of models.☆43Updated this week