babylm / baseline-pretrainingLinks
Code for pre-training BabyLM baseline models.
☆16Updated 2 years ago
Alternatives and similar repositories for baseline-pretraining
Users that are interested in baseline-pretraining are comparing it to the libraries listed below
Sorting:
- Mamba training library developed by kotoba technologies☆71Updated 2 years ago
- ☆16Updated last year
- Checkpointable dataset utilities for foundation model training☆32Updated 2 years ago
- CycleQD is a framework for parameter space model merging.☆48Updated last year
- This is a new metric that can be used to evaluate faithfulness of text generated by LLMs. The work behind this repository can be found he…☆31Updated 2 years ago
- Ongoing research training Mixture of Expert models.☆21Updated last year
- ☆59Updated last year
- Support Continual pre-training & Instruction Tuning forked from llama-recipes☆34Updated last year
- Example of using Epochraft to train HuggingFace transformers models with PyTorch FSDP☆11Updated 2 years ago
- Experiments for efforts to train a new and improved t5☆76Updated last year
- ☆77Updated last year
- Code repository for the c-BTM paper☆108Updated 2 years ago
- Code for the note "NF4 Isn't Information Theoretically Optimal (and that's Good)☆21Updated 2 years ago
- Token Omission Via Attention☆128Updated last year
- Japanese LLaMa experiment☆54Updated last month
- Official repository for the paper "Approximating Two-Layer Feedforward Networks for Efficient Transformers"☆38Updated 8 months ago
- ☆53Updated 2 years ago
- An unofficial implementation of the Infini-gram model proposed by Liu et al. (2024)☆33Updated last year
- Code for the examples presented in the talk "Training a Llama in your backyard: fine-tuning very large models on consumer hardware" given…☆15Updated 2 years ago
- Swallowプロジェクト 事後学習済み大規模言語モデル 評価フレームワーク☆24Updated 3 months ago
- ☆42Updated last year
- Shaping capabilities with token-level pretraining data filtering☆75Updated 2 weeks ago
- ☆53Updated 2 years ago
- Train, tune, and infer Bamba model☆137Updated 8 months ago
- [NeurIPS 2023] Sparse Modular Activation for Efficient Sequence Modeling☆40Updated 2 years ago
- ☆33Updated last year
- Minimum Description Length probing for neural network representations☆20Updated last year
- The GeoV model is a large langauge model designed by Georges Harik and uses Rotary Positional Embeddings with Relative distances (RoPER).…☆121Updated 2 years ago
- ☆24Updated last year
- Code for Discovering Preference Optimization Algorithms with and for Large Language Models☆65Updated last year