euclaise / supertrainer2000Links
☆50Updated last year
Alternatives and similar repositories for supertrainer2000
Users that are interested in supertrainer2000 are comparing it to the libraries listed below
Sorting:
- Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limit☆63Updated 2 years ago
- Collection of autoregressive model implementation☆85Updated 8 months ago
- ☆82Updated last year
- Experiments for efforts to train a new and improved t5☆76Updated last year
- QLoRA with Enhanced Multi GPU Support☆37Updated 2 years ago
- Exploring finetuning public checkpoints on filter 8K sequences on Pile☆116Updated 2 years ago
- ☆53Updated last year
- ☆20Updated 2 years ago
- Fast, Modern, and Low Precision PyTorch Optimizers☆118Updated 3 months ago
- Full finetuning of large language models without large memory requirements☆94Updated 3 months ago
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training☆132Updated last year
- Code repository for the c-BTM paper☆108Updated 2 years ago
- Official repository for the paper "Approximating Two-Layer Feedforward Networks for Efficient Transformers"☆38Updated 6 months ago
- [WIP] Transformer to embed Danbooru labelsets☆13Updated last year
- RWKV-7: Surpassing GPT☆101Updated last year
- Repository containing the SPIN experiments on the DIBT 10k ranked prompts☆24Updated last year
- ☆39Updated last year
- ☆136Updated last year
- Train a SmolLM-style llm on fineweb-edu in JAX/Flax with an assortment of optimizers.☆18Updated 5 months ago
- An introduction to LLM Sampling☆79Updated last year
- Comprehensive analysis of difference in performance of QLora, Lora, and Full Finetunes.☆83Updated 2 years ago
- ☆34Updated last year
- an implementation of Self-Extend, to expand the context window via grouped attention☆119Updated last year
- A library for squeakily cleaning and filtering language datasets.☆49Updated 2 years ago
- ☆91Updated last year
- NanoGPT-speedrunning for the poor T4 enjoyers☆73Updated 8 months ago
- Scaling is a distributed training library and installable dependency designed to scale up neural networks, with a dedicated module for tr…☆66Updated last month
- Utilities for Training Very Large Models☆58Updated last year
- ☆21Updated last year
- ☆62Updated 2 years ago