abetlen / program-constrained-language-model-samplingLinks
☆35Updated 2 years ago
Alternatives and similar repositories for program-constrained-language-model-sampling
Users that are interested in program-constrained-language-model-sampling are comparing it to the libraries listed below
Sorting:
- Full finetuning of large language models without large memory requirements☆94Updated 3 months ago
- an implementation of Self-Extend, to expand the context window via grouped attention☆119Updated 2 years ago
- ☆50Updated 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
- Reimplementation of the task generation part from the Alpaca paper☆119Updated 2 years ago
- ☆40Updated 2 years ago
- Mixing Language Models with Self-Verification and Meta-Verification☆111Updated last year
- Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limit☆63Updated 2 years ago
- ☆45Updated 2 years ago
- MiniHF is an inference, human preference data collection, and fine-tuning tool for local language models. It is intended to help the user…☆183Updated 2 months ago
- Comprehensive analysis of difference in performance of QLora, Lora, and Full Finetunes.☆83Updated 2 years ago
- Zeus LLM Trainer is a rewrite of Stanford Alpaca aiming to be the trainer for all Large Language Models☆70Updated 2 years ago
- utilities for loading and running text embeddings with onnx☆45Updated 5 months ago
- Chat Markup Language conversation library☆55Updated 2 years ago
- [WIP] Transformer to embed Danbooru labelsets☆13Updated last year
- QLoRA: Efficient Finetuning of Quantized LLMs☆79Updated last year
- Use context-free grammars with an LLM☆175Updated last year
- Multi-Domain Expert Learning☆67Updated last year
- ☆22Updated 2 years ago
- ReLM is a Regular Expression engine for Language Models☆107Updated 2 years ago
- Repository containing the SPIN experiments on the DIBT 10k ranked prompts☆23Updated last year
- Just a bunch of benchmark logs for different LLMs☆119Updated last year
- ☆105Updated last year
- Command-line script for inferencing from models such as MPT-7B-Chat☆100Updated 2 years ago
- 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
- ☆62Updated 2 years ago
- ☆74Updated 2 years ago
- ☆23Updated last year
- ☆63Updated last year