lechmazur / writing
This benchmark tests how well LLMs incorporate a set of 10 mandatory story elements (characters, objects, core concepts, attributes, motivations, etc.) in a short creative story
☆135Updated last week
Alternatives and similar repositories for writing:
Users that are interested in writing are comparing it to the libraries listed below
- An easy-to-understand framework for LLM samplers that rewind and revise generated tokens☆137Updated last month
- An unsupervised model merging algorithm for Transformers-based language models.☆106Updated 10 months ago
- Hallucinations (Confabulations) Document-Based Benchmark for RAG. Includes human-verified questions and answers.☆116Updated this week
- ☆273Updated last month
- A pipeline parallel training script for LLMs.☆129Updated last week
- ☆152Updated 8 months ago
- LLM based agents with proactive interactions, long-term memory, external tool integration, and local deployment capabilities.☆99Updated this week
- A benchmark for emotional intelligence in large language models☆249Updated 7 months ago
- klmbr - a prompt pre-processing technique to break through the barrier of entropy while generating text with LLMs☆71Updated 6 months ago
- Low-Rank adapter extraction for fine-tuned transformers models☆171Updated 10 months ago
- ☆117Updated 7 months ago
- Easily view and modify JSON datasets for large language models☆71Updated 2 weeks ago
- Generate Synthetic Data Using OpenAI, MistralAI or AnthropicAI☆224Updated 10 months ago
- SLOP Detector and analyzer based on dictionary for shareGPT JSON and text☆64Updated 4 months ago
- ☆111Updated 3 months ago
- Dynamically structure language models to produce outputs that adhere to specific requirements without sacrificing their creative capabili…☆118Updated last week
- idea: https://github.com/nyxkrage/ebook-groupchat/☆86Updated 7 months ago
- A user interface for DSPy☆140Updated 5 months ago
- an implementation of Self-Extend, to expand the context window via grouped attention☆118Updated last year
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆168Updated 2 months ago
- A comprehensive repository of reasoning tasks for LLMs (and beyond)☆423Updated 5 months ago
- All the world is a play, we are but actors in it.☆47Updated this week
- Formatron empowers everyone to control the format of language models' output with minimal overhead.☆189Updated 2 months ago
- Sandboxed code execution for AI agents, locally or on the cloud. Massively parallel, easy to extend. Powering SWE-agent and more.☆122Updated this week
- Load multiple LoRA modules simultaneously and automatically switch the appropriate combination of LoRA modules to generate the best answe…☆150Updated last year