bold84 / cot_proxy
A lightweight proxy for filtering `<think>` tags from any OpenAI-compatible API endpoint. Designed for chain-of-thought language models that expose their reasoning process through think tags.
β36Updated last month
Alternatives and similar repositories for cot_proxy:
Users that are interested in cot_proxy are comparing it to the libraries listed below
- Let's create synthetic textbooks together :)β74Updated last year
- π₯ LitLytics - an affordable, simple analytics platform that leverages LLMs to automate data analysisβ97Updated 4 months ago
- Scripts to create your own moe models using mlxβ89Updated last year
- β91Updated 2 months ago
- klmbr - a prompt pre-processing technique to break through the barrier of entropy while generating text with LLMsβ71Updated 6 months ago
- Use smol agents to do research and then update csv coumns with its findings.β37Updated last month
- Distributed Inference for mlx LLmβ87Updated 7 months ago
- Local LLM inference & management server with built-in OpenAI APIβ31Updated 11 months ago
- Gradio based tool to run opensource LLM models directly from Huggingfaceβ91Updated 9 months ago
- Dagger functions to import Hugging Face GGUF models into a local ollama instance and optionally push them to ollama.com.β115Updated 10 months ago
- Simple Graph Memory for AI applicationsβ84Updated 8 months ago
- β39Updated last year
- Experimental LLM Inference UX to aid in creative writingβ114Updated 3 months ago
- GRDN.AI app for garden optimizationβ70Updated last year
- auto fine tune of models with synthetic dataβ75Updated last year
- Synthify: Seamlessly generate ai datasets with a no-code UI | https://synthify.toolstack.runβ48Updated last month
- β111Updated 3 months ago
- A python package for serving LLM on OpenAI-compatible API endpoints with prompt caching using MLX.β73Updated 3 months ago
- Easily view and modify JSON datasets for large language modelsβ71Updated 3 weeks ago
- Testing LLM reasoning abilities with family relationship quizzes.β62Updated last month
- GPT-4 Level Conversational QA Trained In a Few Hoursβ59Updated 7 months ago
- A guidance compatibility layer for llama-cpp-pythonβ34Updated last year
- Complex RAG backendβ28Updated last year
- A Python library to orchestrate LLMs in a neural network-inspired structureβ46Updated 5 months ago
- β125Updated this week
- β29Updated 3 months ago
- Serving LLMs in the HF-Transformers format via a PyFlask APIβ71Updated 6 months ago
- β53Updated last year
- Using modal.com to process FineWeb-edu dataβ20Updated 3 weeks ago
- Run multiple resource-heavy Large Models (LM) on the same machine with limited amount of VRAM/other resources by exposing them on differeβ¦β55Updated last month