bold84 / cot_proxyLinks
Smart proxy for LLM APIs that enables model-specific parameter control, automatic mode switching (like Qwen3's /think and /no_think), and <think> tag filtering. Perfect for using advanced models with apps that lack parameter customization.
☆47Updated 2 weeks ago
Alternatives and similar repositories for cot_proxy
Users that are interested in cot_proxy are comparing it to the libraries listed below
Sorting:
- klmbr - a prompt pre-processing technique to break through the barrier of entropy while generating text with LLMs☆75Updated 8 months ago
- Serving LLMs in the HF-Transformers format via a PyFlask API☆71Updated 8 months ago
- ☆24Updated 4 months ago
- Glyphs, acting as collaboratively defined symbols linking related concepts, add a layer of multidimensional semantic richness to user-AI …☆49Updated 3 months ago
- Run multiple resource-heavy Large Models (LM) on the same machine with limited amount of VRAM/other resources by exposing them on differe…☆65Updated this week
- A python package for serving LLM on OpenAI-compatible API endpoints with prompt caching using MLX.☆84Updated 5 months ago
- ☆91Updated 3 weeks ago
- Dagger functions to import Hugging Face GGUF models into a local ollama instance and optionally push them to ollama.com.☆115Updated last year
- ☆66Updated last year
- Local LLM inference & management server with built-in OpenAI API☆31Updated last year
- Convert URLs into LLM-friendly markdown chunks☆64Updated 9 months ago
- The DPAB-α Benchmark☆24Updated 4 months ago
- GRDN.AI app for garden optimization☆70Updated last year
- run ollama & gguf easily with a single command☆50Updated last year
- ☆75Updated 2 weeks ago
- ☆41Updated 2 months ago
- Demo of an "always-on" AI assistant.☆24Updated last year
- ☆90Updated 5 months ago
- ☆17Updated 5 months ago
- Mistral7B playing DOOM☆28Updated last year
- Create text chunks which end at natural stopping points without using a tokenizer☆25Updated 2 months ago
- Testing LLM reasoning abilities with lineage relationship quizzes.☆27Updated 2 months ago
- Use smol agents to do research and then update csv coumns with its findings.☆40Updated 4 months ago
- A guidance compatibility layer for llama-cpp-python☆34Updated last year
- One Line To Build Zero-Data Classifiers in Minutes☆55Updated 8 months ago
- Official homepage for "Self-Harmonized Chain of Thought" (NAACL 2025)☆90Updated 4 months ago
- Guaranteed Structured Output from any Language Model via Hierarchical State Machines☆134Updated this week
- Distributed Inference for mlx LLm☆92Updated 10 months ago
- Benchmark that evaluates LLMs using 651 NYT Connections puzzles extended with extra trick words☆93Updated this week
- The original BabyAGI, updated with LiteLLM and no vector database reliance (csv instead)☆21Updated 8 months ago