Hellisotherpeople / llm_steer-oobaboogaLinks
Steer LLM outputs towards a certain topic/subject and enhance response capabilities using activation engineering by adding steering vectors, now in oobabooga text generation webui!
☆43Updated last year
Alternatives and similar repositories for llm_steer-oobabooga
Users that are interested in llm_steer-oobabooga are comparing it to the libraries listed below
Sorting:
- ☆27Updated last year
- Experimental sampler to make LLMs more creative☆31Updated 2 years ago
- The Benefits of a Concise Chain of Thought on Problem Solving in Large Language Models☆22Updated 9 months ago
- ☆66Updated last year
- Experimental LLM Inference UX to aid in creative writing☆120Updated 8 months ago
- "a towel is about the most massively useful thing an interstellar AI hitchhiker can have"☆48Updated 10 months ago
- An OpenAI API compatible LLM inference server based on ExLlamaV2.☆25Updated last year
- ☆23Updated last year
- Low-Rank adapter extraction for fine-tuned transformers models☆175Updated last year
- entropix style sampling + GUI☆27Updated 9 months ago
- Let's create synthetic textbooks together :)☆75Updated last year
- High level library for batched embeddings generation, blazingly-fast web-based RAG and quantized indexes processing ⚡☆67Updated 9 months ago
- An unsupervised model merging algorithm for Transformers-based language models.☆106Updated last year
- run ollama & gguf easily with a single command☆52Updated last year
- GPT-2 small trained on phi-like data☆67Updated last year
- An easy-to-understand framework for LLM samplers that rewind and revise generated tokens☆146Updated 6 months ago
- ☆15Updated last year
- Modified Beam Search with periodical restart☆12Updated 11 months ago
- Simple LLM inference server☆20Updated last year
- ☆50Updated last year
- Local LLM inference & management server with built-in OpenAI API☆31Updated last year
- Python package wrapping llama.cpp for on-device LLM inference☆84Updated last month
- ☆59Updated last month
- Transplants vocabulary between language models, enabling the creation of draft models for speculative decoding WITHOUT retraining.☆42Updated last month
- LLM backed Fantasy Tribe Game☆19Updated 9 months ago
- ☆116Updated 8 months ago
- A public implementation of the ReLoRA pretraining method, built on Lightning-AI's Pytorch Lightning suite.☆34Updated last year
- ☆49Updated last year
- Easy to use, High Performant Knowledge Distillation for LLMs☆92Updated 3 months ago
- SLOP Detector and analyzer based on dictionary for shareGPT JSON and text☆72Updated 9 months ago