jukofyork / control-vectorsLinks
Genertaes control vectors for use with llama.cpp in GGUF format.
☆36Updated 9 months ago
Alternatives and similar repositories for control-vectors
Users that are interested in control-vectors are comparing it to the libraries listed below
Sorting:
- An unsupervised model merging algorithm for Transformers-based language models.☆108Updated last year
- Low-Rank adapter extraction for fine-tuned transformers models☆180Updated last year
- A pipeline parallel training script for LLMs.☆164Updated 7 months ago
- ☆27Updated 2 years ago
- Transplants vocabulary between language models, enabling the creation of draft models for speculative decoding WITHOUT retraining.☆47Updated last month
- Model REVOLVER, a human in the loop model mixing system.☆33Updated 2 years ago
- Train Llama Loras Easily☆31Updated 2 years ago
- Steer LLM outputs towards a certain topic/subject and enhance response capabilities using activation engineering by adding steering vecto…☆43Updated last year
- LLM backed Fantasy Tribe Game☆19Updated last year
- 5X faster 60% less memory QLoRA finetuning☆21Updated last year
- Deploy Apollo HF space locally☆40Updated last year
- Load multiple LoRA modules simultaneously and automatically switch the appropriate combination of LoRA modules to generate the best answe…☆157Updated last year
- Using fourier interpolation to merge large language models☆11Updated 11 months ago
- SLOP Detector and analyzer based on dictionary for shareGPT JSON and text☆79Updated 2 weeks ago
- Experimental LLM Inference UX to aid in creative writing☆127Updated last year
- Experimental sampler to make LLMs more creative☆31Updated 2 years ago
- Easily view and modify JSON datasets for large language models☆85Updated 7 months ago
- Image Diffusion block merging technique applied to transformers based Language Models.☆56Updated 2 years ago
- ☆136Updated last year
- ☆26Updated 8 months ago
- An easy-to-understand framework for LLM samplers that rewind and revise generated tokens☆150Updated 10 months ago
- ☆51Updated last year
- klmbr - a prompt pre-processing technique to break through the barrier of entropy while generating text with LLMs☆86Updated last year
- Landmark Attention: Random-Access Infinite Context Length for Transformers QLoRA☆124Updated 2 years ago
- ☆68Updated last year
- GPT-2 small trained on phi-like data☆67Updated last year
- ☆55Updated 3 months ago
- Text WebUI extension to add clever Notebooks to Chat mode☆144Updated 4 months ago
- Video+code lecture on building nanoGPT from scratch☆68Updated last year
- Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"☆82Updated last year