AUGMXNT / deccp
Evaling and unaligning Chinese LLM censorship
☆60Updated 6 months ago
Alternatives and similar repositories for deccp:
Users that are interested in deccp are comparing it to the libraries listed below
- Make abliterated models with transformers, easy and fast☆64Updated last week
- automatically quant GGUF models☆164Updated last week
- LLM inference in C/C++☆67Updated last week
- Public Goods Game (PGG) Benchmark: Contribute & Punish is a multi-agent benchmark that tests cooperative and self-interested strategies a…☆31Updated last week
- A benchmark for emotional intelligence in large language models☆253Updated 8 months ago
- An unsupervised model merging algorithm for Transformers-based language models.☆104Updated 11 months ago
- ☆81Updated 3 weeks ago
- idea: https://github.com/nyxkrage/ebook-groupchat/☆86Updated 7 months ago
- Glyphs, acting as collaboratively defined symbols linking related concepts, add a layer of multidimensional semantic richness to user-AI …☆49Updated last month
- Low-Rank adapter extraction for fine-tuned transformers models☆171Updated 11 months ago
- ☆152Updated 8 months ago
- ☆81Updated last month
- ☆53Updated 10 months ago
- ☆74Updated last year
- A pipeline parallel training script for LLMs.☆136Updated last week
- ☆59Updated 11 months ago
- Self-hosted LLM chatbot arena, with yourself as the only judge☆38Updated last year
- LLM based agents with proactive interactions, long-term memory, external tool integration, and local deployment capabilities.☆99Updated last week
- Load multiple LoRA modules simultaneously and automatically switch the appropriate combination of LoRA modules to generate the best answe…☆150Updated last year
- ☆83Updated 3 months ago
- RWKV infctx trainer, for training arbitary context sizes, to 10k and beyond!☆148Updated 7 months ago
- DRT-o1: Optimized Deep Reasoning Translation via Long Chain-of-Thought☆211Updated 3 months ago
- A benchmark for role-playing language models☆90Updated 2 weeks ago
- A pipeline for LLM knowledge distillation☆99Updated this week
- ☆24Updated 2 months ago
- This is the Mixture-of-Agents (MoA) concept, adapted from the original work by TogetherAI. My version is tailored for local model usage a…☆113Updated 9 months ago
- Free Search is a wrapper on top of publicly available SearXNG instances to give free internet access as a rest API.☆147Updated this week
- Easy to use, High Performant Knowledge Distillation for LLMs☆55Updated this week
- entropix style sampling + GUI☆25Updated 5 months ago
- Formatron empowers everyone to control the format of language models' output with minimal overhead.☆190Updated 2 months ago