llama-securelm
llama-securelm заставляет Llama-3.1-8B-Instruct отказываться от гораздо большего количества атак с помощью джейлбрейка (до 49,5 баллов при задержанных атаках),...
llama-securelm заставляет Llama-3.1-8B-Instruct отказываться от гораздо большего количества атак с помощью джейлбрейка (до 49,5 баллов при задержанных атаках),...
Fully uncensored, refusal-free Llama 3.2 1B that runs on a CPU or a tiny GPU — with its...
A LoRA adapter that turns openai/gpt-oss-120b into a quantitative trading analyst: it audits backtests for bias, extracts implementable...
— Developed by: Harsha Deep Joga — Funded by [optional]: Self Project — Shared by [optional]: HarshaDeep2006 —...
Finance SLM Router is a QLoRA adapter built on top of Qwen3-8B for finance intent routing and structured...
This is a Natural Language Autoencoder (Anthropic, 2026) trained for Qwen/Qwen3.6-27B on layer-42 residual-stream activations using easyNLA. This...
> This is an independent, unofficial project. It is not affiliated with, endorsed by, or > produced by...
This model is a QLoRA fine-tuned version of meta-llama/Llama-3.2-1B specialized for robot task planning in construction environments. The...
Athenas-Symbiote-9B is a large language model (LLM) fine-tuned for advanced reasoning, complex text interpretation, and legal/academic domain expertise,...
The first open-source compression model trained specifically for coding agents. Compresses individual long files to as little as...