Skip to content
View Amerisium's full-sized avatar

Block or report Amerisium

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Showing results

Training-free language model modification: Remove censorship, suppress slop, reduce sycophancy, and more

Python 40,735 4,682 Updated Nov 14, 2026

Self-hosted metasearch and grounding engine for AI agents, based on SearXNG. Rust, JSON API, optional page text.

Rust 978 82 Updated Nov 16, 2026

Find, rank and steer MLP neurons of GGUF models on llama.cpp; export control vectors; 3D web UI and MCP server

Python 104 9 Updated Nov 15, 2026

ComfyUI node that feeds a reference image through the Qwen3.5-9B vision tower and injects its embeddings into the text prompt (MOSS-Image conditioning)

Python 50 9 Updated Oct 21, 2026

llama.cpp on a jailbroken PS5: run any GGUF model natively on the console, starting with Qwen 3.8

C++ 851 77 Updated Nov 16, 2026

Japanese character-persona LoRA experiments on small LLMs (Qwen3.5 / Spark-X2.5): does the model break, and does the persona stay stable?

Python 3 Updated Nov 3, 2026

A server for streaming tweets by emulating browser WebPush.

Rust 862 34 Updated Mar 5, 2026

歌詞から文字PVを自動で組み立てるブラウザアプリ

HTML 2,289 305 Updated Nov 10, 2026

Japanese continual training of CuteTTS (~230M params). Reading CER 30.94% -> 7.12%, against 5.59% for real human recordings measured the same way. Adds the training code upstream does not ship, plu…

Python 14 Updated Sep 26, 2026

Serve the experimental DiffusionGemma-Jev diffusion model on Cloud Run GPUs (vLLM, RTX PRO 6000), with demo apps and published benchmarks.

HTML 589 39 Updated Oct 14, 2026
Python 61 4 Updated Sep 19, 2026

Neural latent upscaler for Minimax H3 (24ch). Bypasses costly 5B-param VAE decode/encode. Upscale low-res latents directly, then refine. Accelerates high-res video gen, outperforms naive interp.

Python 844 62 Updated Nov 10, 2026

Extending Late-Layer KV Approximation to Mixture-of-Experts Models via Co-Routed Low-Rank Projectors

Python 4 Updated Sep 14, 2026

LLKVApprox experiments on Gemma 4 12B: training code, reproducibility tools, and speed-quality evaluation.

Python 2 Updated Sep 12, 2026

LLM inference in C/C++

C++ 1 Updated Aug 21, 2025

Resource-aware open research on neural circuits, bodies, and simulated organisms. Starting with Drosophila.

Python 26 1 Updated Oct 13, 2026

HRFFA: High-Angle Robust Fast Face Alignment. Whole-head face alignment dataset & training pipeline.

Python 206 29 Updated Oct 9, 2026

Antidoom generates and trains targeted preference data for reducing model repetition loops (doom loops).

Python 411 37 Updated Nov 16, 2026

for wan full finetuning

Python 1 Updated May 17, 2026

LLM inference in C/C++

C++ 56 14 Updated Nov 16, 2026

Text to image generation for Japanese-like Images

Python 4 Updated May 9, 2026

SPECA: Specification-to-Checklist Agentic Auditing Framework

Python 463 32 Updated Oct 29, 2026

high-performance linear attention kernel library built on TileLang

Python 758 89 Updated Oct 30, 2026

The most powerful and modular stable diffusion GUI, api and backend with a graph/nodes interface. Now ZLUDA enhanced for better AMD GPU performance.

Python 997 84 Updated Nov 15, 2026

FT-LLM2026で開発した日本語SpeechLLMの学習コード

Python 13 1 Updated Apr 5, 2026

1 script run the vphone

Shell 8,133 1,328 Updated Aug 27, 2026

An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.

Rust 194,765 107,273 Updated Nov 10, 2026

TurboMLX v0.1 Research Preview public source tree for Qwen3.5-focused MLX TurboQuant experiments.

Python 120 6 Updated May 16, 2026
Next