Skip to content
View dsadawq3's full-sized avatar
👾
👾
1 follower · 1 following

Achievements

Achievement: Starstruck

Achievements

Achievement: Starstruck

Block or report dsadawq3

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. Markdown is supported. 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
dsadawq3/README.md

dsadawq3 — quantization notes (F-Labs)

I work on post-training INT4 quantization of LLMs (group-wise INT4, SRC, DV-SSQ, KV-BSS).

Models: https://huggingface.co/F-Labs | Related: QuaRot, SpinQuant, GPTQ, AWQ, ZeroQuant-V2, LoRC, LLM.int8(), SpQR.

Pinned Loading

  1. ai-rhamz ai-rhamz Public

    Forked from anomalyco/opencode

    AI RHAMZ: Unchained OpenCode v2.0.16 fork for offensive security, bug bounty, reverse engineering & low-level coding

    TypeScript 18 3

  2. dzeta-agi dzeta-agi Public

    Dzeta — Riemann Spectral Oscillator Field: AGI через чистую математику. CPU-first, zero dependencies, C++20.

    C++ 8

  3. DynamicTune DynamicTune Public

    DynamicTune: Cross-model hidden trajectory transport and direct MLP weight surgery across dimensions (Qwen3.5 4B -> 0.8B on 8GB RX 580)

    Python 9 2