Skip to content
View ictup's full-sized avatar

Highlights

  • Pro

Block or report ictup

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.

Please don't include any personal information such as legal names or email addresses. Maximum 250 characters, markdown supported. This note will be visible to only you.
Report abuse

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

Report abuse

Popular repositories Loading

  1. Enhancing-QA-Systems-through-Integrated-Reasoning-over-Knowledge-Bases-and-Large-Language-Models Enhancing-QA-Systems-through-Integrated-Reasoning-over-Knowledge-Bases-and-Large-Language-Models Public

    KG-RAG + ToT + multi-agent LLMs for evidence-grounded QA with Neo4j and fine-tuning; reproducible medical case study & evaluation.

    Python 4 1

  2. LLM-Chinese-Textual-Disambiguation LLM-Chinese-Textual-Disambiguation Public

    Uncovering the Fragility of Trustworthy LLMs through Chinese Textual Ambiguity

    Jupyter Notebook 3

  3. AI-Enabled-Robust-SVD-Operator-for-Wireless-Communication AI-Enabled-Robust-SVD-Operator-for-Wireless-Communication Public

    第四届“华为杯”无线通信算法大赛:LoMACS-SVDNet: PyTorch model for MIMO SVD (no QR/SVD/EVD), orthogonality via NOR, FFT gating, projected attention, structured pruning. Score 63 — 4th (Third Prize).

    Python 3 2

  4. Build-a-LLM-model-from-scratch-simple Build-a-LLM-model-from-scratch-simple Public

    LLM pipeline: data→tokenizer→attention→GPT train/eval→instruction FT→sampling. Reproducible, clean configs, RTX-4060 defaults, ready for AMP/LoRA/DDP.

    Jupyter Notebook 2

  5. cs336-assignment-1 cs336-assignment-1 Public

    Python 1

  6. Build-a-LLM-model-from-scratch-update Build-a-LLM-model-from-scratch-update Public

    SentencePiece BPE-32k, GQA, RMSNorm, SwiGLU, RoPE with context scaling, and incremental KV-cache; streaming packed-LM over fineweb/fineweb2

    Python 1