Skip to content
View tsarihan's full-sized avatar
  • Harrisburg University of Science and Technology
  • LinkedIn in/tsarihan

Block or report tsarihan

Block user
See More

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.

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

Popular repositories Loading

  1. MirrorLaw MirrorLaw Public

    Scaling of systematic-bias transfer in language-model preference optimization

    Python

  2. model-council-mcp model-council-mcp Public

    Native Claude Code CLI plugin for multi-model council reviews across local, subscription, and cloud models

    JavaScript

  3. model-council-mcp-codex model-council-mcp-codex Public

    Native Codex plugin for multi-model council reviews across local, subscription, and cloud models

    JavaScript

  4. model-council-ui model-council-ui Public

    Web UI for model-council-mcp — multi-model council deliberations (Ollama, Claude, ChatGPT) from a chat interface

    TypeScript

  5. deepseek-v4-flash-0731-2x-dgx-spark-playbook deepseek-v4-flash-0731-2x-dgx-spark-playbook Public

    Serving DeepSeek-V4-Flash-0731 at 1M context across 2x DGX Spark (GB10) with TP=2, DSpark speculative decoding and NVFP4 KV cache. Measured findings: why PP is impossible, DSpark's 32-stream ceilin…

    Python

  6. deepseek-v4-flash-0731-nvfp4-2x-dgx-spark-playbook deepseek-v4-flash-0731-nvfp4-2x-dgx-spark-playbook Public

    DeepSeek-V4-Flash-0731 transcoded to NVFP4, served TP=2 on 2x DGX Spark (GB10). Transcoder, serving playbook, and like-for-like benchmarks vs MXFP4.

    Python