Skip to content
View Hemeskyo's full-sized avatar
1 follower · 2 following

Block or report Hemeskyo

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

Pinned Loading

  1. mlx-ios-toolcall mlx-ios-toolcall Public

    On-device iOS assistant: a QLoRA-tuned LFM2.5-2.6B tool-calling LLM runs on the iPhone via Apple MLX and drives real system actions.

    Swift 1

  2. miniGPT miniGPT Public

    A from-scratch transformer in PyTorch — GQA, RoPE, QK-norm, SwiGLU, KV-cache.

    Python 1

  3. lfm2-toolcalling-qlora lfm2-toolcalling-qlora Public

    Bare QLoRA fine-tune of LFM2.5-2.6B for on-device tool calling (PEFT + TRL + bitsandbytes).

    Python

  4. lfm2-mlx lfm2-mlx Public

    Merging Liquid AI's LFM2.5-2.6B with an external QLoRA fine-tuned tool-calling adapter, then converting and quantizing to an 8-bit MLX model for local Apple Silicon and future iOS integration.

    Python 1

  5. bme280telemetry bme280telemetry Public

    C++