Pinned Loading

1. unsloth-rs unsloth-rs Public

   Memory-optimized GPU kernels for LLM fine-tuning in Rust (2-5x speedup, 70-80% less VRAM)

   Rust 2 1

2. axolotl-rs axolotl-rs Public

   YAML-driven configurable fine-tuning toolkit for LLMs in Rust

   Rust

3. peft-rs peft-rs Public

   Rust PEFT adapter library: LoRA, prefix tuning, prompt tuning for LLM fine-tuning

   Rust 2

4. qlora-rs qlora-rs Public

   4-bit NormalFloat (NF4) quantized LoRA for Rust with GGUF export

   Rust

5. webpuppet-rs-mcp webpuppet-rs-mcp Public

   MCP server for webpuppet browser automation

   Rust

6. tritter tritter Public

   Tritter research-driven custom any-to-any multimodal AI model optimized RTX 5080 16GB GDDR7. Combines Microsoft BitNet b1.58 ternary quantization with embedding prediction for semantic reasoning at…

   Python 1