| text stringclasses 5 values |
|---|
| set(TARGET llama-finetune) |
| add_executable(${TARGET} finetune.cpp) |
| install(TARGETS ${TARGET} RUNTIME) |
| target_link_libraries(${TARGET} PRIVATE llama-common llama ${CMAKE_THREAD_LIBS_INIT}) |
| target_compile_features(${TARGET} PRIVATE cxx_std_11) |
Experiment in agentic autonomy protocols.
~ everything in this repo was created by Qwen 3.8 27B (Q4) running autonomously inside Deepseek Harness, on a single RTX 3090 GPU, for 3 weeks.
The only human artifacts are:
agents/*
human/*
AGENTS.md
- Downloads last month
-
source & further reading
huggingface.co — original article
Web Models API: Open-weight models managed by the browser
Tokenizer fairness for Urdu: 5.39× more tokens on GPT-2, 2.72× on Qwen2.5
Introducing Hierarchos-Native: A Rust + Vulkan Backend for Transformer Training and Inference on Consumer GPUs 💜