Skip to content

Repository files navigation

AGmind-ML

Locally fine-tuned Russian models for the self-hosted AGmind RAG stack. Teacher distillation, quantization to GGUF, inference on AMD (Vulkan, no CUDA) via llama.cpp. Commercial-OK licenses, fully local. Trained on a single consumer GPU (RTX 5090), deployed on AMD Strix Halo. Three models shipped so far — a document splitter, query expansion, and a retrieval embedder.

License Serve Lang

Models

Project What it does Base Key numbers Status
agmind-rag-splitter-ru · 🤗 Context-aware document splitter for RAG: semantic chunks, tables and code kept whole, lossless reconstruction t-tech/T-lite-it-2.1 (Qwen3-8B) 100% valid JSON, boundary-F1@±1 0.821 ✅ on HF
qmd-query-expansion-ru · 🤗 Search-query expansion for qmd (hyde/lex/vec, word forms for BM25); fixes the stock model's English hallucinations on Russian Qwen/Qwen3-1.7B reward-score 94.8; 100% format ✅ on HF
strizh-ru-retriever · 🤗 · GGUF RU-first no-prefix dense retriever: 4 layers, distilled by layer-pruning + BGE-M3 hard negatives. A speed/drop-in specialist — beats rubert-tiny2 on Russian, below USER2-small/bge-m3 on quality deepvk/RuModernBERT-small RU recall@10 0.75 (clean) / EN nDCG@10 0.34; 24M, fast on Strix Vulkan (slower on CPU) ✅ on HF
next… (150M embedder, reranker, grounded-QA) planned

Method

  • Teacher distillation. A strong model labels the task or defines the target space — no manual annotation, with strict validation gates, dedup and retries.
  • One RTX 5090 (32 GB). Generative models: bf16 LoRA (+rsLoRA), response-only loss. Embedders: teacher layer-pruning (warm-start) + contrastive (MNRL) on hard negatives.
  • Cyrillic bases. Russian-tuned tokenizers are more economical than vanilla ones.
  • Deploy anywhere. GGUF → llama.cpp Vulkan on AMD Strix Halo, no CUDA.

Layout

AGmind-ML/
├── agmind-rag-splitter-ru/   # document splitter
├── qmd-query-expansion-ru/   # query expansion
└── strizh-ru-retriever/      # retrieval embedder

Each project has its own README.md: task, method, metrics, reproduction.

About

Locally fine-tuned Russian RAG models: document splitter, query expansion, retrieval embedder. Teacher distillation → GGUF → llama.cpp on AMD Vulkan. Commercial-OK licenses.

Topics

Resources

Stars

20 stars

Watchers

1 watching

Forks

Releases

Packages

Contributors

Languages