limite-1b-violetto-Gundem-LoRA

LoRA adapter for Turkish news headline classification. Requires the pinned base model; this is not a standalone full checkpoint or a general chat assistant.

Base: paradigma-inc/limite-1b-violetto · revision 9f4d1567975a44c35127503deadfe52d434d734f.

DeepSeek-generated answers were used for assistant-only supervised fine-tuning (response distillation). No DeepSeek weights or logits were used; the student's parameter count is unchanged. The split contains 825 training, 107 validation and 101 test examples. Three epochs, lr=0.0002, LoRA r16/alpha32, accumulation=8, max_length=512, seed=42.

Use

Download this repository, install a suitable CUDA PyTorch build and the supplied requirements, then run from the downloaded folder:

python -m pip install -r requirements.txt
python release_infer.py --model . --headline "İşçiler ücret artışı için greve başladı"

The supplied loader handles architecture compatibility, the exact task template, pinned base revision, CPU fp32 adapter merging and CUDA BF16 inference. Allow CPU RAM for the full fp32 base model and GPU memory for BF16 inference. Loading the base model executes its remote model code. Review it before use. The result contains prediction or an explicit error; generation is not constrained by a JSON grammar.

The model receives only the headline and student-system.txt. Output fields: etiketler (topics), tur (event type), and etki, ciddiyet, aciliyet (integer scores 0–3).

Evaluation

HF/CUDA BF16, greedy, batch=4, maximum 160 new tokens, no JSON grammar. Gündem Score = 30×topic F1 + 20×type accuracy + 30×(1−mean score MAE/3) + 20×exact match (fractional metrics). It measures this task's teacher-label agreement, not general LLM intelligence or an accuracy percentage. Small differences on this previously evaluated, single-seed test do not establish superiority. Batch size and numerical runtime changes can affect outputs. See evaluation.json and release-manifest.json.

Licensing and limitations

Gündem response-distillation LoRA adaptation of paradigma-inc/limite-1b-violetto, revision 9f4d1567975a44c35127503deadfe52d434d734f. Modified artifact: adapter weights trained on DeepSeek-labelled Turkish headlines. Model and tokenizer licensing follows the upstream license files. Gündem helper code: MIT.

Experimental adaptation: explicit task ChatML replaces the fixed mathematical prompt. Direct-weight LoRA paths bypass feature dropout during training.

The task uses a small, domain-specific dataset. Inspect predictions before relying on them. Raw headlines, teacher answers and the full dataset are not redistributed. Model licensing is separate from the MIT-licensed Gündem helper code.

Training and benchmark tools · All released models

Mobile GGUF pair

Original and fine-tuned Q4_K_M files, tested with the Gündem native engine.

These scores come from the HF/BF16 experiment; mobile GGUF quality was not rescored. Both files retain the base model license and notices included in this repository. The original model is not fine-tuned.