Base model: Qwen/Qwen3-4B
Architecture: Qwen3ForCausalLM
Format: Hugging Face Transformers + Safetensors
Primary use: structured article-evaluation prompts for scoring, ranking, or label prediction

Intended Use

The model is intended for research and internal experimentation on structured article-evaluation prompts.

It is not intended as a general-purpose factual assistant or as a substitute for expert peer review.

Files

This repository keeps only the files needed to load and run the model:

model weights in safetensors
tokenizer files
model config and generation config

Training-state artifacts such as training_args.bin are intentionally excluded.

Example

python

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "K1mG0ng/AI-taste-eco-4B"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)

Notes

This is a fine-tuned research model.
Output quality depends on prompt format and label schema used at inference time.
Benchmark datasets and training framework are maintained separately.