qwen35-0.8b-ner-json-lora

LoRA adapters for Qwen/Qwen3.5-0.8B fine-tuned to extract named entities from a sentence and return JSON only:

{"people": [], "places": [], "dates": []}

Task

Input: a sentence.

Output: strict JSON with:

• people
• places
• dates

Entity mapping from OntoNotes:

• PERSON → people
• GPE, LOC, FAC → places
• DATE → dates

Training data

• Dataset: tner/ontonotes5 raw JSON shards
• Train examples: 12000
• Eval examples: 512
• Fixed scored eval slice: first 64 validation examples after deterministic filtering/shuffle with seed 42
• Negative ratio: 0.15

Training recipe

• Base model: Qwen/Qwen3.5-0.8B
• 4-bit base + LoRA SFT
• LoRA target modules: auto-discovered
• LoRA rank/alpha/dropout: 16 / 32 / 0.05
• Batch size: 2
• Grad accumulation: 8
• Max steps: 300
• Learning rate: 2e-4
• Max length: 384
• Max new tokens: 96
• Seed: 42

Metrics

Original logged winning run (Run 4):

• entity_f1_pct: 89.5105
• json_exact_match_pct: 81.2500
• parseable_pct: 100.0000

Republished checkpoint pushed to this repo from the same recipe/commit with Hub push enabled:

• entity_f1_pct: 94.4444
• json_exact_match_pct: 92.1875
• parseable_pct: 100.0000

Usage

from transformers import AutoTokenizer, AutoModelForImageTextToText
from peft import PeftModel

base_model = "Qwen/Qwen3.5-0.8B"
adapter_id = "Mike0021/qwen35-0.8b-ner-json-lora"

tokenizer = AutoTokenizer.from_pretrained(adapter_id, trust_remote_code=True)
model = AutoModelForImageTextToText.from_pretrained(base_model, trust_remote_code=True)
model = PeftModel.from_pretrained(model, adapter_id)

Prompt format used during training:

• system: Extract named entities from the sentence. Return strict JSON only with keys people, places, dates. Each value must be an array of strings. Use [] when empty.
• user: Sentence: <sentence>

The model should answer with JSON only.