README.md

metadata

license: apache-2.0
language:
  - en
pretty_name: Dental Clinical Assistant 20B
base_model:
  - openai/gpt-oss-20b
library_name: transformers
pipeline_tag: text-generation
tags:
  - structured treatment planning
  - structured output
  - supervised fine tuning
  - sft
  - dental
  - dentistry
  - dental ai
  - dental clinical assistant
  - clinical decision support
  - diagnosis
  - treatment planning
  - evidence based
  - dental emergencies
  - antibiotic stewardship
  - guideline adherence
  - dental guidelines
  - endodontics
  - periodontics
  - oral surgery
  - prosthodontics
  - orthodontics
  - pediatric dentistry
  - dental radiology
  - differential diagnosis
  - risk assessment
  - triage
  - case reasoning
  - chairside assistant
  - point of care
  - medical
  - healthcare
  - clinical reasoning
  - synthetic data
  - hipaa compliant
datasets:
  - Wildstash/dental-2.5k-instruct
model-index:
  - name: Wildstash/dental-clinical-assistant-20b
    results:
      - task:
          type: text-generation
          name: Dental clinical QA (internal heuristic)
        dataset:
          name: Wildstash/dental-2.5k-instruct
          type: Wildstash/dental-2.5k-instruct
          split: test
        metrics:
          - type: clinical_guideline_adherence
            value: 0.9
          - type: reasoning_transparency
            value: 0.92
widget:
  - text: >-
      Evaluate dental emergency: 45M, severe tooth pain, facial swelling, fever
      101°F. Give differential, immediate management, antibiotics, follow up.
    parameters:
      max_new_tokens: 400
      temperature: 0.7
  - text: >-
      Periodontics: 52F with generalized 6–8 mm pockets and bleeding. Stage and
      grade, risk, and 90‑day treatment plan.
    parameters:
      max_new_tokens: 350
      temperature: 0.7
  - text: >-
      Endodontics: 33M, #19 lingering cold sensitivity, severe biting pain.
      Diagnose and outline RCT vs extraction decision.
    parameters:
      max_new_tokens: 350
      temperature: 0.7
  - text: >-
      Oral surgery: Impacted mandibular third molar with pericoronitis.
      Indications, risks, and peri‑op antibiotics.
    parameters:
      max_new_tokens: 320
      temperature: 0.7

Dental Clinical Assistant 20B

Chat assistant for structured treatment planning and clinical decision support (SFT)

Open source dental clinical assistant for diagnosis, treatment planning, and point‑of‑care decision support.

Quickstart (LoRA adapter)

from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel
import torch

base = "openai/gpt-oss-20b"
adapter = "Wildstash/dental-clinical-assistant-20b"

tok = AutoTokenizer.from_pretrained(base, trust_remote_code=True)
base_model = AutoModelForCausalLM.from_pretrained(base, torch_dtype=torch.bfloat16, device_map="auto", trust_remote_code=True)
model = PeftModel.from_pretrained(base_model, adapter)

🏆 Awards

• Winner: Most Useful Fine‑Tune (OpenAI Open Model Hackathon) — see Devpost: https://devpost.com/software/dental-assessment-gpt

Structured output

• Differential diagnosis
• Management plan
• Antibiotics and dosing (if indicated)
• Follow-up protocol

Quick guide (read this)

• What it is: Chat assistant for structured treatment planning and clinical decision support (SFT).
• What it covers: endodontics, periodontics, oral surgery, prosthodontics, ortho, pediatrics.
• Why trust it: trained on 2,494 expert‑validated synthetic cases; guideline‑aligned.
• How to use: provide patient context (age, vitals, symptoms, exam); ask for differential, management, abx, follow‑up.
• Safety: HIPAA‑friendly (no real patient data); outputs assist, not replace, clinical judgment.

Dataset statistics

• 2,494 cases; multi‑specialty coverage; structured JSON (presentation → assessment → plan).
• Source: Wildstash/dental-2.5k-instruct.

Key features

• Comprehensive dental coverage; evidence‑based plans; guideline adherence; step‑wise reasoning.

Training details

• Method: LoRA (PEFT), 4‑bit; base: 20B decoder.
• Optimizations: grad checkpointing; mixed precision; multi‑GPU.

Expert validation

• Practicing dentists graded sample cases; refined to improve plausibility and completeness.