๐Ÿฆท doctor-dental-implant-Qwen2.5-7B-Instruct (GGUF - F16)

This is the full precision (f16) GGUF version of a model trained for medical chatbot and dental implant assistant tasks. It combines general doctorโ€“patient dialogue understanding with domain-specific Q&A derived from Straumannยฎ dental implant system manuals.

๐Ÿง  Based on: Qwen/Qwen2.5-VL-7B-Instruct
๐Ÿ› ๏ธ Finetuned using: Unsloth
๐Ÿ“ฆ Format: GGUF (f16), compatible with llama.cpp, Ollama, LM Studio, and other local inference engines.


๐Ÿ“Š Dataset

Merged and instruction-formatted dataset from:

Total: ~900 examples, formatted in Alpaca-style with <|im_end|> as EOS.


๐Ÿง  Prompt Format

For Qwen2.5-style use:

<|im_start|>system
You are a helpful and knowledgeable medical assistant.<|im_end|>
<|im_start|>user
What is the purpose of a healing abutment in dental implants?<|im_end|>
<|im_start|>assistant
A healing abutment is used to shape the gum tissue and protect the implant during healing before placing the final crown.<|im_end|>

Or if you're using Alpaca-style:

Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
What are the post-op care instructions after implant surgery?

### Response:
Patients are usually advised to avoid chewing on the surgical site, maintain oral hygiene with chlorhexidine rinses, and follow up in 7โ€“10 days.<|im_end|>

๐Ÿ›  How to Use (LLaMA.cpp / LM Studio / Ollama)

Once downloaded, you can run the model locally via:

๐Ÿงช llama.cpp

./main -m doctor-dental-implant-Qwen2.5-7B-Instruct-f16.gguf --prompt "What is a dental implant?"

๐Ÿ’ป Ollama (if you've converted the model)

ollama run doctor-dental

๐Ÿ”ฌ Use Cases

  • ๐Ÿง‘โ€โš•๏ธ Patient-facing virtual assistant
  • ๐Ÿฆท Dental implant Q&A
  • ๐Ÿ“š Medical education simulation
  • ๐Ÿงช Domain adaptation benchmarking (healthcare)

โš ๏ธ Limitations

  • Not for clinical use or medical advice
  • May hallucinate or provide overly simplified explanations
  • Training data is synthetic or handbook-derived, not real EMR

๐Ÿ“œ License

MIT License


โœ๏ธ Author

Created by (BirdieByte1024) as part of an applied research project in medical LLM alignment.

Downloads last month
37
GGUF
Model size
7.62B params
Architecture
qwen2
Hardware compatibility
Log In to view the estimation

16-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support