GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
AmareshHebbar
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
AmareshHebbar
Model Tree
unsloth/Qwen2.5-3B-Instruct
Input Modalities
Output Modalities
Supported Functionality
| Base model | unsloth/Qwen2.5-3B-Instruct |
| Fine-tuning method | QLoRA (4-bit NF4), rank 16 |
| Training framework | Unsloth + TRL SFTTrainer |
| Training data | AmareshHebbar/medical-billing-sft — 17,029 rows |
| Hardware | NVIDIA A40 (48GB), single GPU |
| License | Apache 2.0 |
Automate medical billing workflows or train internal coding-assist tools for outpatient charge capture and revenue cycle management.
This model is not a substitute for a certified medical professional's judgment. Output should be reviewed by a qualified person before being used in a clinical or billing decision. The model can make mistakes, especially on rare or compound cases.
python
from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModelimport torch base_model = "unsloth/Qwen2.5-3B-Instruct"adapter = "AmareshHebbar/medical-billing-qwen25-3b" tokenizer = AutoTokenizer.from_pretrained(base_model)model = AutoModelForCausalLM.from_pretrained( base_model, torch_dtype=torch.bfloat16, device_map="auto",)model = PeftModel.from_pretrained(model, adapter) messages = [ {"role": "system", "content": "You are a medical billing assistant. Given a clinical encounter description, return the CPT code, ICD-10-CM code, and modifier if applicable."}, {"role": "user", "content": "Procedure: Office visit, established patient, 25 minutes, moderate complexity."},]inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True).to(model.device)outputs = model.generate(inputs, max_new_tokens=128, temperature=0.1, do_sample=True)print(tokenizer.decode(outputs[0][inputs.shape[1]:], skip_special_tokens=True))Expected output:
text
CPT/HCPCS: 99214\nDescription: Office/outpatient visit, established, moderate complexity\nWork RVU: 1.92\nNote: Assign appropriate ICD-10-CM diagnosis code. Verify modifier requirements.python
from unsloth import FastLanguageModel model, tokenizer = FastLanguageModel.from_pretrained( model_name="AmareshHebbar/medical-billing-qwen25-3b", max_seq_length=512, load_in_4bit=True,)FastLanguageModel.for_inference(model) messages = [ {"role": "system", "content": "You are a medical billing assistant. Given a clinical encounter description, return the CPT code, ICD-10-CM code, and modifier if applicable."}, {"role": "user", "content": "Procedure: ECG with interpretation and report, 12-lead."},]prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = tokenizer(prompt, return_tensors="pt").to("cuda")outputs = model.generate(**inputs, max_new_tokens=128, temperature=0.1, do_sample=True)print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))bash
vllm serve unsloth/Qwen2.5-3B-Instruct \ --enable-lora \ --lora-modules medical-billing-qwen25-3b=AmareshHebbar/medical-billing-qwen25-3b \ --host 0.0.0.0 --port 8000 --dtype bfloat16python
from openai import OpenAI client = OpenAI(base_url="http://localhost:8000/v1", api_key="not-needed")response = client.chat.completions.create( model="medical-billing-qwen25-3b", messages=[ {"role": "system", "content": "You are a medical billing assistant. Given a clinical encounter description, return the CPT code, ICD-10-CM code, and modifier if applicable."}, {"role": "user", "content": "Procedure: MRI brain with and without contrast."}, ], temperature=0.1,)print(response.choices[0].message.content)Trained on 17,029 examples extracted from real CMS Physician Fee Schedule 2026 — PPRRVU nonQPP procedures with RVU data. No synthetic or LLM-generated training data — every example pairs real-world input with its authoritative output.
See the dataset card for the full extraction pipeline.
| Parameter | Value |
|---|---|
| LoRA rank | 16 |
| LoRA alpha | 32 |
| LoRA dropout | 0 |
| Target modules | q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj |
| Quantization | 4-bit NF4 (QLoRA) |
| Max sequence length | 512 |
| Optimizer | paged_adamw_8bit |
| Learning rate | 2e-4, cosine schedule |
Fine-tuned with Unsloth for 2x faster training and reduced VRAM, using TRL's SFTTrainer. Training run on a single NVIDIA A40 GPU. Experiment tracking via Weights & Biases.
| Model | Task | Size |
|---|---|---|
| icd10-coder-qwen25-7b | ICD-10-CM medical coding | 7B |
| snomed-mapper-qwen25-7b | Clinical concept mapping | 7B |
| icd10-to-drg-qwen25-1b | ICD-10 → DRG reimbursement | 1.5B |
| pmjay-classifier-qwen25-3b |
Full collection: [link your HF collection here]
bibtex
@misc{medicalai2026, author = {Hebbar, Amaresh}, title = {Medical AI Fine-tuning Suite}, year = {2026}, publisher = {HuggingFace}, url = {https://huggingface.co/AmareshHebbar}}| India PM-JAY classification |
| 3B |