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/Qwen2.5-1.5B-Instruct
Input Modalities
Output Modalities
Supported Functionality
| Base model | unsloth/Qwen2.5-1.5B-Instruct |
| Fine-tuning method | QLoRA (4-bit NF4), rank 16 |
| Training framework | Unsloth + TRL SFTTrainer |
| Training data | AmareshHebbar/icd10-to-drg-sft — 5,385 rows |
| Hardware | NVIDIA A40 (48GB), single GPU |
| License | Apache 2.0 |
Hospital reimbursement prediction, DRG validation tooling, and revenue cycle automation under the Medicare Inpatient Prospective Payment System (IPPS).
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/Qwen2.5-1.5B-Instruct"adapter = "AmareshHebbar/icd10-to-drg-qwen25-1b" 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 DRG grouper. Given ICD-10-CM codes, return the MS-DRG code, relative weight, and geometric mean LOS."}, {"role": "user", "content": "ICD-10-CM code: I21.09"},]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
MS-DRG 280 — Acute Myocardial Infarction, Discharged Alive with MCC\nRelative Weight: 2.8613\nGeometric Mean LOS: 4.7 dayspython
from unsloth import FastLanguageModel model, tokenizer = FastLanguageModel.from_pretrained( model_name="AmareshHebbar/icd10-to-drg-qwen25-1b", max_seq_length=512, load_in_4bit=True,)FastLanguageModel.for_inference(model) messages = [ {"role": "system", "content": "You are a DRG grouper. Given ICD-10-CM codes, return the MS-DRG code, relative weight, and geometric mean LOS."}, {"role": "user", "content": "ICD-10-CM code: J18.9"},]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/Qwen2.5-1.5B-Instruct \ --enable-lora \ --lora-modules icd10-to-drg-qwen25-1b=AmareshHebbar/icd10-to-drg-qwen25-1b \ --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="icd10-to-drg-qwen25-1b", messages=[ {"role": "system", "content": "You are a DRG grouper. Given ICD-10-CM codes, return the MS-DRG code, relative weight, and geometric mean LOS."}, {"role": "user", "content": "MS-DRG: 343"}, ], temperature=0.1,)print(response.choices[0].message.content)Trained on 5,385 examples extracted from real CMS MS-DRG v43.1 Definitions Manual + FY2026 Final Rule Table 5 weights. 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 |