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/ayurveda-icd-sft — 3,002 rows |
| Hardware | NVIDIA A40 (48GB), single GPU |
| License | Apache 2.0 |
Support ABDM/ABHA health record integration for AYUSH practitioners and integrative medicine hospitals that need to document in standard codes.
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/ayurveda-icd-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 an integrative medicine specialist. Map the traditional medicine condition to its ICD-10-CM equivalent with a clinical note."}, {"role": "user", "content": "Traditional medicine condition: Amavata"},]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
Nearest ICD-10: M06.9 — Rheumatoid arthritis, unspecified\nClinical note: Amavata is characterised by joint inflammation and constitutional symptoms closely mirroring RA. Check RF, anti-CCP antibodies.python
from unsloth import FastLanguageModel model, tokenizer = FastLanguageModel.from_pretrained( model_name="AmareshHebbar/ayurveda-icd-qwen25-1b", max_seq_length=512, load_in_4bit=True,)FastLanguageModel.for_inference(model) messages = [ {"role": "system", "content": "You are an integrative medicine specialist. Map the traditional medicine condition to its ICD-10-CM equivalent with a clinical note."}, {"role": "user", "content": "Traditional medicine condition: Madhumeha"},]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 ayurveda-icd-qwen25-1b=AmareshHebbar/ayurveda-icd-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="ayurveda-icd-qwen25-1b", messages=[ {"role": "system", "content": "You are an integrative medicine specialist. Map the traditional medicine condition to its ICD-10-CM equivalent with a clinical note."}, {"role": "user", "content": "Traditional medicine condition: Pandu"}, ], temperature=0.1,)print(response.choices[0].message.content)Trained on 3,002 examples extracted from real CMS ICD-10-CM Z and Y codes plus traditional medicine terminology crosswalk. 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 |