Update README.md

README.md

@@ -1,207 +1,154 @@
 ---
+language: en
+license: mit
 base_model: Qwen/Qwen3-1.7B
-library_name: peft
-pipeline_tag: text-generation
 tags:
-- base_model:adapter:Qwen/Qwen3-1.7B
-- lora
-- transformers
+  - medical
+  - lora
+  - peft
+  - rocm
+  - amd
+  - question-answering
+  - fine-tuned
+datasets:
+  - openlifescienceai/medmcqa
 ---
 
-# Model Card for Model ID
-
-<!-- Provide a quick summary of what the model is/does. -->
-
+# MedQA — Qwen3-1.7B LoRA Fine-tuned on MedMCQA
 
+Clinical question-answering AI fine-tuned on MedMCQA.
+Built on AMD Instinct MI300X via ROCm — no CUDA required.
 
 ## Model Details
 
-### Model Description
-
-<!-- Provide a longer summary of what this model is. -->
-
-
-
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-
-### Model Sources [optional]
-
-<!-- Provide the basic links for the model. -->
+- Base Model  : Qwen/Qwen3-1.7B
+- Fine-tuning : LoRA (r=4, target: q_proj + v_proj)
+- Dataset     : openlifescienceai/medmcqa (193k clinical MCQs)
+- Hardware    : AMD Instinct MI300X (192GB HBM3)
+- Precision   : bfloat16 (ROCm native)
+- Trainable   : ~2.2M of 1.7B parameters (0.15%)
 
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
+## What It Does
 
-## Uses
+Given a clinical multiple-choice question with 4 options,
+the model selects the correct answer and explains its reasoning.
 
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+Example input:
 
-### Direct Use
+    ### Question:
+    First-line treatment for hypertensive emergency?
 
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+    ### Options:
+    A) Oral amlodipine
+    B) IV labetalol or IV nitroprusside
+    C) Sublingual nifedipine
+    D) IM hydralazine
 
-[More Information Needed]
+    ### Answer:
 
-### Downstream Use [optional]
+Example output:
 
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+    B) IV labetalol or IV nitroprusside
 
-[More Information Needed]
+    Explanation:
+    Hypertensive emergencies require immediate IV therapy.
+    Labetalol is a combined alpha and beta blocker that rapidly
+    reduces blood pressure safely. Nitroprusside is a vasodilator
+    used when faster or more precise control is needed.
 
-### Out-of-Scope Use
+## How to Use
 
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+    from transformers import AutoTokenizer, AutoModelForCausalLM
+    from peft import PeftModel
+    import torch
 
-[More Information Needed]
+    BASE_MODEL   = "Qwen/Qwen3-1.7B"
+    ADAPTER_REPO = "HK2184/medqa-qwen3-lora"
 
-## Bias, Risks, and Limitations
+    tokenizer = AutoTokenizer.from_pretrained(BASE_MODEL, trust_remote_code=True)
+    tokenizer.pad_token    = tokenizer.eos_token
+    tokenizer.padding_side = "left"
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+    base = AutoModelForCausalLM.from_pretrained(
+        BASE_MODEL,
+        dtype=torch.bfloat16,
+        device_map="auto",
+        trust_remote_code=True,
+    )
 
-[More Information Needed]
+    model = PeftModel.from_pretrained(base, ADAPTER_REPO)
+    model = model.merge_and_unload()
+    model.eval()
 
-### Recommendations
+    prompt = """### Question:
+    First-line treatment for hypertensive emergency?
 
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+    ### Options:
+    A) Oral amlodipine
+    B) IV labetalol or IV nitroprusside
+    C) Sublingual nifedipine
+    D) IM hydralazine
 
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+    ### Answer:
+    """
 
-## How to Get Started with the Model
-
-Use the code below to get started with the model.
-
-[More Information Needed]
+    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+    with torch.no_grad():
+        out = model.generate(
+            **inputs,
+            max_new_tokens=200,
+            do_sample=True,
+            temperature=0.7,
+            top_p=0.9,
+            repetition_penalty=1.3,
+            pad_token_id=tokenizer.eos_token_id,
+        )
+    new = out[0][inputs["input_ids"].shape[-1]:]
+    print(tokenizer.decode(new, skip_special_tokens=True))
 
 ## Training Details
 
-### Training Data
-
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-
-[More Information Needed]
-
-### Training Procedure
-
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-
-#### Preprocessing [optional]
-
-[More Information Needed]
-
-
-#### Training Hyperparameters
-
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-
-#### Speeds, Sizes, Times [optional]
-
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-
-[More Information Needed]
-
-## Evaluation
-
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
-
-## Environmental Impact
-
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
-
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-
-**BibTeX:**
+- Framework    : PyTorch + HuggingFace Transformers + PEFT + TRL
+- LoRA rank    : r=4, alpha=16
+- Batch size   : 4
+- Learning rate: 1e-4
+- Epochs       : 1
+- Max length   : 128 tokens
+- Samples      : 500 from MedMCQA train split
+- Training time: ~5 minutes on AMD MI300X
 
-[More Information Needed]
+## AMD ROCm Notes
 
-**APA:**
+Trained entirely on AMD hardware using ROCm 7.2.
+Key insight: bfloat16 is stable on MI300X — fp16 caused
+gradient norm explosion (nan) during LoRA training.
 
-[More Information Needed]
+Environment variables used:
+    ROCR_VISIBLE_DEVICES=0
+    HIP_VISIBLE_DEVICES=0
+    HSA_OVERRIDE_GFX_VERSION=9.4.2
 
-## Glossary [optional]
+## Live Demo
 
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+Try it without any setup:
+https://huggingface.co/spaces/lablab-ai-amd-developer-hackathon/MedQA-Medical-AI-on-AMD-ROCm
 
-[More Information Needed]
+## Repository
 
-## More Information [optional]
+Full training code, eval script, and Gradio app:
+https://github.com/HK2184/MedQA-Medical-AI-on-AMD-ROCm
 
-[More Information Needed]
+## Dataset
 
-## Model Card Authors [optional]
+MedMCQA — 193,000 medical multiple choice questions
+from Indian medical entrance exams (AIIMS, USMLE-style).
+https://huggingface.co/datasets/openlifescienceai/medmcqa
 
-[More Information Needed]
+## Authors
 
-## Model Card Contact
+Harikrishna Sivanand Iyer and Srijan Sivaram A
+Built for the AMD Hackathon on lablab.ai
 
-[More Information Needed]
-### Framework versions
+## License
 
-- PEFT 0.19.1
+MIT — free to use, modify, and build on.