AmanPriyanshu/gpt-oss-8.4b-specialized-health_or_medicine-pruned-moe-only-11-experts
Health Or Medicine GPT-OSS Model (11 Experts)
Project: https://amanpriyanshu.github.io/GPT-OSS-MoE-ExpertFingerprinting/
<div align="center">
π₯ Follow the Authors
Aman Priyanshu   
Supriti Vijay   
</div>
Introduction
This is a pruned variant of OpenAI's GPT-OSS-20B model, reduced to 11 experts per layer based on activation patterns from the AmanPriyanshu/GPT-OSS-20B MoE Expert Activations dataset. We analyzed router decisions across evaluation benchmarks to identify and retain experts most relevant for health or medicine tasks.
β οΈ Experimental Model: This is an experimental pruned model that may not work well - check the examples below to see if the outputs meet your needs before use.
This pruning approach reduces the model size while attempting to preserve performance on the target domain.
Model Architecture & Statistics
Pruning Methodology
What is Expert Pruning?
Mixture-of-Experts models contain multiple specialized sub-networks (experts) per layer. During inference, only a subset of experts are activated for each token. Expert pruning involves:
- Analyzing Usage Patterns: Tracking which experts activate most frequently for specific tasks
- Removing Underutilized Experts: Discarding experts with low activation rates for the target domain
- Preserving Router Functionality: Maintaining the routing mechanism with fewer available experts
Our Approach
- Data-Driven Selection: Used activation patterns from health or medicine evaluation tasks
- Systematic Reduction: Reduced from 32 to 11 experts per layer
- No Retraining: Direct removal without additional training steps
Performance & Applications
Pruning Benefits
- Smaller Memory Footprint: 34.4% of original expert parameters
- Reduced Computational Load: Fewer routing decisions during inference
- Focused Capabilities: Retains experts relevant to health or medicine tasks
Use Cases
- Speculative Decoding: Draft model for full GPT-OSS-20B
- Resource-Constrained Deployment: Edge devices, mobile applications
- Research: Study expert specialization in MoE models
- Fine-tuning: Smaller base model for domain adaptation
Note: Performance may vary depending on how well the pruned experts match your specific use case.
Motivation & Expert Selection
This medical domain model incorporates experts that activated highly during health and medical tasks from MMLU medical subjects. These experts specialize in clinical knowledge, anatomy, medical procedures, and health-related reasoning.
The expert selection process utilized our comprehensive analysis of router activation patterns across multiple evaluation benchmarks:
- GPQA: Graduate-level questions in physics, chemistry, biology (Diamond & Expert subsets)
- MMLU/MMLU-Pro: Comprehensive knowledge across 57+ subjects including science, medicine, law
- SORRY-Bench: Safety evaluation across harmful content categories
- Tulu3: Persona-driven instruction following with verifiable constraints
- Polyglot-or-Not: Multilingual factual completion tasks
By identifying experts that consistently activated for health or medicine tasks, we created this specialized model that maintains domain expertise while significantly reducing computational requirements from 32 to 11 experts per layer.
Dataset & Analysis Foundation
This model is based on analysis from the GPT-OSS-20B MoE Expert Activations dataset available at: π https://huggingface.co/datasets/AmanPriyanshu/GPT-OSS-20B-MoE-expert-activations
The dataset contains router activation patterns from OpenAI's GPT-OSS-20B model across diverse evaluation benchmarks, enabling the creation of these domain-optimized models through systematic expert pruning.
Pruning Methodology
Our approach involves:
- Activation Analysis: Comprehensive evaluation of expert usage patterns across domain-specific tasks
- Expert Ranking: Identification of the most frequently activated experts for target domains
- Systematic Pruning: Reduction from 32 to 11 experts while preserving router functionality
- Quality Validation: Testing to ensure maintained performance on target tasks
This is a direct pruning approach - no additional training was performed. The model inherits all capabilities from the original GPT-OSS-20B with focused expert selection.
Usage
CPU Inference
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
# Load the specialized model on CPU
model = AutoModelForCausalLM.from_pretrained(
"AmanPriyanshu/gpt-oss-8.4b-specialized-health_or_medicine-pruned-moe-only-11-experts",
torch_dtype=torch.bfloat16,
device_map="cpu",
trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained("AmanPriyanshu/gpt-oss-8.4b-specialized-health_or_medicine-pruned-moe-only-11-experts")
# Generate with the model
messages = [
{"role": "user", "content": "What are the main functions of the human heart?"}
]
inputs = tokenizer.apply_chat_template(
messages,
add_generation_prompt=True,
return_tensors="pt",
return_dict=True,
reasoning_effort="medium"
)
# Ensure inputs are on the same device as model
inputs = {k: v.to(model.device) for k, v in inputs.items()}
outputs = model.generate(
**inputs,
max_new_tokens=512,
do_sample=True,
temperature=0.1,
top_p=0.9,
pad_token_id=tokenizer.eos_token_id,
eos_token_id=tokenizer.eos_token_id
)
# Decode only the generated part
input_length = inputs['input_ids'].shape[1]
response_tokens = outputs[0][input_length:]
response = tokenizer.decode(response_tokens, skip_special_tokens=True)
print(response)Apple Silicon (MPS) Inference
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
# Check MPS availability and load model
device = "mps" if torch.backends.mps.is_available() else "cpu"
model = AutoModelForCausalLM.from_pretrained(
"AmanPriyanshu/gpt-oss-8.4b-specialized-health_or_medicine-pruned-moe-only-11-experts",
torch_dtype=torch.float16, # Better MPS compatibility
device_map=device,
trust_remote_code=True,
low_cpu_mem_usage=True
)
tokenizer = AutoTokenizer.from_pretrained("AmanPriyanshu/gpt-oss-8.4b-specialized-health_or_medicine-pruned-moe-only-11-experts")
# Generate with the model
messages = [
{"role": "user", "content": "What are the main functions of the human heart?"}
]
inputs = tokenizer.apply_chat_template(
messages,
add_generation_prompt=True,
return_tensors="pt",
return_dict=True,
reasoning_effort="medium"
)
# Move inputs to model device
inputs = {k: v.to(model.device) if isinstance(v, torch.Tensor) else v for k, v in inputs.items()}
# Use torch.no_grad for MPS stability
with torch.no_grad():
outputs = model.generate(
**inputs,
max_new_tokens=512,
do_sample=True,
temperature=0.1,
top_p=0.9,
pad_token_id=tokenizer.eos_token_id,
eos_token_id=tokenizer.eos_token_id,
use_cache=True
)
# Decode only the generated part
input_length = inputs['input_ids'].shape[1]
response_tokens = outputs[0][input_length:]
response = tokenizer.decode(response_tokens, skip_special_tokens=True)
print(response)GPU Inference
For CUDA GPU inference, the models work with minimal modifications from the CPU example above. Simply change:
device_map="auto" # Will automatically use GPU if available
torch_dtype=torch.bfloat16 # or torch.float16Model Examples
The following examples demonstrate the model's performance on health or medicine tasks:
Example 1
Question: What are the main functions of the human heart?
Response:
<|channel|>analysis<|message|>Need to answer: main functions: pumping blood, regulating blood pressure, pumping blood to all body, pumping blood to brain, pumping blood to lungs, pumping blood to kidneys, pumping blood to heart. Also endocrine functions: hormone production. Also electrical conduction. Provide explanation.<|end|><|start|>assistant<|channel|>final<|message|>**The human heart is a central organ that performs two main functions:**
---
### 1. **P pumping blood (circulatory function)**
The heartβs βpumpβ keeps the blood moving through the body, ensuring that every organ receives oxygen, nutrients, and wasteβproducts.
* **Rightβs side (rightβventil)** β receives oxygenβrich blood from the lungs and sends it to the body.
* **Leftβs side (leftβventil)** β receives oxygenβpoor blood from the body and sends it to the lungs.
* The heartβs rhythm (the electrical conduction system) guarantees that the blood is pumped in a steady, coordinated way.
---
### 2. **Regulating blood pressure (heβvascular function)**
By adjusting the amount of blood pumped and the resistance of the blood vessels, the heart keeps the blood pressure within the normal range.
* **When the heart pumps more blood** β blood pressure rises.
* **When the heart pumps less blood** β blood pressure falls.
The heartβs response to the bodyβs needs (e.β―g. exercise, stress, dehydration) is part of the autonomic nervous system.
---
### 3. **Hormineβandβneβhβendβfunction**
The heart also produces hormones that help the body respond to stress and maintain fluid balance.
* **Aβangiβandβneβhβ** (adβaβandβneβhβ) β a hormone that helps the blood vessels constren and dilate.
* **Neβhβ** β a hormone that helps the kidneys retain water and salt.
---
### 4. **Electrical conduction system**
The heartβs own electrical system (the sinoβatrial node, atrβventβnode, etc.) creates a rhythm that coordinates the pumping action.
* **Sβnode** β the natural pacemaker.
* **AVβnode** β the electrical relay that slows the heartβs beat.
* **Bundle of Rβr** β the conduction pathway that ensures the heartβs rhythm is coordinated.
---
### 5. **MechanicalβandβtExample 2
Question: Explain the difference between bacteria and viruses.
Response:
<|channel|>analysis<|message|>Need explain differences: size, shape, replication, host, etc.<|end|><|start|>assistant<|channel|>final<|message|>**Bacteria vs. Virons β The Key Differences**
| Feature | Bacteria | Virons |
|--------- |--------- |--------- |
| **Definition** | Microorganisms that are *alive* and can grow, divide, and reproduce. | Microorganisms that are *not alive*; they are genetic material that can replicate inside a host cell. |
| **Size & Shape** | Usually 1β2β―Β΅m in diameter; can be singleβcell (monococ) or multiβcell (polococ). | 0.1β0.5β―Β΅m; often 1β2 strands of DNA, sometimes wrapped in a protein coat. |
| **Cellular Structure** | Have a cell wall, cytoplasm, membrane, ribosomes, DNA, and sometimes mitochondβββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββExample 3
Question: What are the symptoms and causes of diabetes?
Response:
<|channel|>analysis<|message|>Need to answer symptoms and causes.<|end|><|start|>assistant<|channel|>final<|message|>**Diabetes mellitus** is a chronic disease in which the body cannot produce or use insulin, a hormone that regulates bloodβglucose levels. The most common type is typeβ―2 diabetes, but typeβ―1 and other forms also exist. Below are the typical symptoms and the main causes for each type.
---
## 1. Symptoms (common across all types)
| Symptom | Why it happens | How it shows |
|--------|--------------|--------------|
| **Freckly thirst (polpol)** | Blood glucose is high β kidneys try to exβelate β thirst | βIβm always thirstyβ |
| **Freckly urination** | Kidneys exβelate glucose β more urine | βIβm always peilingβ |
| **Weight loss** | Insulin resistance β body burns glucose β weight loss | βIβm losing weightβ |
| **Fatigue** | Body canβt use glucose β energy low | βI feel tiredβ |
| **Poor wound healing** | High glucose β impacts blood flow & immune response | βMy cuts heal slowlyβ |
| **Vision problems** | High glucose β damages small blood vessels in the eye | βI have blurry visionβ |
| **Increased infections** | High glucose β weak immune system | βI get infections more oftenβ |
| **Switching** | High glucose β body tries to store fat β swelling | βI have swellingβ |
| **High blood pressure** | Insulin resistance β high blood pressure | βI have high blood pressureβ |
| **High cholesterol** | Insulin resistance β high cholesterol | βI have high cholesterolβ |
| **High triglycer** | Insulin resistance β high triglycer | βI have high triglycerβ |
| **High blood sugar** | Insulin resistance β high blood sugar | βI have high blood sugarβ |
> **Note**: Symptoms can be subtle or absent in early stages, especially in typeβ―2 diabetes. Many people have βnoβsymptomsβ until the disease is advanced.
---
## 2. Causes
### 2β1. Typeβ―1 Diabetes (Autoimmune)
| Cause | How it works |
|--------|--------------|
| **Autoimmune attack on Ξ²βcells** | The immune system mistakenly destroys insulinβproducing Ξ²βcells in the pancreas | No insulin β high blood glucose |
| **Genetic predis**Citation
If you use this model in your research, please cite:
@misc{priyanshu2025gptoss,
title={{GPT-OSS MoE Expert Fingerprinting: Analyzing Expert Activation Patterns in Mixture of Experts Models}},
author={Priyanshu, Aman and Vijay, Supriti},
year={2025},
howpublished={\url{https://amanpriyanshu.github.io/GPT-OSS-MoE-ExpertFingerprinting/}},
note={Interactive analysis tool for expert activation patterns in MoE architectures}
}References & Resources
- Original Model: OpenAI GPT-OSS Model Card
- Model Hub: GPT-OSS-20B on Hugging Face
- Expert Analysis Dataset: GPT-OSS-20B MoE Expert Activations
- Project Page: GPT-OSS MoE Expert Fingerprinting
- GitHub Repository: OpenAI GPT-OSS
