Downloads · 30 days
15
12% of all-time downloads
AmanPriyanshu/gpt-oss-17.3b-specialized-health_or_medicine-pruned-moe-only-26-experts
gpt-oss-17.3b-specialized-health_or_medicine-pruned-moe-only-26-experts is a text generation model from AmanPriyanshu. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.
Project: https://amanpriyanshu.github.io/GPT-OSS-MoE-ExpertFingerprinting/
Downloads · 30 days
15
12% of all-time downloads
All-time downloads
123
Public
Parameters
17.3B
34.7 GB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors34.7 GB · 100%
From the Hugging Face model README
Project: https://amanpriyanshu.github.io/GPT-OSS-MoE-ExpertFingerprinting/
<div align="center">This is a pruned variant of OpenAI's GPT-OSS-20B model, reduced to 26 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.
⚠️ 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.
| Metric | Value |
|---|---|
| Base Model | openai/gpt-oss-20b |
| Architecture | Mixture-of-Experts Transformer |
| Total Parameters | ~17.3B (pruned from 21B) |
| Original Experts per Layer | 32 |
| Pruned Experts per Layer | 26 |
| Layers | 24 |
| Top-k Routing | 4 |
| Context Length | 128K tokens |
| Attention Heads | 64 (Query), 8 (Key-Value) |
| Residual Dimension | 2880 |
| Attention Pattern | Alternating dense & sliding window (128 tokens) |
| Positional Encoding | RoPE (Rotary Position Embedding) |
| Normalization | RMSNorm |
| Precision | BF16 |
| License | Apache 2.0 |
| Specialization | Health Or Medicine |
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:
Note: Performance may vary depending on how well the pruned experts match your specific use case.
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:
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 26 experts per layer.
This model is based on analysis from the GPT-OSS-20B MoE Expert Activations dataset available at: 🔗 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.
Our approach involves:
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.
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
# Load the specialized model on CPU
model = AutoModelForCausalLM.from_pretrained(
"AmanPriyanshu/gpt-oss-17.3b-specialized-health_or_medicine-pruned-moe-only-26-experts",
torch_dtype=torch.bfloat16,
device_map="cpu",
trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained("AmanPriyanshu/gpt-oss-17.3b-specialized-health_or_medicine-pruned-moe-only-26-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)
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-17.3b-specialized-health_or_medicine-pruned-moe-only-26-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-17.3b-specialized-health_or_medicine-pruned-moe-only-26-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)
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.float16
The following examples demonstrate the model's performance on health or medicine tasks:
Question: What are the main functions of the human heart?
Response:
<|channel|>analysis<|message|>Need concise answer.<|end|><|start|>assistant<|channel|>final<|message|>The human heart is a muscular pump that performs three core functions:
| Function | What it does | Why it matters |
|----------|--------------|----------------|
| **Pumping blood** | Contracts (systole) and relaxes (diastole) to move blood through the circulatory system. | Delivers oxygen, nutrients, hormones, and removes waste products to every cell. |
| **Maintaining blood pressure** | Generates enough force to keep blood moving against resistance in arteries and capillaries. | Keeps tissues perfused and prevents blood from pooling or collapsing. |
| **Regulating blood flow** | Adjusts stroke volume and heart rate in response to body demands (exercise, rest, stress). | Matches oxygen delivery to metabolic needs and maintains homeostasis. |
Together, these functions keep the body’s cells supplied, waste‑free, and operating at the right pressure and flow.<|return|>
Question: Explain the difference between bacteria and viruses.
Response:
<|channel|>analysis<|message|>Need concise explanation.<|end|><|start|>assistant<|channel|>final<|message|>**Bacteria vs. Viruses – the big differences**
| Feature | Bacteria | Viruses |
|--------|----------|---------|
| **Cellular status** | True cells – prokaryotic, with a cell membrane, cytoplasm, ribosomes, and a cell wall (often peptidoglycan). | Not cells – just a protein coat (capsid) surrounding genetic material (DNA or RNA). No membrane, no cytoplasm, no ribosomes. |
| **Size** | 0.5–5 µm (visible under a light microscope). | 20–300 nm (visible only with an electron microscope). |
| **Reproduction** | Self‑replicating by binary fission; can grow and divide in suitable media. | Cannot replicate on their own; must hijack a host cell’s machinery to produce new virions. |
| **Metabolism** | Metabolically active; can obtain energy from sugars, fats, proteins, or inorganic compounds. | No metabolism; rely entirely on the host cell’s enzymes and energy. |
| **Genetic material** | Usually a single circular chromosome (sometimes plasmids). | Either single‑stranded or double‑stranded DNA or RNA; often segmented. |
| **Life cycle** | Can live independently, form colonies, and develop biofilms. | Must infect a host cell, enter, replicate, assemble, and exit (lyse or budding). |
| **Antibiotic susceptibility** | Many antibiotics target bacterial cell walls, membranes, or protein synthesis. | Antibiotics are ineffective; antiviral drugs target specific viral enzymes or entry steps. |
| **Disease mechanisms** | Direct damage (toxins, enzymes), immune response to bacterial components, or secondary infections. | Direct damage from viral replication, immune‑mediated pathology, or viral toxins. |
| **Examples** | *Escherichia coli*, *Staphylococcus aureus*, *Mycobacterium tuberculosis*. | Influenza virus, HIV, SARS‑CoV‑2, HPV. |
**Bottom line:**
Bacteria are living, self‑sufficient cells that can grow and divide on their own. Viruses are acellular particles that are essentially “genetic parasites” – they need a living cell to replicate. This fundamental difference shapes how they cause disease, how we treat them, and how they evolve.<|return|>
Question: What are the symptoms and causes of diabetes?
Response:
<|channel|>analysis<|message|>Need to answer.<|end|><|start|>assistant<|channel|>final<|message|>**Diabetes mellitus** is a group of metabolic disorders characterized by chronic hyperglycemia (high blood sugar). The two most common types are type 1 and type 2, but there are other forms (gestational, monogenic, etc.). Below is a concise overview of the main symptoms, causes, and some additional context.
---
## 1. Symptoms
| Symptom | Typical Onset | Why It Happens |
|---------|---------------|----------------|
| **Polyuria** (frequent urination) | Early | Kidneys excrete excess glucose, pulling water out of the body. |
| **Polydipsia** (excessive thirst) | Early | Dehydration from fluid loss triggers thirst. |
| **Polyphagia** (increased hunger) | Early | Cells can’t use glucose, so the body signals for more food. |
| **Weight loss** (especially in type 1) | Early | Body breaks down fat and muscle for energy. |
| **Fatigue / weakness** | Early | Energy isn’t being efficiently used. |
| **Blurred vision** | Early‑mid | High glucose causes fluid shifts in the eye lens. |
| **Slow‑healing cuts or infections** | Mid‑to‑late | Poor circulation and immune function. |
| **Numbness or tingling in hands/feet** | Late | Chronic hyperglycemia damages nerves (diabetic neuropathy). |
| **Red, swollen, or painful gums** | Late | Diabetes worsens gum disease. |
| **Recurrent infections** (urinary, skin, vaginal) | Late | High glucose fuels bacterial growth. |
| **Darkened skin patches (acanthosis nigricans)** | Late | Often seen in insulin resistance. |
> **Note:** Many people with type 2 diabetes are asymptomatic for years; routine screening is essential, especially if risk factors are present.
---
## 2. Causes
### A. Type 1 Diabetes (T1D)
| Factor | Explanation |
|--------|-------------|
| **Autoimmune destruction of β‑cells** | The immune system mistakenly attacks insulin‑producing cells in the pancreas. |
| **Genetic predisposition** | Certain HLA genes (e.g., HLA‑DR3/DR4) increase risk. |
| **Environmental triggers** | Viral infections (e.g., enteroviruses), early exposure to cow’s milk,
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}
}