Downloads · 30 days
11
8% of all-time downloads
AmanPriyanshu/gpt-oss-12.6b-specialized-health_or_medicine-pruned-moe-only-18-experts
gpt-oss-12.6b-specialized-health_or_medicine-pruned-moe-only-18-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
11
8% of all-time downloads
All-time downloads
130
Public
Parameters
12.6B
25.1 GB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors25.1 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 18 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 | ~12.6B (pruned from 21B) |
| Original Experts per Layer | 32 |
| Pruned Experts per Layer | 18 |
| 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 18 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-12.6b-specialized-health_or_medicine-pruned-moe-only-18-experts",
torch_dtype=torch.bfloat16,
device_map="cpu",
trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained("AmanPriyanshu/gpt-oss-12.6b-specialized-health_or_medicine-pruned-moe-only-18-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-12.6b-specialized-health_or_medicine-pruned-moe-only-18-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-12.6b-specialized-health_or_medicine-pruned-moe-only-18-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 performs two core functions:
1. **Pumping blood** – It acts as a mechanical pump that propels oxygen‑rich blood from the lungs to the rest of the body and returns oxygen‑poor blood back to the lungs for gas exchange.
2. **Regulating circulation** – By controlling the rate and force of contraction, the heart adjusts blood flow to meet the metabolic demands of tissues (e.g., during exercise, rest, or stress).<|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 key differences**
| Feature | Bacteria | Viruses |
|---|---|---|
| **Basic nature** | Single‑cell, living organisms (prokaryotes) | Non‑living particles (no cellular structure) |
| **Size** | ~1–10 µm (micrometers) | ~0.1–100 nm (nanometers) |
| **Structure** | Cell wall, membrane, cytoplasm, DNA genome, ribosomes, organelles (e.g., mitochondria) | Envelope (optional), capsid, nucleic acid genome (DNA or RNA), no ribosomes |
| **Replication** | Self‑replication by cell division (mitosis‑like process) | Replication inside a host cell using the host’s machinery |
| **Genetic material** | DNA (most) | DNA or RNA (single or double strand) |
| **Energy source** | Metabolism (can be autotrophic or heterotrophic) | No metabolism; relies entirely on host cell |
| **Infection mechanism** | Can colonize surfaces, produce toxins, or invade tissues; often spread by contact, food, water | Attach to specific host receptors, inject genetic material, hijack host cell |
| **Treatment** | Antibiotics (target cell wall, protein synthesis, etc.) | Antiviral drugs (target viral replication steps) or vaccines; antibiotics ineffective |
| **Evolutionary flexibility** | Can form biofilms, develop resistance via gene exchange | Rapid mutation rates (especially RNA viruses) → high antigenic change |
| **Examples** | *Staphylococcus aureus*, *E. coli*, *Bacillus subtilis* | Influenza, HIV, SARS‑CoV‑2, HPV |
**Bottom‑line takeaway:**
Bacteria are living cells that can grow and reproduce on their own, whereas viruses are tiny, non‑living particles that need a host cell to make copies of themselves. This fundamental difference shapes how we diagnose, treat, and prevent infections caused by each.<|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 chronic metabolic disorder in which the body cannot regulate blood glucose properly. The two main types—Type 1 and Type 2—have overlapping symptoms but different underlying causes. Below is a concise overview of the most common signs, symptoms, and the mechanisms that lead to each type.
---
## 1. Symptoms (Signs that may indicate diabetes)
| Symptom | Typical Onset | Why It Happens |
|---|---|---|
| **Polyuria** (frequent urination) | Early | High blood glucose spills into the urine; kidneys try to excrete the excess sugar, pulling water with it. |
| **Polydipsia** (excessive thirst) | Early | Dehydration from polyuria and osmotic diuresis stimulates thirst. |
| **Polyphagia** (increased hunger) | Early | Cells are starved for glucose; the brain signals hunger. |
| **Weight loss** (especially in Type 1) | Early | Body breaks down fat and muscle for energy when insulin is absent. |
| **Fatigue / Weakness** | Early | Energy cannot be efficiently used by cells. |
| **Blurred vision** | Early | Hyperglycemia causes fluid shifts in the eye’s lens. |
| **Slow wound healing** | Early | Poor circulation and impaired immune function. |
| **Recurrent infections** (especially yeast, urinary, skin) | Early | High glucose provides a food source for microbes; immune response is dampened. |
| **Peripheral neuropathy** (tingling, numbness, burning in feet) | Late | Chronic hyperglycemia damages nerves. |
| **Foot ulcers / Charcot foot** | Late | Neuropathy + poor circulation. |
| **Diabetic retinopathy** (vision loss) | Late | High glucose damages retinal blood vessels. |
| **Diabetic nephropathy** (protein in urine, high blood pressure) | Late | Glomerular damage from chronic hyperglycemia. |
| **Diabetic ketoacidosis (DKA)** (Type 1) | Acute | Severe insulin deficiency → fat breakdown → ketone buildup → metabolic acidosis. |
| **Hyperosmolar hyperglycemic syndrome (HHS)** (Type 2) | Acute | Extremely high glucose → severe dehydration, altered mental status. |
> **Note:** Many of these symptoms develop gradually, so early detection
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}
}