Downloads · 30 days
12
9% of all-time downloads
AmanPriyanshu/gpt-oss-19.7b-specialized-health_or_medicine-pruned-moe-only-30-experts
gpt-oss-19.7b-specialized-health_or_medicine-pruned-moe-only-30-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
12
9% of all-time downloads
All-time downloads
130
Public
Parameters
19.7B
39.5 GB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors39.4 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 30 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 | ~19.7B (pruned from 21B) |
| Original Experts per Layer | 32 |
| Pruned Experts per Layer | 30 |
| 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 30 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-19.7b-specialized-health_or_medicine-pruned-moe-only-30-experts",
torch_dtype=torch.bfloat16,
device_map="cpu",
trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained("AmanPriyanshu/gpt-oss-19.7b-specialized-health_or_medicine-pruned-moe-only-30-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-19.7b-specialized-health_or_medicine-pruned-moe-only-30-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-19.7b-specialized-health_or_medicine-pruned-moe-only-30-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 to answer.<|end|><|start|>assistant<|channel|>final<|message|>The human heart is a muscular pump that performs several essential functions to keep the circulatory system working efficiently. Its main functions can be grouped into three interrelated categories:
| Function | What it does | Why it matters |
|----------|--------------|----------------|
| **Pumping (circulation)** | • Generates rhythmic contractions (systole) that force blood out of the heart.<br>• Relaxation (diastole) allows the chambers to fill with blood. | Keeps blood moving through the body, delivering oxygen, nutrients, and hormones while removing waste products. |
| **Pressure regulation** | • Maintains arterial pressure (systolic) and venous pressure (diastolic) through coordinated contraction and relaxation.<br>• Works with the autonomic nervous system and hormonal signals (e.g., adrenaline, angiotensin II). | Ensures that blood reaches tissues at the right pressure; prevents damage to capillaries and organs. |
| **Blood distribution (circulatory routing)** | • Divides blood into two main circuits:<br> – **Pulmonary circuit**: de‑oxygenated blood goes to the lungs for gas exchange.<br> – **Systemic circuit**: oxygenated blood is delivered to the rest of the body.<br>• Uses valves (tricuspid, pulmonary, mitral, aortic) to keep flow unidirectional. | Guarantees that oxygen‑rich blood reaches every cell and that carbon dioxide and metabolic waste are carried back to the lungs and kidneys for elimination. |
### How the heart accomplishes these functions
1. **Electrical conduction system**
- **Sinoatrial (SA) node**: “pacemaker” that initiates the heartbeat.
- **Atrioventricular (AV) node, Bundle of His, Purkinje fibers**: conduct the impulse to the ventricles, coordinating contraction.
2. **Cardiac muscle (myocardium)**
- Contractile fibers generate force; their contraction is powered by ATP from oxygenated blood.
3. **Valves and chambers**
- **Right atrium → right ventricle → pulmonary artery → lungs → left atrium → left ventricle → aorta → body**.
- Valves prevent back‑flow, ensuring efficient forward movement.
4. **Autonomic regulation**
- Sympathetic stimulation increases heart rate and contractility (fight‑or
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 |
|---------|----------|---------|
| **Basic nature** | Living, single‑cell organisms (prokaryotes). | Non‑living particles; need a host cell to replicate. |
| **Size** | ~0.5–5 µm (visible under light microscope). | ~20–300 nm (visible only with electron microscope). |
| **Structure** | Cell wall, cell membrane, cytoplasm, ribosomes, DNA (circular or linear). | Protein coat (capsid) surrounding a nucleic acid core (DNA or RNA). No metabolic machinery. |
| **Reproduction** | Binary fission (self‑replication). | Hijack host cell’s replication machinery to produce new virions. |
| **Metabolism** | Can grow on nutrients, produce energy, respire, etc. | No metabolism; rely entirely on host cell. |
| **Genetic material** | DNA (sometimes plasmids). | DNA or RNA, single or double stranded. |
| **Response to antibiotics** | Many antibiotics target bacterial cell wall, protein synthesis, etc. | Antibiotics are ineffective; antiviral drugs target specific viral enzymes or entry steps. |
| **Disease mechanisms** | Direct damage, toxin production, immune activation. | Direct cell lysis, immune evasion, integration into host genome (retroviruses). |
| **Examples** | *Escherichia coli*, *Staphylococcus aureus*, *Mycobacterium tuberculosis*. | Influenza virus, HIV, SARS‑CoV‑2, HPV. |
**Bottom line:**
Bacteria are autonomous, living cells that can grow and reproduce on their own, whereas viruses are inert genetic packages that must invade a host cell to replicate. This fundamental difference shapes how we treat infections: antibiotics for bacteria, antivirals or vaccines for viruses.<|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 less common forms (gestational, MODY, etc.). Below is a concise overview of the main symptoms, causes, and some key differences between the types.
---
## 1. Symptoms (Signs)
| Symptom | Typical Onset | Why It Happens |
|---------|---------------|----------------|
| **Polyuria** (frequent urination) | Early | Kidneys excrete excess glucose, pulling water with it. |
| **Polydipsia** (excessive thirst) | Early | Dehydration from fluid loss. |
| **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 production is impaired. |
| **Blurred vision** | Early | Hyperglycemia causes fluid shifts in the lens. |
| **Slow‑healing cuts or infections** | Early‑mid | Poor blood flow and immune function. |
| **Numbness or tingling in extremities** | Mid‑to‑late | Peripheral neuropathy from chronic high glucose. |
| **Skin changes (dry, itchy, fungal infections)** | Mid‑to‑late | Hyperglycemia impairs skin barrier and immune response. |
| **Recurrent urinary tract or genital infections** | Mid‑to‑late | Glucose in urine provides a food source for bacteria/fungi. |
| **Eye problems (retinopathy, cataracts, glaucoma)** | Late | Chronic damage to retinal vessels and lens. |
| **Kidney problems (proteinuria, decreased GFR)** | Late | Glomerular damage from prolonged hyperglycemia. |
| **Cardiovascular disease (angina, heart attack, stroke)** | Late | Accelerated atherosclerosis. |
> **Tip:** In type 1 diabetes, symptoms often appear rapidly (days to weeks). In type 2, they can develop insidiously over months or years, sometimes going unnoticed until complications arise.
---
## 2. Causes & Risk Factors
| Category | Key Points |
|----------|------------|
| **Type
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}
}