Downloads · 30 days
14
10% of all-time downloads
AmanPriyanshu/gpt-oss-6.6b-specialized-math-pruned-moe-only-8-experts
gpt-oss-6.6b-specialized-math-pruned-moe-only-8-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
14
10% of all-time downloads
All-time downloads
134
Public
Parameters
6.6B
13.2 GB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors13.2 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 8 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 math 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 | ~6.6B (pruned from 21B) |
| Original Experts per Layer | 32 |
| Pruned Experts per Layer | 8 |
| 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 | Math |
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 mathematics-focused model utilizes experts that exhibited strong performance on mathematical reasoning tasks from MMLU mathematics subjects and quantitative sections. These experts excel at mathematical computation, proof strategies, and logical reasoning.
The expert selection process utilized our comprehensive analysis of router activation patterns across multiple evaluation benchmarks:
By identifying experts that consistently activated for math tasks, we created this specialized model that maintains domain expertise while significantly reducing computational requirements from 32 to 8 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-6.6b-specialized-math-pruned-moe-only-8-experts",
torch_dtype=torch.bfloat16,
device_map="cpu",
trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained("AmanPriyanshu/gpt-oss-6.6b-specialized-math-pruned-moe-only-8-experts")
# Generate with the model
messages = [
{"role": "user", "content": "Solve this equation: 2x + 5 = 17. Show your work step by step."}
]
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-6.6b-specialized-math-pruned-moe-only-8-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-6.6b-specialized-math-pruned-moe-only-8-experts")
# Generate with the model
messages = [
{"role": "user", "content": "Solve this equation: 2x + 5 = 17. Show your work step by step."}
]
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 math tasks:
Question: Solve this equation: 2x + 5 = 17. Show your work step by step.
Response:
<|channel|>analysis<|message|>We need to produce a solution: 2x + 5 = 17. Show step by step. Provide explanation. Provide final answer.<|end|><|start|>assistant<|channel|>final<|message|>**Solve the equation**
\[
2x + 5 = 17
\]
---
### Step 1: Sub isolate the variable
1. **Subtract 5 from both sides**
\[
2x + 5 - 5 = 17 - 5
\]
2. **Simplify**
\[
2x = 12
\]
---
### Step 2: Divide the variable by 2
1. **Divide both sides by 2**
\[
\frac{2x}{2} = \frac{12}{2}
\]
2. **Simplify**
\[
x = 6
\]
---
### Final answer
\[
\boxed{x = 6}
\]<|return|>
Question: What is the Pythagorean theorem and how is it used?
Response:
<|channel|>analysis<|message|>Need to explain theorem and usage. Provide explanation, maybe mention formula, usage in geometry, maybe in distance, etc. Provide details.<|end|><|start|>assistant<|channel|>final<|message|>### The Pythagorean Theorem (or Pythag’s Law)
**Statement**
For a given two‑point (or two‑dimensional) triangle with a side lengths \(a\) and \(b\) and a hyp‑ (or diagonal) side \(c\),
\[
a^{2}+b^{2}=c^{2}\qquhr\text{or}\qquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqquqqu
Question: Calculate the area of a circle with radius 7 meters.
Response:
<|channel|>analysis<|message|>We need to compute area of circle with radius 7 meters. The area formula: A = π r^2. So r=7 m. r^2=49. Multiply π: 49π. So area = 49π m^2. Provide numeric approximate: 49 * 3.14159 = 154.159. So answer: 49π ≈ 154.2 m^2.<|end|><|start|>assistant<|channel|>final<|message|>The area of a circle with a radius of 7 m is given by the formula:
\[
A = \pi r^{2}
\]
Plugting in the radius:
\[
A = \pi (7\,\text{m})^{2} = \pi \times 49\,\text{m}^{2}
\]
So the area is:
\[
\boxed{49\pi \text{ m}^{2}}
\]
which is approximately:
\[
49 \times 3.14159 \approx 154.2 \text{ m}^{2}
\]<|return|>
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}
}