Downloads · 30 days
364
53% of all-time downloads
AmanPriyanshu/gpt-oss-4.8b-specialized-all-pruned-moe-only-5-experts
gpt-oss-4.8b-specialized-all-pruned-moe-only-5-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
364
53% of all-time downloads
All-time downloads
684
Public
Parameters
4.8B
9.6 GB on disk
Likes
2
Public
Click a slice to open those files.
.safetensors9.6 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 5 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 all 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 | ~4.8B (pruned from 21B) |
| Original Experts per Layer | 32 |
| Pruned Experts per Layer | 5 |
| 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 | All |
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 general-purpose model maintains broad capabilities across all domains while significantly reducing computational requirements. It preserves the essential routing patterns discovered across our comprehensive analysis of diverse evaluation benchmarks including GPQA, MMLU, SORRY-Bench, and Tulu3 datasets.
The expert selection process utilized our comprehensive analysis of router activation patterns across multiple evaluation benchmarks:
By identifying experts that consistently activated for all tasks, we created this specialized model that maintains domain expertise while significantly reducing computational requirements from 32 to 5 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-4.8b-specialized-all-pruned-moe-only-5-experts",
torch_dtype=torch.bfloat16,
device_map="cpu",
trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained("AmanPriyanshu/gpt-oss-4.8b-specialized-all-pruned-moe-only-5-experts")
# Generate with the model
messages = [
{"role": "user", "content": "What is artificial intelligence and how does it work?"}
]
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-4.8b-specialized-all-pruned-moe-only-5-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-4.8b-specialized-all-pruned-moe-only-5-experts")
# Generate with the model
messages = [
{"role": "user", "content": "What is artificial intelligence and how does it work?"}
]
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 all tasks:
Question: What is artificial intelligence and how does it work?
Response:
<|channel|>analysis<|message|>We need to answer: "What is artificial intelligence and how does it work?" The user wants to explain what AI and how it works. Provide explanation, maybe mention the concept, algorithm, etc. Provide a simple explanation. Provide details. Provide mention of how it works: algorithmic, data, etc. Provide mention of how it works: classification, etc. Provide mention of how it works: how it uses data, etc. Provide mention of how it works: how it uses algorithmic processes. Provide mention of how it works: how it uses pattern recognition. Provide mention of how it works: how it uses computing. Provide mention of how it works: how it uses etc. Provide mention of how it works: how it uses. Provide mention of how it works: how it uses. Provide mention of how it works: how it uses. Provide mention of how it works: how it uses. Provide mention of how it works: how it uses. Provide mention of how it works: how it uses. Provide mention of how it works: how it uses. Provide mention of how it works: how it uses. Provide mention of how it works: how it uses. Provide mention of how it works: how it uses. Provide mention of how it works: how it uses. Provide mention of how it works: how it uses. Provide mention of how it works: how it uses. Provide mention of how it works: how it uses. Provide mention of how it works: how it uses. Provide mention of how it works: how it uses. Provide mention of how it works: how it uses. Provide mention of how it works: how it uses. Provide mention of how it works: how it uses. Provide mention of how it works: how it uses. Provide mention of how it works: how it uses. Provide mention of how it works: how it uses. Provide mention of how it works: how it uses. Provide mention of how it works: how it uses. Provide mention of how it works: how it uses. Provide mention of how it works: how it uses. Provide mention of how it works: how it uses. Provide mention of how it works: how it uses. Provide mention of how it works: how it uses. Provide mention of how it works: how it uses. Provide mention of how it works: how it uses. Provide mention of how it works: how it uses. Provide mention of how it works: how it uses. Provide mention of how it works: how
Question: Explain Einstein's theory of relativity in simple terms.
Response:
<|channel|>analysis<|message|>We need to explain Einstein's theory of relativity in simple terms. The user wants a simple explanation. We should explain what Einstein's theory of relativity is about the concept of relatational physics, the idea that the universe is not a finite space, and that the physics is governed by the laws of the universe. We can mention that Einstein's theory of relativity is about that the universe is not a finite space, and that the physics is governed by the laws of the universe. We can mention that Einstein's theory of relativity is about that the universe is not a finite space, and that the physics is governed by the laws of the universe. We can mention that Einstein's theory of relativity is about that the universe is not a finite space, and that the physics is governed by the laws of the universe. We can mention that Einstein's theory of relativity is about that the universe is not a finite space, and that the physics is governed by the laws of the universe. We can mention that Einstein's theory of relativity is about that the universe is not a finite space, and that the physics is governed by the laws of the universe. We can mention that Einstein's theory of relativity is about that the universe is not a finite space, and that the physics is governed by the laws of the universe. We can mention that Einstein's theory of relativity is about that the universe is not a finite space, and that the physics is governed by the laws of the universe. We can mention that Einstein's theory of relativity is about that the universe is not a finite space, and that the physics is governed by the laws of the universe. We can mention that Einstein's theory of relativity is about that the universe is not a finite space, and that the physics is governed by the laws of the universe. We can mention that Einstein's theory of relativity is about that the universe is not a finite space, and that the physics is governed by the laws of the universe. We can mention that Einstein's theory of relativity is about that the universe is not a finite space, and that the physics is governed by the laws of the universe. We can mention that Einstein's theory of relativity is about that the universe is not a finite space, and that the physics is governed by the laws of the universe. We can mention that Einstein's theory of relativity is about that the universe is not a finite space, and that the physics is governed by the laws of the universe. We can mention
Question: How does democracy function in modern governments?
Response:
<|channel|>analysis<|message|>We need to answer: "How does democracy function in modern governments?" The user wants to explain how democracy functions in modern governments. Provide a detailed explanation. Should be helpful. Provide a structured explanation. Use examples. Provide a bullet list. Provide a mention of the role of democratic institutions. Provide mention of the role of representation, checks, etc. Provide mention of the role of the checks. Provide mention of the role of the checks. Provide mention of the role of the checks. Provide mention of the role of the checks. Provide mention of the role of the checks. Provide mention of the role of the checks. Provide mention of the role of the checks. Provide mention of the role of the checks. Provide mention of the role of the checks. Provide mention of the role of the checks. Provide mention of the role of the checks. Provide mention of the role of the checks. Provide mention of the role of the checks. Provide mention of the role of the checks. Provide mention of the role of the checks. Provide mention of the role of the checks. Provide mention of the role of the checks. Provide mention of the role of the checks. Provide mention of the role of the checks. Provide mention of the role of the checks. Provide mention of the role of the checks. Provide mention of the role of the checks. Provide mention of the role of the checks. Provide mention of the role of the checks. Provide mention of the role of the checks. Provide mention of the role of the checks. Provide mention of the role of the checks. Provide mention of the role of the checks. Provide mention of the role of the checks. Provide mention of the role of the checks. Provide mention of the role of the checks. Provide mention of the role of the checks. Provide mention of the role of the checks. Provide mention of the role of the checks. Provide mention of the role of the checks. Provide mention of the role of the checks. Provide mention of the role of the checks. Provide mention of the role of the checks. Provide mention of the role of the checks. Provide mention of the role of the checks. Provide mention of the role of the checks. Provide mention of the role of the checks. Provide mention of the role of the checks. Provide mention of the role of the checks. Provide mention of the role of the checks. Provide mention of the role of the checks. Provide mention of the role of the checks. Provide mention of the role of the checks. Provide mention of the role of the
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}
}