You can deploy this model and start earning money today!

AmanPriyanshu/
gpt-oss-7.8b-specialized-law-pruned-moe-only-10-experts

Name: gpt-oss-7.8b-specialized-law-pruned-moe-only-10-experts
Availability: InStock

Views

No views yet

Law GPT-OSS Model (10 Experts)

Project: https://amanpriyanshu.github.io/GPT-OSS-MoE-ExpertFingerprinting/

👥 Follow the Authors

Aman Priyanshu

Supriti Vijay

Introduction

This is a pruned variant of OpenAI's GPT-OSS-20B model, reduced to 10 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 law 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.

Model Architecture & Statistics

Metric	Value
Base Model	openai/gpt-oss-20b
Architecture	Mixture-of-Experts Transformer
Total Parameters	~7.8B (pruned from 21B)
Original Experts per Layer	32
Pruned Experts per Layer	10
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	Law

Pruning Methodology

What is Expert Pruning?

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:

Analyzing Usage Patterns: Tracking which experts activate most frequently for specific tasks
Removing Underutilized Experts: Discarding experts with low activation rates for the target domain
Preserving Router Functionality: Maintaining the routing mechanism with fewer available experts

Our Approach

Data-Driven Selection: Used activation patterns from law evaluation tasks
Systematic Reduction: Reduced from 32 to 10 experts per layer
No Retraining: Direct removal without additional training steps

Performance & Applications

Pruning Benefits

Smaller Memory Footprint: 31.2% of original expert parameters
Reduced Computational Load: Fewer routing decisions during inference
Focused Capabilities: Retains experts relevant to law tasks

Use Cases

Speculative Decoding: Draft model for full GPT-OSS-20B
Resource-Constrained Deployment: Edge devices, mobile applications
Research: Study expert specialization in MoE models
Fine-tuning: Smaller base model for domain adaptation

Note: Performance may vary depending on how well the pruned experts match your specific use case.

Motivation & Expert Selection

This legal domain model employs experts that demonstrated expertise during law-related tasks from MMLU legal subjects. These experts excel at legal reasoning, jurisprudence, and understanding of legal frameworks and procedures.

The expert selection process utilized our comprehensive analysis of router activation patterns across multiple evaluation benchmarks:

GPQA: Graduate-level questions in physics, chemistry, biology (Diamond & Expert subsets)
MMLU/MMLU-Pro: Comprehensive knowledge across 57+ subjects including science, medicine, law
SORRY-Bench: Safety evaluation across harmful content categories
Tulu3: Persona-driven instruction following with verifiable constraints
Polyglot-or-Not: Multilingual factual completion tasks

By identifying experts that consistently activated for law tasks, we created this specialized model that maintains domain expertise while significantly reducing computational requirements from 32 to 10 experts per layer.

Dataset & Analysis Foundation

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.

Pruning Methodology

Our approach involves:

Activation Analysis: Comprehensive evaluation of expert usage patterns across domain-specific tasks
Expert Ranking: Identification of the most frequently activated experts for target domains
Systematic Pruning: Reduction from 32 to 10 experts while preserving router functionality
Quality Validation: Testing to ensure maintained performance on target tasks

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.

Usage

CPU Inference

python

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load the specialized model on CPU
model = AutoModelForCausalLM.from_pretrained(
    "AmanPriyanshu/gpt-oss-7.8b-specialized-law-pruned-moe-only-10-experts", 
    torch_dtype=torch.bfloat16, 
    device_map="cpu", 
    trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained("AmanPriyanshu/gpt-oss-7.8b-specialized-law-pruned-moe-only-10-experts")

# Generate with the model
messages = [
    {"role": "user", "content": "What is the difference between civil and criminal law?"}
]

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)

Apple Silicon (MPS) Inference

python

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-7.8b-specialized-law-pruned-moe-only-10-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-7.8b-specialized-law-pruned-moe-only-10-experts")

# Generate with the model
messages = [
    {"role": "user", "content": "What is the difference between civil and criminal law?"}
]

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)

GPU Inference

For CUDA GPU inference, the models work with minimal modifications from the CPU example above. Simply change:

python

device_map="auto"  # Will automatically use GPU if available
torch_dtype=torch.bfloat16  # or torch.float16

Model Examples

The following examples demonstrate the model's performance on law tasks:

Example 1

Question: What is the difference between civil and criminal law?

Response:

<|channel|>analysis<|message|>Need explain difference: civil law deals disputes between private parties, damages, contracts, torts; criminal law deals offenses against society, punishments, prosecution by state. Also procedural differences, burden of proof, standard of proof, rights, remedies. Provide examples.<|end|><|start|>assistant<|channel|>final<|message|>**Short‑answer**

| **Civil law** | Dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑dis‑

Example 2

Question: Explain the concept of due process in legal systems.

Response:

<|channel|>analysis<|message|>Need explain due process concept.<|end|><|start|>assistant<|channel|>final<|message|>**Due process** (or *due process* in some jurisdictions) is a fundamental principle that guarantees that every person who is subject to legal action—whether criminal, civil, administrative, or otherwise—must be afforded a fair, impartial, and transparent legal procedure. In short, it means that the law must be applied *fairly* and *equently* to everyone, and that the courts and other authorities must follow a set of procedural rules that protect the rights of the parties involved.

---

## 1. What is “Due Process”?

|  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |

Example 3

Question: What are the basic rights protected by the First Amendment?

Response:

<|channel|>analysis<|message|>Need answer: First Amendment rights: freedom from slavery, freedom from unjust imprisonment, freedom from arbitrary searches, freedom from unreasonable searches, freedom from unreasonable seizures, freedom from unreasonable searches, freedom from unreasonable searches? Actually First Amendment: freedom from slavery, freedom from unjust imprisonment, freedom from arbitrary searches, freedom from unreasonable searches, freedom from unreasonable seizures, freedom from unreasonable searches? Wait: First Amendment: freedom from slavery, freedom from unjust imprisonment, freedom from arbitrary searches, freedom from unreasonable searches, freedom from unreasonable seizures, freedom from unreasonable searches? Actually: freedom from slavery, freedom from unjust imprisonment, freedom from arbitrary searches, freedom from unreasonable searches, freedom from unreasonable seizures, freedom from unreasonable searches? Might list: freedom from slavery, freedom from unjust imprisonment, freedom from arbitrary searches, freedom from unreasonable searches, freedom from unreasonable seizures, freedom from unreasonable searches? But better: freedom from slavery, freedom from unjust imprisonment, freedom from arbitrary searches, freedom from unreasonable searches, freedom from unreasonable seizures, freedom from unreasonable searches? Actually: freedom from slavery, freedom from unjust imprisonment, freedom from arbitrary searches, freedom from unreasonable searches, freedom from unreasonable seizures, freedom from unreasonable searches? This is repetitive. Let's answer: freedom from slavery, freedom from unjust imprisonment, freedom from arbitrary searches, freedom from unreasonable searches, freedom from unreasonable seizures, freedom from unreasonable searches? Probably they want: freedom from slavery, freedom from unjust imprisonment, freedom from arbitrary searches, freedom from unreasonable searches, freedom from unreasonable seizures, freedom from unreasonable searches? I'll give concise.<|end|><|start|>assistant<|channel|>final<|message|>The First Amendment protects a set of fundamental freedoms that are the core of American liberty. In short, it guarantees:

1. **Freedom from slavery** – no person may be owned or forced to work against their will.  
2. **Freedom from unjust imprisonment** – no person may be held in jail or other places of confinement without a lawful basis.  
3. **Freedom from arbitrary searches** – no person may be searched or investigated without a reasonable suspicion or probable cause.  
4. **Freedom from unreasonable searches** – no person may be subjected to intrusive investigations or surveillance without a proper legal justification.  
5. **Freedom from unreasonable seizures** – no person may have property or personal belongings taken without a lawful warrant or due to a legitimate legal claim.  

These rights form the foundation of the rest of the Constitution and are the basic protections that the First Amendment guarantees.<|return|>

Citation

If you use this model in your research, please cite:

bibtex

@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}
}

References & Resources

Original Model: OpenAI GPT-OSS Model Card
Model Hub: GPT-OSS-20B on Hugging Face
Expert Analysis Dataset: GPT-OSS-20B MoE Expert Activations
Project Page: GPT-OSS MoE Expert Fingerprinting
GitHub Repository: OpenAI GPT-OSS