Downloads · 30 days
11
9% of all-time downloads
AmanPriyanshu/gpt-oss-17.9b-specialized-law-pruned-moe-only-27-experts
gpt-oss-17.9b-specialized-law-pruned-moe-only-27-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
9% of all-time downloads
All-time downloads
124
Public
Parameters
17.9B
35.9 GB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors35.9 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 27 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.
| Metric | Value |
|---|---|
| Base Model | openai/gpt-oss-20b |
| Architecture | Mixture-of-Experts Transformer |
| Total Parameters | ~17.9B (pruned from 21B) |
| Original Experts per Layer | 32 |
| Pruned Experts per Layer | 27 |
| 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 |
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 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:
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 27 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-17.9b-specialized-law-pruned-moe-only-27-experts",
torch_dtype=torch.bfloat16,
device_map="cpu",
trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained("AmanPriyanshu/gpt-oss-17.9b-specialized-law-pruned-moe-only-27-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)
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-17.9b-specialized-law-pruned-moe-only-27-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-17.9b-specialized-law-pruned-moe-only-27-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)
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 law tasks:
Question: What is the difference between civil and criminal law?
Response:
<|channel|>analysis<|message|>Need explain difference.<|end|><|start|>assistant<|channel|>final<|message|>**Civil law** and **criminal law** are two distinct branches of the legal system that serve different purposes, involve different parties, and have different procedures and outcomes. Below is a concise comparison of the key differences:
| Feature | Civil Law | Criminal Law |
|---------|-----------|--------------|
| **Purpose** | To resolve disputes between private parties (individuals, businesses, organizations) and to compensate the injured party. | To protect society by punishing conduct that is deemed harmful or dangerous to the public. |
| **Parties** | Plaintiff (the party bringing the claim) vs. Defendant (the party being sued). | State or government (prosecution) vs. Defendant (the accused). |
| **Burden of Proof** | “Preponderance of the evidence” – more likely than not (about 51%+). | “Beyond a reasonable doubt” – a very high standard (the prosecution must convince the judge/jury that there is no reasonable doubt of guilt). |
| **Outcome** | Typically monetary damages, injunctions, or specific performance (ordering a party to do or not do something). | Penalties such as fines, probation, community service, imprisonment, or, in some jurisdictions, the death penalty. |
| **Procedure** | Generally less formal, often starts with a civil complaint filed in a civil court. | Formal criminal proceedings: arrest, arraignment, pre‑trial motions, trial, sentencing. |
| **Rights of the Defendant** | Right to a fair trial, but the defendant is not presumed guilty. | Presumption of innocence; the defendant must prove innocence only in cases of civil‑law‑like “reverse burden” (rare). |
| **Evidence Rules** | More flexible; hearsay may be admissible if it is relevant. | Strict rules; hearsay is usually inadmissible unless it falls under an exception. |
| **Appeals** | Usually appeal to a higher civil court; remedies may be limited to monetary damages. | Appeals can go to higher criminal courts; the state may appeal a conviction or sentence. |
| **Examples of Cases** | Breach of contract, property disputes, personal injury, divorce, landlord‑tenant disputes. | Murder, assault, theft, fraud, drug offenses, traffic violations. |
### Key Take‑aways
1. **Who is involved?**
- *Civil*: Private parties.
- *Criminal*: The state prosecutes
Question: Explain the concept of due process in legal systems.
Response:
<|channel|>analysis<|message|>Need explain due process.<|end|><|start|>assistant<|channel|>final<|message|>**Due process** is a foundational principle that guarantees fair treatment under the law. It is a constitutional safeguard—found in the U.S. Constitution’s Fifth and Fourteenth Amendments, and in many other countries’ legal frameworks—that requires the state to follow established legal procedures before depriving a person of life, liberty, or property. In essence, it is the legal guarantee that the government must act fairly, transparently, and with respect for individual rights when it exercises its power.
---
## 1. What “Due Process” Means
| **Aspect** | **Explanation** | **Typical Examples** |
|------------|-----------------|----------------------|
| **Procedural Due Process** | The right to a fair procedure before the state acts. | Notice of charges, right to be heard, impartial judge, opportunity to present evidence, right to appeal. |
| **Substantive Due Process** | The right that laws themselves are fair and not arbitrary. | Laws that are overly vague, discriminatory, or violate fundamental rights (e.g., laws that criminalize speech without clear limits). |
| **Natural Justice** | The idea that justice must be administered in a manner that is both fair and perceived as fair. | “Rule of law,” “rule of law” principles, “no one is above the law.” |
---
## 2. Historical Roots
| **Period** | **Key Development** | **Impact on Due Process** |
|------------|---------------------|---------------------------|
| **17th–18th century** | English common law and the Magna Carta (1215) | Established that the king could not arbitrarily seize property or imprison without a fair trial. |
| **1787–1791** | U.S. Constitution & Bill of Rights | The Fifth Amendment (federal) and Fourteenth Amendment (state) embed due process clauses. |
| **19th century** | Supreme Court cases (e.g., *Ex parte Milligan*, *Miller v. Alabama*) | Clarified that due process applies to both criminal and civil actions, and that procedural safeguards are required before deprivation of liberty. |
| **20th century** | Civil rights era, *Miranda v. Arizona* (1966) | Expanded procedural due process to include rights such as the right to counsel and the right to remain silent. |
| **21st century** | Digital age, data privacy
Question: What are the basic rights protected by the First Amendment?
Response:
<|channel|>analysis<|message|>Need to answer: rights: freedom of religion, speech, press, assembly, petition.<|end|><|start|>assistant<|channel|>final<|message|>The First Amendment to the United States Constitution protects a handful of core civil liberties that are considered essential to a free and democratic society. In plain terms, it guarantees:
| Right | What it means |
|-------|---------------|
| **Freedom of Religion** | Individuals may practice any religion, or none at all, and the government may not establish a state religion or favor one faith over another. |
| **Freedom of Speech** | People can express ideas, opinions, and information without fear of government censorship or punishment (subject to certain well‑defined limits such as incitement, defamation, or obscenity). |
| **Freedom of the Press** | Newspapers, books, radio, television, and other media can publish news and viewpoints without government interference. |
| **Freedom of Assembly** | Citizens may gather peacefully for protests, rallies, or other collective actions. |
| **Right to Petition the Government** | Individuals can request the government to address grievances, ask for changes in law, or seek redress for wrongs. |
These five freedoms together form the core of the First Amendment’s protection of individual liberty and democratic participation.<|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}
}