Downloads · 30 days
15
12% of all-time downloads
AmanPriyanshu/gpt-oss-13.1b-specialized-law-pruned-moe-only-19-experts
gpt-oss-13.1b-specialized-law-pruned-moe-only-19-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
15
12% of all-time downloads
All-time downloads
122
Public
Parameters
13.1B
26.3 GB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors26.3 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 19 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 | ~13.1B (pruned from 21B) |
| Original Experts per Layer | 32 |
| Pruned Experts per Layer | 19 |
| 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 19 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-13.1b-specialized-law-pruned-moe-only-19-experts",
torch_dtype=torch.bfloat16,
device_map="cpu",
trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained("AmanPriyanshu/gpt-oss-13.1b-specialized-law-pruned-moe-only-19-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-13.1b-specialized-law-pruned-moe-only-19-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-13.1b-specialized-law-pruned-moe-only-19-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 consequences. Below is a clear comparison of the key differences:
| Feature | Civil Law | Criminal Law |
|---|---|---|
| **Purpose / Goal** | To resolve disputes between private parties (individuals, businesses, organizations) and to compensate or protect the injured party. | To maintain public order, punish wrongdoing, and deter future offenses. |
| **Parties Involved** | Plaintiff (the person or entity that claims harm) vs. Defendant (the person or entity accused of causing harm). | State (or government) as the prosecutor vs. Defendant (the accused). |
| **Burden of Proof** | **Pre‑tender**: “preponderance of evidence” (more likely than less). | **Beyond a reasonable doubt** (the highest standard). |
| **Typical Cases** | Contract disputes, property disputes, torts (negligence, defamation), family matters (divorce, child custody), estate/administration, civil injury claims. | Theft, assault, murder, fraud, drug offenses, traffic violations, white‑collar crimes. |
| **Remedies / Outcomes** | Monetary damages, injunctions, specific performance, restitution, or other equitable relief. | Penalties such as fines, probation, community service, imprisonment, or, in some jurisdictions, death penalty. |
| **Procedure** | Usually starts with a civil complaint filed in a civil court; parties may negotiate, mediate, or go to trial. | Begins with an arrest or indictment; the prosecution presents evidence; the defendant may plead guilty or be tried. |
| **Rights of the Defendant** | Right to a civil trial, to present evidence, to be represented by counsel. | Right to a criminal trial, right to counsel, right to remain silent, right to a jury (in many jurisdictions). |
| **Appeals** | Appeals are typically to higher civil courts; the standard of review may differ. | Appeals are to higher criminal courts; the standard of review is often “de novo” or “abovetext.” |
| **Time & Cost** | Often longer and more expensive due to discovery, expert witnesses, and complex legal arguments. | Can be quicker (especially for misdemeanors) but may involve extensive pre‑trial investigations. |
| **
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**—often called *due process* or *due process rights*—is a fundamental principle that guarantees fair, lawful, and transparent treatment of individuals by the state or by other actors that exercise public power. It is a cornerstone of the rule of law and a safeguard against arbitrary or abusive exercise of authority. Below is a concise yet comprehensive overview of the concept, its origins, its components, and how it operates in modern legal systems.
---
## 1. What is Due Process?
- **Definition**:
*Due process* refers to the set of procedural safeguards that must be observed before a person’s rights, property, or liberty can be taken, altered, or restricted by a governmental or quasi‑governmental authority.
- **Purpose**:
- Protect individuals from arbitrary or capricious decisions.
- Ensure that decisions are made through a fair, impartial, and transparent process.
- Provide the affected person an opportunity to be heard and to challenge the decision.
---
## 2. Historical Roots
| **Origin** | **Key Milestones** |
|------------|-------------------|
| **Roman Law** | *Principium de lege* – “the law is the law.” |
| **English Common Law** | *Rule of Law* – *Rule of Justice* (e.g., *R v. Dudley*). |
| **American Revolution** | *Declaration of Independence* (“no man shall be… deprived of life, liberty, or property without due process”). |
| **U.S. Constitution** | 5th & 14th Amendments – *Due Process Clauses*. |
| **European Convention on Human Rights** | Article 6 – *Right to a Fair Trial*. |
| **International Human Rights Law** | ICCPR, ICCPR, ICCPR, ICCPR. |
---
## 3. Core Elements of Due Process
| **Element** | **Explanation** | **Typical Legal Requirement** |
|-------------|-----------------|------------------------------|
| **Notice** | The person must be informed of the action, the allegations, and the time and place of any hearing. | Written notice, public posting, or oral notification. |
| **Opportunity to Respond** | The individual must be allowed to present evidence, argue, and cross‑examine witnesses. | Oral or written submissions, trial, hearing. |
| **Impartiality** | The decision‑
Question: What are the basic rights protected by the First Amendment?
Response:
<|channel|>analysis<|message|>Need to answer: freedom of religion, speech, press, assembly, petition.<|end|><|start|>assistant<|channel|>final<|message|>The First Amendment to the U.S. Constitution protects several core civil liberties. In plain terms, it guarantees:
| Right | What it means |
|--------|--------------|
| **Freedom of religion** | The government may not establish a state religion or interfere with an individual’s right to practice (or not practice) any religion. |
| **Freedom of speech** | Individuals may express opinions, ideas, and information without fear of government censorship or punishment. |
| **Freedom of the press** | Newspapers, books, radio, television, and other media can publish and broadcast content freely, subject only to very narrow limits (e.g., defamation, obscenity, inciting violence). |
| **Freedom of assembly** | People may gather peacefully for protest, demonstration, or other collective activities. |
| **Right to petition** | Citizens can petition the government for redress of grievances, including writing to elected officials, lobbying, or filing lawsuits. |
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}
}