Downloads · 30 days
15
12% of all-time downloads
AmanPriyanshu/gpt-oss-20.3b-specialized-law-pruned-moe-only-31-experts
gpt-oss-20.3b-specialized-law-pruned-moe-only-31-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
20.3B
40.7 GB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors40.6 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 31 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 | ~20.3B (pruned from 21B) |
| Original Experts per Layer | 32 |
| Pruned Experts per Layer | 31 |
| 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 31 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-20.3b-specialized-law-pruned-moe-only-31-experts",
torch_dtype=torch.bfloat16,
device_map="cpu",
trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained("AmanPriyanshu/gpt-oss-20.3b-specialized-law-pruned-moe-only-31-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-20.3b-specialized-law-pruned-moe-only-31-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-20.3b-specialized-law-pruned-moe-only-31-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 to explain differences.<|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 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, maintain public order, and punish wrongdoing that violates criminal statutes. |
| **Parties Involved** | 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 (≈51%+). | “Beyond a reasonable doubt” – a very high standard of certainty. |
| **Typical Cases** | Breach of contract, property disputes, torts (negligence, defamation), family matters (divorce, child custody), landlord‑tenant issues. | Theft, assault, murder, fraud, drug offenses, traffic violations that are criminalized. |
| **Outcome / Remedy** | Usually monetary damages or an order to do or refrain from doing something (injunction). | Penalties such as fines, probation, community service, imprisonment, or death (in jurisdictions that allow it). |
| **Procedure** | Civil courts (often trial courts) with a judge or jury; parties present evidence and arguments; parties may be represented by attorneys but can also represent themselves. | Criminal courts (often trial courts) with a judge or jury; prosecution must prove guilt; defendant has constitutional rights (e.g., right to counsel, right to remain silent). |
| **Appeals** | Usually appeal to a higher civil court; the standard of review may differ. | Appeals are typically to higher criminal courts; the appellate court reviews legal errors, not factual findings. |
| **Timing** | Statutes of limitations often apply (e.g., 3–6 years for many torts). | Statutes of limitations may also apply, but some crimes (e.g., murder) are timeless. |
| **Evidence Rules** | Generally more flexible; hearsay may be admissible if it is relevant. | Strict rules; hearsay is usually inadmissible unless it falls under an exception. |
| **Role
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 through the normal judicial system, especially as a citizen’s entitlement to a fair trial and protection against arbitrary or unjust actions by the state. It is a safeguard embedded in many legal systems—most notably in the U.S. Constitution (5th and 14th Amendments) and in international human‑rights instruments such as the Universal Declaration of Human Rights (Article 10) and the International Covenant on Civil and Political Rights (Article 9).
---
## 1. Two Faces of Due Process
| Aspect | Meaning | Key Elements |
|--------|---------|--------------|
| **Procedural Due Process** | Fairness of the procedures used to enforce laws. | Notice, opportunity to be heard, impartial decision‑makers, right to appeal, evidence rules, and the right to counsel. |
| **Substantive Due Process** | Protection of fundamental rights from unreasonable government interference, even if procedures are fair. | Certain rights (e.g., privacy, marriage, bodily integrity) are protected against laws that are not justified by a compelling state interest. |
---
## 2. Core Components
| Component | What it Ensures | Typical Legal Requirements |
|-----------|-----------------|----------------------------|
| **Notice** | Individuals must know what law or action is being taken against them. | Written notice, public posting, or other reasonable means. |
| **Hearing** | Opportunity to present evidence and argue one’s case. | Oral or written submissions, cross‑examination, and the right to confront witnesses. |
| **Impartial Tribunal** | Decision made by a neutral judge or jury. | No conflict of interest, unbiased adjudication. |
| **Right to Counsel** | Access to legal representation. | Especially in criminal cases; sometimes in civil matters. |
| **Right to Appeal** | Ability to challenge a decision. | Appeals courts, appellate procedures. |
| **Reasoned Decision** | Judgment must be based on facts and law. | Written opinions, legal reasoning. |
---
## 3. Historical Development
| Era | Milestone | Impact |
|-----|-----------|--------|
| **17th–18th c. England** | *Bill of Rights* (1689) | Established limits on arbitrary royal power. |
| **U.S. Constitution (1791)** | 5th & 14th Amendments | Introduced procedural due process; later expanded
Question: What are the basic rights protected by the First Amendment?
Response:
<|channel|>analysis<|message|>Need to list rights: freedom of religion, speech, press, assembly, petition.<|end|><|start|>assistant<|channel|>final<|message|>The First Amendment to the United States Constitution protects five core freedoms that are considered fundamental to a democratic society. These rights are:
| # | Right | Key Elements |
|---|-------|--------------|
| 1 | **Freedom of Religion** | • **Establishment Clause** – The government may not establish an official religion or favor one religion over another. <br>• **Free‑Exercise Clause** – Individuals may practice any religion (or none) without government interference. |
| 2 | **Freedom of Speech** | • Individuals may express opinions, ideas, and information without censorship or punishment, subject to limited restrictions (e.g., incitement, defamation, obscenity). |
| 3 | **Freedom of the Press** | • The press can publish news, opinions, and investigative reporting without prior restraint or censorship by the government. |
| 4 | **Freedom of Assembly** | • People may gather peacefully for protests, demonstrations, or other collective activities. |
| 5 | **Freedom to Petition the Government** | • Citizens can request changes, express grievances, or seek redress from the government without fear of retaliation. |
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}
}