At a glance

50% expert-pruned version of PrimeIntellect/INTELLECT-3 using Cerebras REAP (Router-weighted Expert Activation Pruning).

Model Details

REAP Configuration

yaml
Copy code
dataset: 0xSero/glm47-reap-calibration-v2
samples: 1360
  - evol-codealpaca-v1: 700 (code generation)
  - xlam-function-calling-60k: 330 (function calling)
  - SWE-smith-trajectories: 330 (agentic multi-turn)
distance_measure: angular
seed: 42
model_max_length: 2048
compression_ratio: 0.50
prune_method: reap

Usage

python
Copy code
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "0xSero/INTELLECT-3-57B",
    torch_dtype="auto",
    device_map="auto",
    trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained("0xSero/INTELLECT-3-57B", trust_remote_code=True)

messages = [{"role": "user", "content": "Write a Python function to calculate fibonacci numbers"}]
inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True).to(model.device)
outputs = model.generate(inputs, max_new_tokens=512)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Related Models

License & citation

License inherited from the base model.

bibtex
Copy code
@misc{lasby2025reap,
  title  = {REAP the Experts: Why Pruning Prevails for One-Shot MoE Compression},
  author = {Mike Lasby and Ivan Lazarevich and Nish Sinnadurai and Sean Lie and Yani Ioannou and Vithursan Thangarasa},
  year   = {2025}, eprint = {2510.13999}, archivePrefix = {arXiv}
}

Sponsors

Made possible by NVIDIA · TNG Technology · Lambda · Prime Intellect · Hot Aisle.