GLM-4.7-202B

[!TIP] Support this work → · X · GitHub · REAP paper · Cerebras REAP

GLM-4.7-202B

REAP-pruned zai/glm-4.7.

At a glance

Which variant should I pick?

<p align="center"> <em>𓌳 <strong>REAP</strong>𓌳 the Experts: Why Pruning Prevails for One-Shot MoE Compression</em><br> <a href="https://arxiv.org/abs/2510.13999">📄 Paper</a> • <a href="https://github.com/CerebrasResearch/reap">💻 Code</a> • <a href="https://www.cerebras.ai/blog/reap">📝 Blog</a> </p>

GLM-4.7-REAP-45

✨ Highlights

45% Expert-Pruned GLM-4.7 optimized for code generation, function calling, and agentic workflows.

Created using REAP (Router-weighted Expert Activation Pruning) by Cerebras:

• 358B → 197B: 45% of MoE experts pruned (88/160 remaining)
• Calibrated for Code & Tools: Preserves coding and function-calling capabilities
• One-Shot Compression: No fine-tuning required
• Drop-in Compatible: Works with vLLM, Transformers, SGLang

📋 Model Specifications

---

🔬 Calibration Dataset: Deep Dive

REAP's effectiveness depends critically on calibration data that represents the target use case. We specifically optimized for code generation, function/tool calling, and agentic workflows.

Why These 3 Datasets?

The Science Behind Dataset Selection

REAP Algorithm:
1. Forward pass calibration samples through model
2. Record which experts activate and their magnitudes
3. Compute saliency = router_weight × activation_norm
4. Prune lowest-saliency experts

Key Insight: Experts are TASK-SPECIFIC
├── Some experts specialize in natural language
├── Some experts specialize in code syntax
├── Some experts specialize in JSON/structured output
└── Some experts specialize in multi-turn context

If calibration lacks code → code-specialized experts appear "unused" → get pruned → model loses coding ability

Cerebras' Original Mix (from paper)

Cerebras used the same 3 datasets in their GLM-4.6 REAP experiments:

• evol-codealpaca-v1 for code generation
• xlam-function-calling-60k for tool calling
• SWE-smith-trajectories for agentic tasks

We followed this exact recipe for reproducibility.

Combined Dataset

Our calibration mix: 0xSero/glm47-reap-calibration-v2

---

📦 Related Models

---

🚀 Deployment

vLLM (Recommended)

vllm serve 0xSero/GLM-4.7-202B \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --dtype bfloat16

Transformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "0xSero/GLM-4.7-202B",
    torch_dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained("0xSero/GLM-4.7-202B", trust_remote_code=True)

messages = [{"role": "user", "content": "Write a Python function to merge two sorted lists."}]
inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True)
outputs = model.generate(inputs.to(model.device), max_new_tokens=512, temperature=0.7)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

---

🧩 Reproduction

REAP Pruning Script

#!/usr/bin/env python3
"""
REAP Pruning Script for MoE Models
Adapted from: https://github.com/CerebrasResearch/reap
"""

import subprocess
import sys

def run_reap(
    model_path: str,
    compression_ratio: float,
    dataset: str = "0xSero/glm47-reap-calibration-v2",
    samples: int = 1360,
    seed: int = 42,
    distance: str = "angular",
    reuse_observations: str = None,
):
    """
    Run REAP expert pruning.

    Args:
        model_path: Path to base model
        compression_ratio: 0.30 = prune 30%, keep 70%
        dataset: Calibration dataset (code + tools + agentic)
        samples: Number of calibration samples
        seed: Random seed for reproducibility
        distance: Distance metric for expert clustering
        reuse_observations: Path to pre-computed observations for instant pruning
    """
    cmd = [
        sys.executable, "src/reap/prune.py",
        "--model-name", model_path,
        "--dataset-name", dataset,
        "--compression-ratio", str(compression_ratio),
        "--prune-method", "reap",
        "--seed", str(seed),
        "--samples_per_category", str(samples),
        "--model_max_length", "2048",
        "--distance_measure", distance,
        "--record_pruning_metrics_only", "true",
    ]

    if reuse_observations:
        # Instant pruning: skip calibration, reuse precomputed expert scores
        cmd.extend(["--load_observations", reuse_observations])

    subprocess.run(cmd, check=True)

# Example: Create 40% pruned model
run_reap(
    model_path="/path/to/GLM-4.7",
    compression_ratio=0.40,  # Prune 40% of experts
)

Observation Reuse (Instant Multi-Ratio Pruning)

REAP computes expert saliency scores during calibration. These scores are compression-ratio independent, enabling instant pruning at any ratio:

# First run: compute observations (~5 hours)
python prune.py --compression-ratio 0.40 --output_file_name observations.pt

# Subsequent runs: instant pruning (<5 minutes)
python prune.py --compression-ratio 0.30 --load_observations observations.pt
python prune.py --compression-ratio 0.50 --load_observations observations.pt

---

⚖️ License

Apache 2.0 (inherited from GLM-4)

---

License & citation

License inherited from the base model.

@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.