---
language:
- en
library_name: transformers
tags:
- MOE
- agentic
- cerebras
- code
- compression
- function-calling
- glm
- glm4
- pruning
- reap
license: apache-2.0
pipeline_tag: text-generation
base_model:
- zai/glm-4.7
---

> [!TIP]
> **[Support this work →](https://donate.sybilsolutions.ai)** · [X](https://x.com/0xsero) · [GitHub](https://github.com/0xsero) · [REAP paper](https://arxiv.org/abs/2510.13999) · [Cerebras REAP](https://huggingface.co/collections/cerebras/cerebras-reap)

# GLM-4.7-202B

REAP-pruned [zai/glm-4.7](https://huggingface.co/zai/glm-4.7).

## At a glance

| | |
|---|---|
| Base model | — |
| Format | BF16 |
| Total params | **202B** |
| Active / token | — |
| Experts / layer | 88 |
| Layers | 92 |
| Hidden size | 5120 |
| Context | 202,752 |
| On-disk size | 403 GB |

## Which variant should I pick?

| Variant | Format | Link |
|---|---|---|
| `GLM-4.7-185B` | BF16 | [link](https://huggingface.co/0xSero/GLM-4.7-185B) |
| `GLM-4.7-185B-W4A16` | W4A16 | [link](https://huggingface.co/0xSero/GLM-4.7-185B-W4A16) |
| `GLM-4.7-202B` **(this)** | BF16 | [link](https://huggingface.co/0xSero/GLM-4.7-202B) |
| `GLM-4.7-218B-W4A16` | W4A16 | [link](https://huggingface.co/0xSero/GLM-4.7-218B-W4A16) |
| `GLM-4.7-REAP-40-W4A16` | W4A16 | [link](https://huggingface.co/0xSero/GLM-4.7-REAP-40-W4A16) |

<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)](https://arxiv.org/abs/2510.13999)** 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

| Property | Value |
|----------|-------|
| **Base Model** | [zai/glm-4.7](https://huggingface.co/zai/glm-4.7) |
| **Architecture** | Sparse Mixture-of-Experts (SMoE) |
| **Original Parameters** | 358B |
| **Pruned Parameters** | 197B |
| **Compression** | 45% experts removed |
| **Experts per Layer** | 88 (was 160) |
| **MoE Layers** | 92 |
| **Activated Experts** | 8 per token |
| **Precision** | BF16 |
| **Disk Size** | ~370GB |
| **VRAM Required** | ~370GB |

---


## 🔬 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?

| Dataset | Samples | Purpose | Why It Matters |
|---------|---------|---------|----------------|
| [evol-codealpaca-v1](https://huggingface.co/datasets/theblackcat102/evol-codealpaca-v1) | 700 | Code generation | **51% of mix** — Code tasks activate specific expert pathways; pruning without code calibration destroys coding ability |
| [xlam-function-calling-60k](https://huggingface.co/datasets/Salesforce/xlam-function-calling-60k) | 330 | Function/tool calling | **24% of mix** — Tool use requires structured JSON output; experts handling schema generation must be preserved |
| [SWE-smith-trajectories](https://huggingface.co/datasets/SWE-bench/SWE-smith-trajectories) | 330 | Agentic multi-turn | **24% of mix** — Real SWE-bench trajectories with tool calls, file edits, and multi-step reasoning |

### 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](https://huggingface.co/datasets/0xSero/glm47-reap-calibration-v2)


---

## 📦 Related Models

| Model | Params | Experts | Size | Format |
|-------|--------|---------|------|--------|
| [GLM-4.7-REAP-30](https://huggingface.co/0xSero/GLM-4.7-REAP-30) | 251B | 112 | ~470GB | BF16 |
| [GLM-4.7-REAP-35](https://huggingface.co/0xSero/GLM-4.7-REAP-35) | 233B | 104 | ~439GB | BF16 |
| [GLM-4.7-REAP-40](https://huggingface.co/0xSero/GLM-4.7-REAP-40) | 218B | 96 | ~407GB | BF16 |
| [GLM-4.7-REAP-45](https://huggingface.co/0xSero/GLM-4.7-202B) | 197B | 88 | ~370GB | BF16 |
| [GLM-4.7-REAP-50](https://huggingface.co/0xSero/GLM-4.7-185B) | 179B | 80 | ~345GB | BF16 |
| [GLM-4.7-REAP-40-W4A16](https://huggingface.co/0xSero/GLM-4.7-REAP-40-W4A16) | 218B | 96 | ~108GB | GPTQ |
| [GLM-4.7-REAP-50-W4A16](https://huggingface.co/0xSero/GLM-4.7-185B-W4A16) | 179B | 80 | ~92GB | GPTQ |

---

## 🚀 Deployment

### vLLM (Recommended)

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

### Transformers

```python
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


```python
#!/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:

```bash
# 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.

```bibtex
@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**.