---
license: mit
base_model:
- zai-org/GLM-4-32B-0414
datasets:
- mit-han-lab/pile-val-backup
pipeline_tag: text-generation
tags:
- gptq
- vllm
- llmcompressor
- text-generation-inference
---

# GLM-4-32B-0414 Quantized with GPTQ (4-Bit weight-only, W4A16)

This repo contains GLM-4-32B-0414 quantized with asymmetric GPTQ to 4-bit to make it suitable for consumer hardware.

The model was calibrated with 2048 samples of max sequence length 4096 from the dataset [`mit-han-lab/pile-val-backup`](https://huggingface.co/datasets/mit-han-lab/pile-val-backup).

This is my very first quantized model, I welcome suggestions. 2048/4096 were chosen over the default of 512/2048 to minimize overfitting risk and maximize convergence.
They also happen to fit in my GPU.

Original Model:
  - [zai-org/GLM-4-32B-0414](https://huggingface.co/zai-org/GLM-4-32B-0414)

## 📥 Usage & Running Instructions

The model was tested with vLLM, here is a script suitable for 32GB VRAM GPUs.

```
export MODEL="mratsim/GLM-4-32B-0414.w4a16-gptq"
vllm serve "${MODEL}" \
  --served-model-name glm-4-32b \
  --gpu-memory-utilization 0.90 \
  --enable-prefix-caching \
  --enable-chunked-prefill \
  --max-model-len 130000 \
  --max_num_seqs 256 \
  --generation-config "${MODEL}" \
  --enable-auto-tool-choice --tool-call-parser pythonic \
  --rope-scaling '{"rope_type":"yarn","factor":4.0,"original_max_position_embeddings":32768}'
```

## 🔬 Quantization method

The llmcompressor library was used with the following recipe for asymmetric GPTQ:

```yaml
default_stage:
  default_modifiers:
    GPTQModifier:
      dampening_frac: 0.005
      config_groups:
        group_0:
          targets: [Linear]
          weights: {num_bits: 4, type: int, symmetric: false, group_size: 128, strategy: group,
            dynamic: false, observer: minmax}
      ignore: [lm_head]
```

and calibrated on 2048 samples, 4096 sequence length of [`mit-han-lab/pile-val-backup`](https://huggingface.co/datasets/mit-han-lab/pile-val-backup)