---
pipeline_tag: text-generation
language: arb
license: apache-2.0
tags:
  - trimmed
  - granite
  - granite-4.0
library_name: transformers
base_model: ibm-granite/granite-4.0-h-1b
base_model_relation: quantized
datasets:
  - lbourdois/fineweb-2-trimming
---

# granite-4.0-h-1b-arb-16384
This model is a **8.82% smaller** version of [ibm-granite/granite-4.0-h-1b](https://huggingface.co/ibm-granite/granite-4.0-h-1b) optimized for **Arabic** language via vocabulary size reduction using the [trimming](https://huggingface.co/blog/lbourdois/introduction-to-trimming) method.  
This trimmed model should perform similarly to the original model with only 16,384 tokens and a much smaller memory footprint. However, it may not perform well for other languages as tokens not commonly used in the selected languages were removed from the vocabulary.

## Model Statistics
| Metric | Original | Trimmed | Reduction |
|--------|----------|---------|-----------|
| **Vocabulary size** | 100,352 tokens | 16,384 tokens | **83.67%** |
| **Model size** | 1,461,538,368 params | 1,332,563,520 params | **8.82%** |

![image](https://raw.githubusercontent.com/lbourdois/blog/refs/heads/master/assets/images/Trimming/granite-4.0-h-1b-16384.png)

## Mining Dataset Statistics
- **Number of texts used for mining**: 200,000 texts  
- **Dataset**: [lbourdois/fineweb-2-trimming](https://huggingface.co/datasets/lbourdois/fineweb-2-trimming)

## Usage
```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

device = "cuda"
model_path = "alphaedge-ai/granite-4.0-h-1b-arb-16384"

tokenizer = AutoTokenizer.from_pretrained(model_path)
# drop device_map if running on CPU
model = AutoModelForCausalLM.from_pretrained(model_path, device_map=device)
model.eval()

# change input text as desired
chat = [
    {"role": "user", "content": "Your prompt in Arabic."},
]
chat = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)

# tokenize the text
input_tokens = tokenizer(chat, return_tensors="pt").to(device)

# generate output tokens
output = model.generate(**input_tokens, max_new_tokens=100)

# decode output tokens into text
output = tokenizer.batch_decode(output)
print(output[0])
```

## Citations

#### Granite 4.0
```
@misc{granite2025,
  author       = {IBM Research},
  title        = {Granite 4.0 Language Models},
  year         = {2025},
  howpublished = {https://github.com/ibm-granite/granite-4.0-language-models},
}
```

#### Trimming blog post
```
@misc{hf_blogpost_trimming,
      title={Introduction to Trimming}, 
      author={Loïck BOURDOIS and Tom AARSEN and Bram VANROY and Christopher AKIKI and Woojun JUNG and Manuel ROMERO and Prithiv SAKTHI},
      year={2026},
      url={https://huggingface.co/blog/lbourdois/introduction-to-trimming}, 
}
```