README.md

---
pipeline_tag: text-generation
inference: false
license: apache-2.0
# datasets:
# metrics:
# - code_eval
library_name: transformers
tags:
- language
- granite-3.0
model-index:
- name: granite-3.0-2b-base
  results:
  - task:
      type: text-generation
    dataset:
        type: human-exams
        name: MMLU
    metrics:
    - name: pass@1
      type: pass@1
      value: 55.00
      veriefied: false
  - task:
      type: text-generation
    dataset:
        type: human-exams
        name: MMLU-Pro
    metrics:
    - name: pass@1
      type: pass@1
      value: 23.64
      veriefied: false
  - task:
      type: text-generation
    dataset:
        type: human-exams
        name: AGI-Eval
    metrics:
    - name: pass@1
      type: pass@1
      value: 21.75
      veriefied: false
  - task:
      type: text-generation
    dataset:
        type: commonsense
        name: WinoGrande
    metrics:
    - name: pass@1
      type: pass@1
      value: 71.59
      veriefied: false
  - task:
      type: text-generation
    dataset:
        type: commonsense
        name: OBQA 
    metrics:
    - name: pass@1
      type: pass@1
      value: 42.80
      veriefied: false
  - task:
      type: text-generation
    dataset:
        type: commonsense
        name: SIQA
    metrics:
    - name: pass@1
      type: pass@1
      value: 59.84
      veriefied: false
  - task:
      type: text-generation
    dataset:
        type: commonsense
        name: PIQA
    metrics:
    - name: pass@1
      type: pass@1
      value: 79.27
      veriefied: false
  - task:
      type: text-generation
    dataset:
        type: commonsense
        name: Hellaswag
    metrics:
    - name: pass@1
      type: pass@1
      value: 75.76
      veriefied: false
  - task:
      type: text-generation
    dataset:
        type: commonsense
        name: TruthfulQA
    metrics:
    - name: pass@1
      type: pass@1
      value: 39.90
      veriefied: false
  - task:
      type: text-generation
    dataset:
        type: reading-comprehension
        name: BoolQ
    metrics:
    - name: pass@1
      type: pass@1
      value: 81.35
      veriefied: false
  - task:
      type: text-generation
    dataset:
        type: reading-comprehension
        name: SQuAD v2
    metrics:
    - name: pass@1
      type: pass@1
      value: 25.22
      veriefied: false
  - task:
      type: text-generation
    dataset:
        type: reasoning
        name: ARC-C
    metrics:
    - name: pass@1
      type: pass@1
      value: 47.61
      veriefied: false
  - task:
      type: text-generation
    dataset:
        type: reasoning
        name: GPQA
    metrics:
    - name: pass@1
      type: pass@1
      value: 29.19
      veriefied: false
  - task:
      type: text-generation
    dataset:
        type: reasoning
        name: BBH
    metrics:
    - name: pass@1
      type: pass@1
      value: 46.89
      veriefied: false
  - task:
      type: text-generation
    dataset:
        type: code
        name: HumanEval
    metrics:
    - name: pass@1
      type: pass@1
      value: 31.71
      veriefied: false
  - task:
      type: text-generation
    dataset:
        type: code
        name: MBPP
    metrics:
    - name: pass@1
      type: pass@1
      value: 35.40
      veriefied: false     
  - task:
      type: text-generation
    dataset:
        type: math
        name: GSM8K
    metrics:
    - name: pass@1
      type: pass@1
      value: 51.48
      veriefied: false 
  - task:
      type: text-generation
    dataset:
        type: math
        name: MATH
    metrics:
    - name: pass@1
      type: pass@1
      value: 19.46
      veriefied: false   
  - task:
      type: text-generation
    dataset:
        type: multilingual
        name: MGSM
    metrics:
    - name: pass@1
      type: pass@1
      value: 30.47
      veriefied: false
---
<!-- ![image/png](https://cdn-uploads.huggingface.co/production/uploads/62cd5057674cdb524450093d/1hzxoPwqkBJXshKVVe6_9.png) -->

# Granite-3.0-2B-Base

## Model Summary
**Granite-3.0-2B-Base** is an open-source decoder-only language model from IBM Research that supports a variety of text-to-text generation tasks (e.g., question-answering, text-completion). **Granite-3.0-2B-Base** is trained from scratch and follows a two-phase training strategy. In the first phase, it is trained on 10 trillion tokens sourced from diverse domains. During the second phase, it is further trained on 2 trillion tokens using a carefully curated mix of high-quality data, aiming to enhance its performance on specific tasks.

- **Developers:** IBM Research
- **GitHub Repository:** [ibm-granite/granite-language-models](https://github.com/ibm-granite/granite-language-models)
- **Website**: [Granite Docs](https://www.ibm.com/granite/docs/)
- **Paper:** [Granite Language Models](https://) <!--     TO DO: Update github repo link when it is ready -->
- **Release Date**: October 21st, 2024
- **License:** [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0).

## Supported Languages
English, German, Spanish, French, Japanese, Portuguese, Arabic, Czech, Italian, Korean, Dutch, Chinese (Simplified) 

## Usage
### Intended use
Prominent use cases of LLMs in text-to-text generation include summarization, text classification, extraction, question-answering, and more. All Granite Base models are able to handle these tasks as they were trained on a large amount of data from various domains. Moreover, all Granite language model can serve as baseline to create specialized models for specific application scenarios. 

### Generation
This is a simple example of how to use **Granite-3.0-2B-Base** model.

Install the following libraries:

```shell
pip install torch torchvision torchaudio
pip install accelerate
pip install transformers
```
Then, copy the code snippet below to run the example.

```python
from transformers import AutoModelForCausalLM, AutoTokenizer
device = "auto"
model_path = "ibm-granite/granite-3.0-2b-base"
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
input_text = "Where is the MIT-IBM Watson AI Lab located?"
# tokenize the text
input_tokens = tokenizer(input_text, return_tensors="pt").to(device)
# generate output tokens
output = model.generate(**input_tokens,
                        max_length=4000)
# decode output tokens into text
output = tokenizer.batch_decode(output)
# print output
print(output)
```

## Model Architeture
**Granite-3.0-2B-Base** is based on a decoder-only dense transformer architecture. Core components of this architecture are: GQA and RoPE, MLP with SwiGLU, RMSNorm, and shared input/output embbeddings.

| Model                        | 2B Dense     | 8B Dense | 1B MoE   | 3B MoE   |
| :--------                    | :--------    | :--------| :--------| :--------|
| Embedding size               | **2048**     | 4096     | 1024     | 1536     |
| Number of layers             | **40**       | 40       | 24       | 32       |
| Attention head size          | **64**       | 128      | 64       | 64       |
| Number of attention heads    | **32**       | 32       | 16       | 24       |
| Number of KV heads           | **8**        | 8        | 8        | 8        |
| MLP hidden size              | **8192**     | 12800    | 512      | 512      |
| MLP activation               | **SwiGLU**   | SwiGLU   | SwiGLU   | SwiGLU   |
| Number of Experts            | **—**        | —        | 32       | 40       |
| MoE TopK                     | **—**        | —        | 8        | 8        |
| Initialization std           | **0.1**      | 0.1      | 0.1      | 0.1      |
| Sequence Length              | **4096**     | 4096     | 4096     | 4096     |
| Position Embedding           | **RoPE**     | RoPE     | RoPE     | RoPE     |
| # Paremeters                 | **2.5B**     | 8.1B     | 1.3B     | 3.3B     |
| # Active Parameters          | **2.5B**     | 8.1B     | 400M     | 800M     |
| # Training tokens            | **12T**      | 12T      | 10T      | 10T      |

<!-- TO DO: To be completed once the paper is ready -->
## Training Data
This model is trained on a mix of open-source and proprietary data following a two-phase training strategy.
* Phase 1 data: The data for phase 1 is sourced from diverse domains, such as: web, code, academic sources, books, and math data.
* Phase 2 data: The data for phase 2 comprises a curated mix of high-quality data from the same domains, plus multilingual and instruction data. The goal of this second training phase is to enhance the model’s performance on specific tasks.

## Infrastructure 
We train the Granite Language models using IBM's super computing cluster, Blue Vela, which is outfitted with NVIDIA H100 GPUs. This cluster provides a scalable and efficient infrastructure for training our models over thousands of GPUs.

## Ethical Considerations and Limitations
The use of Large Language Models involves risks and ethical considerations people must be aware of, including but not limited to: bias and fairness, misinformation, and autonomous decision-making. **Granite-3.0-2B-Base** model is not the exception in this regard. Even though this model is suited for multiple generative AI tasks, it has not undergone any safety alignment, there it may produce problematic outputs. Additionally, it remains uncertain whether smaller models might exhibit increased susceptibility to hallucination in generation scenarios by copying text verbatim from the training dataset due to their reduced sizes and memorization capacities. This aspect is currently an active area of research, and we anticipate more rigorous exploration, comprehension, and mitigations in this domain. Regarding ethics, a latent risk associated with all Large Language Models is their malicious utilization. We urge the community to use **Granite-3.0-2B-Base** model with ethical intentions and in a responsible way. 

## Citation
```
@misc{granite-models,
  author = {author 1, author2, ...},
  title = {},
  journal = {},
  volume = {},
  year = {2024},
  url = {https://arxiv.org/abs/0000.00000},
}
```