SAM

🚀 SAM (Small Agentic Model)

SAM (Small Agentic Model) is a 7B model. Despite its relatively small size, it showcases remarkable reasoning capabilities. SAM - 7B has outperformed existing state - of - the - art (SoTA) models on various reasoning benchmarks, such as GSM8k and ARC - C.

For comprehensive details about this model, please refer to our release blog post.

✨ Features

• SAM - 7B outperforms GPT 3.5, Orca, and several other 70B models on multiple reasoning benchmarks, including ARC - C and GSM8k.
• Intriguingly, even though it is trained on a dataset 97% smaller, SAM - 7B surpasses Orca - 13B on GSM8k.
• All responses in our fine - tuning dataset are generated by open - source models without any assistance from state - of - the - art models like GPT - 3.5 or GPT - 4.

📦 Installation

This section is not provided in the original README, so it is skipped.

💻 Usage Examples

Basic Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "SuperAGI/SAM"
tokenizer = AutoTokenizer.from_pretrained(model_id)

model = AutoModelForCausalLM.from_pretrained(model_id)

text = "Can elephants fly?"
inputs = tokenizer(text, return_tensors="pt")

outputs = model.generate(**inputs, max_new_tokens=200)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

📚 Documentation

Training

Example Prompt

The template used to build a prompt for the Instruct model is defined as follows:

<s> [INST] Instruction [/INST] Model answer</s> [INST] Follow - up instruction [/INST]

Note that <s> and </s> are special tokens for beginning of string (BOS) and end of string (EOS) while [INST] and [/INST] are regular strings.

Evaluation

These benchmarks show that our model has improved reasoning as compared to orca 2 - 7b, orca 2 - 13b and GPT - 3.5. Despite being smaller in size, we show better multi - hop reasoning, as shown below:

⚠️ Important Note

Temperature = 0.3 is the suggested for optimal performance

🔧 Technical Details

This section is not provided in the original README, so it is skipped.

📄 License

This model is licensed under the Apache - 2.0 license.

Limitations

SAM is a demonstration that better reasoning can be induced using less but high - quality data generated using OpenSource LLMs. The model is not suitable for conversations and simple Q&A. It performs better in task breakdown and reasoning only. It does not have any moderation mechanisms. Therefore, the model is not suitable for production usage as it doesn't have guardrails for toxicity, societal bias, and language limitations. We would love to collaborate with the community to build safer and better models.

The SuperAGI AI Team

Anmol Gautam, Arkajit Datta, Rajat Chawla, Ayush Vatsal, Sukrit Chatterjee, Adarsh Jha, Abhijeet Sinha, Rakesh Krishna, Adarsh Deep, Ishaan Bhola, Mukunda NS, Nishant Gaurav.