SAM is an open-source language model by SuperAGI. Features: 7b LLM, VRAM: 14.4GB, Context: 32K, License: apache-2.0, LLM Explorer Score: 0.12, Arc: 59.4, HellaSwag: 82.3, MMLU: 62.2, GSM8K: 22.9.
SAM Parameters and Internals
Model Type Use Cases
Areas: reasoning, task breakdown
Limitations: Not suitable for conversations and simple Q&A, Lacks moderation mechanisms for toxicity and societal bias
Considerations: Not suitable for production usage due to lack of guardrails
Additional Notes Demonstrates the potential for high-quality data with less volume to induce better reasoning.
Supported Languages Training Details
Data Volume: 97% smaller dataset compared to others
Methodology: Fine-tuned using responses generated by open-source models
Training Time: Hardware Used: NVIDIA 6 x H100 SxM (80GB)
Model Architecture: Trained using Mistral 7B architecture
Input Output
Input Format: Template with [INST] and [/INST] for instructions
Accepted Modalities: Output Format: Performance Tips: Suggested temperature = 0.3 for optimal performance
Rank the SAM capabilities
Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.
Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation
Quantized Models of the SAM
Best Alternatives to SAM
Note: green Score (e.g. "73.2 ") means that the model is better than SuperAGI/SAM .
Expand