| Model Type | | text generation, conversational, instruction following, reasoning, function calling | 
 | 
| Use Cases | 
| Areas: | | research, commercial applications | 
 |  | Applications: | | instruction following, knowledge-driven QA, reasoning, truthful answer generation, function calling, generalist applications | 
 |  | Primary Use Cases: | | instruction-following, knowledge-driven QA benchmarks, reasoning, function-calling | 
 |  | 
| Additional Notes | | Llama-3.1-Storm-8B merges fine-tuned model with Llama-Spark using SLERP to improve characteristics. | 
 | 
| Supported Languages | | en (English), de (German), fr (French), it (Italian), pt (Portuguese), hi (Hindi), es (Spanish), th (Thai) | 
 | 
| Training Details | 
| Data Sources: |  |  | Data Volume: | | ~1 million examples selected from ~2.8 million | 
 |  | Methodology: | | Self-Curation, Spectrum-based targeted fine-tuning, SLERP model merging | 
 |  | Context Length: |  |  | Training Time: |  |  | Hardware Used: |  |  | Model Architecture: |  |  | 
| Input Output | 
| Input Format: |  |  | Accepted Modalities: |  |  | Output Format: |  |  | 
| Release Notes | | 
| Version: |  |  | Date: |  |  | Notes: | | Introduction of GGUF quantized version for use with llama.cpp | 
 |  | 
 |