TinyMistral 248M V2.5 is an open-source language model by Locutusque. Features: 248m LLM, VRAM: 1GB, Context: 32K, License: apache-2.0, Merged, LLM Explorer Score: 0.17, Arc: 24.6, HellaSwag: 27.5, MMLU: 23.2.
TinyMistral 248M V2.5 Parameters and Internals
Model Type Additional Notes This model fixes exploding gradient issues present in v2, making it easier to fine-tune.
Training Details
Data Sources: open-phi/programming_books_llama, open-phi/textbooks
Methodology: The model was created by merging TinyMistral-248M-v1 and v2, then further pretraining on synthetic textbooks.
Input Output
Performance Tips: The model's performance seems to degrade in the inference API. It's recommended to try the model by installing it directly.
Rank the TinyMistral 248M V2.5 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
Best Alternatives to TinyMistral 248M V2.5
Expand