| --- |
| license: mit |
| datasets: |
| - openbmb/Ultra-FineWeb-L3 |
| language: |
| - en |
| pipeline_tag: text-generation |
| tags: |
| - deepseek_v41 |
| --- |
| |
| # Penny Alpha |
| A 59M parameters model with Deepseek V4.1 Flash architechture |
|
|
| Other formats: |
| - GGUF: https://huggingface.co/LocalWisdom/Penny-Alpha-GGUF |
|
|
| Trained on 1B tokens of Ultra-FineWeb-L3 over 1 day 12 hours using 1x RTX 5060 Ti costing us $5.64. |
|
|
| Official context window is 8192 tokens. However, the model's native context window is 1M tokens. Tokens above 8192 has never been trained. |
