deepscaler

295K 6 months ago

A fine-tuned version of Deepseek-R1-Distilled-Qwen-1.5B that surpasses the performance of OpenAI’s o1-preview with just 1.5B parameters on popular math evaluations.

1.5b

5 models

deepscaler:latest
0031bcf7459f • 3.6GB • 128K context window •
Text input • 6 months ago
deepscaler:1.5b latest
0031bcf7459f • 3.6GB • 128K context window •
Text input • 6 months ago
deepscaler:1.5b-preview-q4_K_M
305c4a53269d • 1.1GB • 128K context window •
Text input • 6 months ago
deepscaler:1.5b-preview-q8_0
37b8148c7f55 • 1.9GB • 128K context window •
Text input • 6 months ago
deepscaler:1.5b-preview-fp16
0031bcf7459f • 3.6GB • 128K context window •
Text input • 6 months ago