DeepSeek-V3.1 is a hybrid model that supports both thinking mode and non-thinking mode. Compared to the previous version, this upgrade brings improvements in multiple aspects:
Hybrid thinking mode: One model supports both thinking mode and non-thinking mode by changing the chat template.
Smarter tool calling: Through post-training optimization, the model’s performance in tool usage and agent tasks has significantly improved.
Higher thinking efficiency: DeepSeek-V3.1-Think achieves comparable answer quality to DeepSeek-R1-0528, while responding more quickly.
The tool calling improvements are very welcome
I wonder if we can extend the context length. It already fine-tuned with YaRN so we can’t get free extend with that method.