Unverified85% confidenceFactTime unknown
NousResearch此前以Hermes系列微调模型闻名，这些模型在函数调用、结构化输出和指令遵循方面表现突出
1
Sources
85%
Confidence
Long-term
Relevance
6/1/2026
First Seen
Sources
Hermes-Agent开源框架深度解析：GitHub 13万Star的AI智能体
githubNousResearch
Related Entities
Related Claims
UnverifiedNous Research is best known for releasing the Hermes series of fine-tuned models.78% similarUnverifiedNousResearch在LLaMA、Mistral等开源基座模型之上通过微调策略打造适配Agent工作流的模型变体70% similarUnverifiedHermes模型从微调阶段就大量使用结构化输出训练数据，使模型天然倾向于生成格式正确的JSON63% similarVerifiedCodex底层依赖Function Calling（函数调用）机制，模型在推理过程中可以声明需要调用某个工具61% similarUnverifiedThe Claude series of models excels at long-context understanding and instruction following.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/34953API
curl https://kongchang.com/api/v1/knowledge/claims/34953MCP
get_claim(id=34953)