Unverified50% confidenceOpinionExact time
Tool calling is a separate skill trained separately from writing code, and below a certain parameter threshold models struggle to emit valid tool calls reliably.
1
Sources
50%
Confidence
Long-term
Relevance
10/13/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedSimply stacking parameters without sufficient training data results in a model that is large but not capable; a leap in parameters must be accompanied by a proportionally expanded training corpus and computing power to realize capability gains.77% similarUnverifiedTools such as the Training API lower the barrier to custom training, enabling teams with high-quality proprietary data to convert their data advantage into a model advantage.76% similarUnverifiedNot all local small models can reliably support tool calling; this capability requires the model to be specifically fine-tuned for the Function Calling format during training.75% similarUnverified训练秘诀（Training Recipe）包括数据配比策略、学习率调度曲线、过滤规则、对齐技术等，往往比模型架构本身更难被复现75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1013111API
curl https://kongchang.com/api/v1/knowledge/claims/1013111MCP
get_claim(id=1013111)