How to Add Special Tokens to LLMs Without Losing Performance

This guide explains why naïvely adding special tokens during supervised fine‑tuning can destabilize a large language model, and provides step‑by‑step strategies—including tokenizer updates, embedding resizing, smart initialization, and LoRA‑based PEFT—to integrate new tokens while preserving the model's original capabilities.

LLMLoRAspecial tokens

0 likes · 9 min read

How to Add Special Tokens to LLMs Without Losing Performance

AntTech

Apr 11, 2025 · Artificial Intelligence

Understanding MCP and Function Call: A Comprehensive Guide to LLM Tool Integration

This article explains the MCP protocol and Function Call mechanism for large language models, detailing how tools are described, invoked, and processed, and provides practical code examples ranging from OpenAI JSON specifications to fast‑MCP Python and Spring MVC implementations.

AI tool integrationLarge Language ModelMCP

0 likes · 14 min read

Understanding MCP and Function Call: A Comprehensive Guide to LLM Tool Integration

Ops Development & AI Practice

Apr 5, 2025 · Artificial Intelligence

How Tool-Specific Tokens Empower LLMs to Interact with the Real World

This article explains the concept of tool-specific tokens for large language models, detailing how they enable efficient, reliable tool calls, the implementation steps, advantages over JSON, practical advice, comparisons, challenges, and future directions for AI agents.

LLMTool Callingmodel fine-tuning

0 likes · 10 min read

How Tool-Specific Tokens Empower LLMs to Interact with the Real World