# Function Call Support

The DeepSeek R1 model has undergone a minor version upgrade, with the current version being DeepSeek-R1-0528. In the latest update, DeepSeek R1 significantly enhanced its deep reasoning and inference capabilities by increasing computational resource investment and introducing algorithmic optimization mechanisms during the post-training phase.

Kanana 1.5 is a new version of the Kanana model family, with significant improvements in coding, math, and function calling capabilities compared to its predecessor, supporting 32K tokens length and extendable to 128K tokens.

Qwen3-14B-FP8-dynamic is an optimized large language model. By quantizing activation values and weights to the FP8 data type, it effectively reduces GPU memory requirements and improves computational throughput.

Trendyol LLM v4.1.0 is a generative model based on Trendyol LLM base v4.0 (a Qwen2.5 7B version further pre-trained on 13 billion tokens), specializing in e-commerce and Turkish language understanding.

Mistral-7B-Instruct-v0.3 is a large language model fine-tuned for instruction following based on Mistral-7B-v0.3, supporting function calls and extended vocabulary.

An RAG version of the LLaMA 3.2 model optimized for Vietnamese, developed based on Meta's lightweight LLM, suitable for local and edge device deployment.

MiniCPM3-4B is the third-generation model in the MiniCPM series, with overall performance surpassing Phi-3.5-mini-Instruct and GPT-3.5-Turbo-0125, comparable to several recent 7B~9B-scale models.

CodeGeeX4-ALL-9B is the latest open-source version of the CodeGeeX4 series models, continuously trained based on GLM-4-9B, significantly enhancing code generation capabilities.

Mistral-7B-Instruct-v0.3 is Mistral AI's instruction fine-tuned version based on Mistral-7B-v0.3, converted to CoreML format, offering both FP16 and Int4 precision versions.

Mistral-7B-Instruct-v0.3 is a large language model fine-tuned for instruction following based on Mistral-7B-v0.3, offering a GPTQ 4-bit quantized version

Mistral-7B-Instruct-v0.3 is a large language model instruction-tuned based on Mistral-7B-v0.3, supporting function calls and extended vocabulary.

Llama3-70B-Chinese-Chat is a large bilingual language model developed based on Meta-Llama-3-70B-Instruct, specifically designed for Chinese and English users, with capabilities such as role-playing, tool usage, and mathematical computation.