Function-calling fine-tune
According to the model card, this model is fine-tuned for function calling.
Open Source Model Profile · Trelis
Llama-2-7b-chat-hf-function-calling-v3 is a 6.74B-parameter Llama chat fine-tune from Trelis. Its model card describes OpenAI-compatible function metadata and Llama-style prompt formatting.
Llama-2-7b-chat-hf-function-calling-v3 is published by Trelis as a text-generation model. The captured configuration identifies LlamaForCausalLM with model type llama, and Safetensors metadata reports 6,738,415,616 parameters. According to the model card, it is a Llama 2 Chat fine-tune for function calling.
According to the model card, this model is fine-tuned for function calling.
The publisher states the function metadata format matches the format used for OpenAI.
According to the model card, prompts combine function lists with Llama [INST] markers or tokenizer.apply_chat_template.
Source: Trelis/Llama-2-7b-chat-hf-function-calling-v3
Captured: Unknown. Processed: 2026-09-07T19:34:38.094586+00:00.
Function Calling Fine-tuned Llama 2 Chat This model is fine-tuned for function calling. The function metadata format is the same as used for OpenAI. The model is suitable for commercial use and is licensed with the Llama 2 Community license. A GGUF version is in the gguf branch. Check out other fine-tuned function calling models here . Quick Server Setup Runpod one click TGI template here . Runpod one click vLLM template here . Runpod Affiliate Link (helps support the Trelis channel). Inference Scripts See below for sample prompt format. Complete inference scripts are available for purchase here : Easily format prompts using tokeniz…
F001F002F003F004F005F006F007F008F009F010F011F012F013F017F018F019F020F023F024