ChatML prompt format
According to the model card, the model uses the ChatML prompt template format, including a documented prompt end token.
Open Source Model Profile · CyberNative-AI
Colibri 8b v0.1 is an 8.03B-parameter Llama-family text-generation model from CyberNative-AI. According to the model card, it uses the ChatML prompt template format and a companion Q5 GGUF is available.
Colibri 8b v0.1 is published by CyberNative-AI as a Llama text-generation model with cybersecurity tags. The captured configuration identifies LlamaForCausalLM and Safetensors metadata reports 8,030,277,632 parameters. According to the model card, it is described as built with Meta Llama 3, although the card states the previously reported Dolphin 2.9 Llama 3 8B upstream lineage cannot currently be verified.
According to the model card, the model uses the ChatML prompt template format, including a documented prompt end token.
According to the model card, a companion Q5 GGUF is available at CyberNative-AI/Colibri_8b_v0.1_q5_gguf.
According to the model card, the Meta Llama 3 Community License Agreement is distributed with the repository and required attribution is in NOTICE.
Source: CyberNative-AI/Colibri_8b_v0.1
Captured: Unknown. Processed: 2026-09-07T19:34:29.730569+00:00.
Llama 3 Colibri 8B v0.1 Built with Meta Llama 3 Repository records previously reported Dolphin 2.9 Llama 3 8B as the upstream model for Llama 3 Colibri 8B v0.1. CyberNative AI cannot currently verify that lineage from a primary training or weight-lineage record. The companion Q5 GGUF is available at CyberNative-AI/Colibri_8b_v0.1_q5_gguf . Provenance limitation This card previously claimed a training corpus of around 35k Q/A pairs derived from cybersecurity-related texts. CyberNative AI cannot currently evidence the source corpus, source URLs, rights holders, licenses, or transformation records for those pairs. Provenance is unverif…
F001F002F003F004F005F006F007F008F009F010F011F012F014F015F016F017