| --- |
| license: llama3 |
| --- |
| |
| # Llama 3 Colibri 8B v0.1 Q5 GGUF |
|
|
| ## Built with Meta Llama 3 |
|
|
| This is a Q5 GGUF quantization of [Llama 3 Colibri 8B v0.1](https://huggingface.co/CyberNative-AI/Colibri_8b_v0.1). |
|
|
| ## Provenance limitation |
|
|
| The source model 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 unverified. Do not infer a rights basis for those pairs from this card. |
|
|
| ## Known-risk and acceptable-use notice |
|
|
| Repository records previously reported Dolphin 2.9 Llama 3 8B as the upstream model for the source model, but CyberNative AI cannot currently verify that lineage from a primary training or weight-lineage record. Its public model card describes it as uncensored; conservatively, this model may produce unsafe, inaccurate, or inappropriate cybersecurity content. Do not use it for illegal, malicious, or harmful activity. Use of Meta Llama 3 is subject to the [Meta Llama 3 Acceptable Use Policy](https://llama.meta.com/llama3/use-policy). |
|
|
| ## What you download, and how to prompt it |
|
|
| One file, `colibri_ggml-model-Q5_K_M.gguf`, 5,732,999,488 bytes. The GGUF header reports architecture `llama`, 8,030,277,632 parameters, a context length of 8192, and an end-of-turn token of `<|im_end|>`. |
|
|
| Prompts use ChatML, not the stock Llama 3 instruct format: |
|
|
| ``` |
| <|im_start|>system |
| You are Colibri, an advanced cybersecurity AI assistant developed by CyberNative AI.<|im_end|> |
| <|im_start|>user |
| {prompt}<|im_end|> |
| <|im_start|>assistant |
| ``` |
|
|
| That template is also embedded in the file, so a runner that reads the GGUF chat template applies it for you; if yours does not, set the format above and stop generation on `<|im_end|>`. |
|
|
| Every number in this section comes from the file's own header: |
|
|
| ``` |
| curl -sL https://huggingface.co/api/models/CyberNative-AI/Colibri_8b_v0.1_q5_gguf | jq .gguf |
| ``` |
|
|
| ## License and notice |
|
|
| The [Meta Llama 3 Community License Agreement](LICENSE) is distributed with this repository. The required attribution is in [NOTICE](NOTICE). |
|
|
| ## Contact |
|
|
| CyberNative AI LLC — hello@cybernative.ai |
|
|
