# Lily-Cybersecurity-7B-v0.2

GGUF versions can be found at https://huggingface.co/segolilylabs/Lily-Cybersecurity-7B-v0.2-GGUF

- **Kind:** model (Hugging Face)
- **Hugging Face:** https://huggingface.co/segolilylabs/Lily-Cybersecurity-7B-v0.2
- **Owner:** segolilylabs (https://forefy.com/u/hf/segolilylabs)
- **Parameters:** 7.2B
- **Context:** 32768 tokens
- **License:** apache-2.0
- **Focus:** offensive
- **Architecture:** MistralForCausalLM
- **Pinned revision:** `1f97cc4e50401717e0ebee7780284a8ad113793e`
- **Page:** https://forefy.com/models/12c34124-5d4e-58ce-8546-20f7d630309b
- **API (JSON):** https://forefy.com/api/asr/models/12c34124-5d4e-58ce-8546-20f7d630309b

## What was done to it

- finetune (declared evidence, from mistralai/Mistral-7B-Instruct-v0.2)

## Lineage

mistralai/Mistral-7B-Instruct-v0.2 → segolilylabs/Lily-Cybersecurity-7B-v0.2

## Checks (repo at the pinned revision; not a behavior test)

- **Identity** [pass]: No lookalike name or conflicting provenance
- **Weights format** [pass]: safetensors only, nothing runs on load
- **Pickle files** [pass]: None.
- **Remote code** [pass]: None
- **Chat template** [warn]: Differs from mistralai/Mistral-7B-Instruct-v0.2's
- **Refusals modified** [pass]: No
- **License** [pass]: apache-2.0
- **Lineage** [pass]: Derives from mistralai/Mistral-7B-Instruct-v0.2
- **Model card** [warn]: 4 of 6, missing training data, evaluation results
- **Safetensors headers** [pass]: Every byte is indexed, no hidden data
- **Tensor layout** [pass]: Same tensors and shapes as mistralai/Mistral-7B-Instruct-v0.2

## Variants

- F32 safetensors (safetensors, 29.0 GB)

## Run it

- transformers: `AutoModelForCausalLM.from_pretrained("segolilylabs/Lily-Cybersecurity-7B-v0.2", revision="1f97cc4e50401717e0ebee7780284a8ad113793e")`