AlicanKiraz0/Seneca-Cybersecurity-LLM_x_Qwen2.5-7B-CyberSecurity

Partial fine-tune vs Qwen/Qwen2.5-Coder-7B-Instruct. Partial change: 19% of the weights changed (attention, mlp, norms), in 28 of 28 layers.

Tensors changed: Embeddings 0/1, Norms 4/57, MLP 15/84, Attention 65/196, lm_head 0/1

2 derivatives checked

• mradermacher/SenecaLLM_x_Qwen2.5-7B-CyberSecurity-i1-GGUF: Quantization
• mradermacher/SenecaLLM_x_Qwen2.5-7B-CyberSecurity-GGUF: Same weights, converted

1 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse