BenevolenceMessiah/Qwen2.5-Coder-7B-Instruct-abliterated-TIES-v2.0
Full fine-tune vs MadeAgents/Hammer2.0-7b. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 57/57, MLP 84/84, Attention 196/196, lm_head 1/1
2 derivatives checked
- mradermacher/Qwen2.5-Coder-7B-Instruct-abliterated-TIES-v2.0-i1-GGUF: Quantization
- mradermacher/Qwen2.5-Coder-7B-Instruct-abliterated-TIES-v2.0-GGUF: Same weights, converted