nbeerbower/llama-3-spicy-abliterated-stella-8B
Full fine-tune vs QuixiAI/Llama-3-8B-Instruct-abliterated-v2. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 65/65, MLP 96/96, Attention 128/128, lm_head 1/1
3 derivatives checked
- mradermacher/llama-3-spicy-abliterated-stella-8B-GGUF: Same weights, converted
- mradermacher/llama-3-spicy-abliterated-stella-8B-i1-GGUF: Quantization
- featherless-ai-quants/nbeerbower-llama-3-spicy-abliterated-stella-8B-GGUF: Quantization