Kukedlc/NeuralLLaMa-3-8b-DT-v0.1
Full fine-tune vs mlabonne/ChimeraLlama-3-8B-v2. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 65/65, MLP 96/96, Attention 128/128
4 derivatives checked
- featherless-ai-quants/Kukedlc-NeuralLLaMa-3-8b-DT-v0.1-GGUF: Quantization
- mradermacher/NeuralLLaMa-3-8b-DT-v0.1-i1-GGUF: Quantization
- mlabonne/Daredevil-8B: Full fine-tune
- mradermacher/NeuralLLaMa-3-8b-DT-v0.1-GGUF: Same weights, converted