mlabonne/ChimeraLlama-3-8B-v2
Full fine-tune vs Locutusque/llama-3-neural-chat-v1-8b. 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
4 derivatives checked
- Kukedlc/NeuralLLaMa-3-8b-DT-v0.1: Full fine-tune
- mradermacher/ChimeraLlama-3-8B-v2-i1-GGUF: Quantization
- mradermacher/ChimeraLlama-3-8B-v2-GGUF: Quantization
- featherless-ai-quants/mlabonne-ChimeraLlama-3-8B-v2-GGUF: Quantization