MaziyarPanahi/Llama-3-8B-Instruct-v0.9
Full fine-tune vs MaziyarPanahi/Llama-3-8B-Instruct-v0.8. Fine-tune: 93% of the weights changed, across 32 of 32 layers.
Tensors changed: lm_head 1/1, Embeddings 0/1, Norms 0/65, MLP 96/96, Attention 128/128
6 derivatives checked
- MaziyarPanahi/Llama-3-8B-Instruct-v0.10: Full fine-tune
- MaziyarPanahi/Llama-3-8B-Instruct-v0.9-GGUF: Same weights, converted
- featherless-ai-quants/MaziyarPanahi-Llama-3-8B-Instruct-v0.9-GGUF: Quantization
- picAIso/TARS-8B: Full fine-tune
- picAIso/STARS-8B: Full fine-tune
- picAIso/MIX1: Full fine-tune