MaziyarPanahi/Llama-3-8B-Instruct-v0.4
Full fine-tune vs meta-llama/Meta-Llama-3-8B-Instruct. Fine-tune: 93% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 96/96, Attention 128/128, lm_head 1/1
10 derivatives checked
- MaziyarPanahi/Llama-3-8B-Instruct-v0.8: Partial fine-tune
- QuantFactory/KingNish-Llama3-8b-v0.2-GGUF: Full fine-tune
- MaziyarPanahi/Llama-3-8B-Instruct-v0.4-GGUF: Quantization
- mradermacher/Llama-3-8B-Instruct-v0.4-i1-GGUF: Quantization
- featherless-ai-quants/MaziyarPanahi-Llama-3-8B-Instruct-v0.4-GGUF: Quantization
- mradermacher/Llama-3-8B-Instruct-v0.4-GGUF: Same weights, converted
- MaziyarPanahi/Llama-3-8B-Instruct-v0.7: Partial fine-tune
- netcat420/MFANNv0.17.10: Partial fine-tune
- netcat420/MFANNv0.15.10: LoRA-style
- netcat420/MFANNv0.16.10: LoRA-style