maldv/badger-writer-llama-3-8b
Full fine-tune vs maldv/badger-lambda-llama-3-8b. Fine-tune: 93% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 0/1, Norms 14/65, MLP 96/96, Attention 128/128, lm_head 1/1
3 derivatives checked
- mradermacher/badger-writer-llama-3-8b-i1-GGUF: Quantization
- featherless-ai-quants/maldv-badger-writer-llama-3-8b-GGUF: Quantization
- mradermacher/badger-writer-llama-3-8b-GGUF: Same weights, converted