princeton-nlp/Llama-3-8B-ProLong-64k-Base
Full fine-tune vs meta-llama/Meta-Llama-3-8B-Instruct. 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
5 derivatives checked
- princeton-nlp/Llama-3-8B-ProLong-512k-Base: Full fine-tune
- princeton-nlp/Llama-3-8B-ProLong-64k-Instruct: Full fine-tune
- mradermacher/Llama-3-8B-ProLong-64k-Base-i1-GGUF: Quantization
- mradermacher/Llama-3-8B-ProLong-64k-Base-GGUF: Same weights, converted
- QuantFactory/Llama-3-8B-ProLong-512k-Base-GGUF: Full fine-tune