Dampfinchen/Llama-3.1-8B-Ultra-Instruct
Full fine-tune vs NousResearch/Meta-Llama-3.1-8B. 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
8 derivatives checked
- bartowski/Llama-3.1-8B-Ultra-Instruct-GGUF: Same weights, converted
- QuantFactory/LLama-3.1-Hyper-Stock-GGUF: Full fine-tune
- mradermacher/Llama-3.1-8B-Ultra-Instruct-i1-GGUF: Quantization
- featherless-ai-quants/Dampfinchen-Llama-3.1-8B-Ultra-Instruct-GGUF: Quantization
- mradermacher/Llama-3.1-8B-Ultra-Instruct-GGUF: Same weights, converted
- bunnycore/Llama-3.1-8B-TitanFusion-v2: Full fine-tune
- bunnycore/LLama-3.1-Hyper-Stock: Full fine-tune
- cstr/llama3.1-8b-spaetzle-v59: Full fine-tune