The EpistemeAI/Fireball-Llama-3.1-8B-Instruct-v1-16bit galaxy

4 models are built on EpistemeAI/Fireball-Llama-3.1-8B-Instruct-v1-16bit: 3 quantized, 1 fine-tuned, 0 adapters and 0 merges. Together they were downloaded 1,342 times in the last 30 days.

Most downloaded direct derivatives

• mradermacher/Fireball-Llama-3.1-8B-Instruct-v1-16bit-GGUF (quantized), 673 downloads in 30 days
• mradermacher/Fireball-Llama-3.1-8B-Instruct-v1-16bit-i1-GGUF (quantized), 627 downloads in 30 days
• EpistemeAI/Fireball-Llama-3.1-8B-Instruct-v1dpo (quantized), 16 downloads in 30 days
• EpistemeAI/Fireball-Llama-3.1-8B-Intruct-v1dpo-16bit (finetune), 11 downloads in 30 days

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.