winglian/llama-3-8b-256k-PoSE

2 derivatives checked

• mradermacher/llama-3-8b-256k-PoSE-i1-GGUF: Quantization
• mradermacher/llama-3-8b-256k-PoSE-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse