neody/Llama-3.1-Swallow-8B-v0.5-gguf

Same weights, converted vs tokyotech-llm/Llama-3.1-Swallow-8B-v0.5. Same weights stored in another dtype (BF16 → BF16/F32), plus 1 new tensors.

Tensors changed: Embeddings 0/1, Norms 0/65, MLP 0/96, Attention 0/128, lm_head 0/1

On the Hub · Downloads on Model Pulse