grimjim/llama-3-nvidia-ChatQA-1.5-8B

Same weights, repacked vs nvidia/Llama3-ChatQA-1.5-8B. Same weights in different files (re-saved, re-sharded or new metadata).

Tensors changed: Attention 0/160, Embeddings 0/1, Norms 0/65, MLP 0/96, lm_head 0/1

2 derivatives checked

• mradermacher/llama-3-nvidia-ChatQA-1.5-8B-i1-GGUF: Quantization
• mradermacher/llama-3-nvidia-ChatQA-1.5-8B-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse