tinyopsec/llama-3-chinese-8b-instruct-v3-GGUF

Same weights, converted vs hfl/llama-3-chinese-8b-instruct-v3. Same weights stored in another dtype (BF16/F16 → F16/F32).

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

On the Hub · Downloads on Model Pulse