mradermacher/chinese_bloom_7b_chat-i1-GGUF
Quantization vs yuanzhoulvpi/chinese_bloom_7b_chat. mradermacher/chinese_bloom_7b_chat-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 212 tensors match exactly and 92 within quantization error.
Tensors changed: Norms 0/122, MLP 0/120, Attention 0/60, Embeddings 0/1, lm_head 0/1