+ OUTPUT_DIR=./upload-Laya + LLAMA_CPP=llama.cpp + DISPLAY_NAME=Laya + QUANTIZE=llama.cpp/build/bin/llama-quantize + python3 llama.cpp/convert_hf_to_gguf.py ./model-temp-Laya-PRIMARY --outtype bf16 --outfile ./upload-Laya/Laya-BF16.gguf --model-name Laya INFO:hf-to-gguf:Loading model: model-temp-Laya-PRIMARY INFO:hf-to-gguf:gguf: detected ModernBert decision checkpoint INFO:hf-to-gguf:Model architecture: ModernBertDecisionModel INFO:hf-to-gguf:gguf: detected ModernBert decision checkpoint INFO:hf-to-gguf:gguf: indexing model part 'model.safetensors' INFO:gguf.gguf_writer:gguf: This GGUF file is for Little Endian only INFO:hf-to-gguf:Exporting model... INFO:hf-to-gguf:token_embd_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:token_embd.weight, torch.float16 --> BF16, shape = {1024, 50368} INFO:hf-to-gguf:output_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.0.attn_output.weight, torch.float16 --> BF16, shape = {1024, 1024} INFO:hf-to-gguf:blk.0.attn_qkv.weight, torch.float16 --> BF16, shape = {1024, 3072} INFO:hf-to-gguf:blk.0.ffn_up.weight, torch.float16 --> BF16, shape = {1024, 5248} INFO:hf-to-gguf:blk.0.ffn_down.weight, torch.float16 --> BF16, shape = {2624, 1024} INFO:hf-to-gguf:blk.0.ffn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.1.attn_output.weight, torch.float16 --> BF16, shape = {1024, 1024} INFO:hf-to-gguf:blk.1.attn_qkv.weight, torch.float16 --> BF16, shape = {1024, 3072} INFO:hf-to-gguf:blk.1.attn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.1.ffn_up.weight, torch.float16 --> BF16, shape = {1024, 5248} INFO:hf-to-gguf:blk.1.ffn_down.weight, torch.float16 --> BF16, shape = {2624, 1024} INFO:hf-to-gguf:blk.1.ffn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.10.attn_output.weight, torch.float16 --> BF16, shape = {1024, 1024} INFO:hf-to-gguf:blk.10.attn_qkv.weight, torch.float16 --> BF16, shape = {1024, 3072} INFO:hf-to-gguf:blk.10.attn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.10.ffn_up.weight, torch.float16 --> BF16, shape = {1024, 5248} INFO:hf-to-gguf:blk.10.ffn_down.weight, torch.float16 --> BF16, shape = {2624, 1024} INFO:hf-to-gguf:blk.10.ffn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.11.attn_output.weight, torch.float16 --> BF16, shape = {1024, 1024} INFO:hf-to-gguf:blk.11.attn_qkv.weight, torch.float16 --> BF16, shape = {1024, 3072} INFO:hf-to-gguf:blk.11.attn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.11.ffn_up.weight, torch.float16 --> BF16, shape = {1024, 5248} INFO:hf-to-gguf:blk.11.ffn_down.weight, torch.float16 --> BF16, shape = {2624, 1024} INFO:hf-to-gguf:blk.11.ffn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.12.attn_output.weight, torch.float16 --> BF16, shape = {1024, 1024} INFO:hf-to-gguf:blk.12.attn_qkv.weight, torch.float16 --> BF16, shape = {1024, 3072} INFO:hf-to-gguf:blk.12.attn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.12.ffn_up.weight, torch.float16 --> BF16, shape = {1024, 5248} INFO:hf-to-gguf:blk.12.ffn_down.weight, torch.float16 --> BF16, shape = {2624, 1024} INFO:hf-to-gguf:blk.12.ffn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.13.attn_output.weight, torch.float16 --> BF16, shape = {1024, 1024} INFO:hf-to-gguf:blk.13.attn_qkv.weight, torch.float16 --> BF16, shape = {1024, 3072} INFO:hf-to-gguf:blk.13.attn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.13.ffn_up.weight, torch.float16 --> BF16, shape = {1024, 5248} INFO:hf-to-gguf:blk.13.ffn_down.weight, torch.float16 --> BF16, shape = {2624, 1024} INFO:hf-to-gguf:blk.13.ffn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.14.attn_output.weight, torch.float16 --> BF16, shape = {1024, 1024} INFO:hf-to-gguf:blk.14.attn_qkv.weight, torch.float16 --> BF16, shape = {1024, 3072} INFO:hf-to-gguf:blk.14.attn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.14.ffn_up.weight, torch.float16 --> BF16, shape = {1024, 5248} INFO:hf-to-gguf:blk.14.ffn_down.weight, torch.float16 --> BF16, shape = {2624, 1024} INFO:hf-to-gguf:blk.14.ffn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.15.attn_output.weight, torch.float16 --> BF16, shape = {1024, 1024} INFO:hf-to-gguf:blk.15.attn_qkv.weight, torch.float16 --> BF16, shape = {1024, 3072} INFO:hf-to-gguf:blk.15.attn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.15.ffn_up.weight, torch.float16 --> BF16, shape = {1024, 5248} INFO:hf-to-gguf:blk.15.ffn_down.weight, torch.float16 --> BF16, shape = {2624, 1024} INFO:hf-to-gguf:blk.15.ffn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.16.attn_output.weight, torch.float16 --> BF16, shape = {1024, 1024} INFO:hf-to-gguf:blk.16.attn_qkv.weight, torch.float16 --> BF16, shape = {1024, 3072} INFO:hf-to-gguf:blk.16.attn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.16.ffn_up.weight, torch.float16 --> BF16, shape = {1024, 5248} INFO:hf-to-gguf:blk.16.ffn_down.weight, torch.float16 --> BF16, shape = {2624, 1024} INFO:hf-to-gguf:blk.16.ffn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.17.attn_output.weight, torch.float16 --> BF16, shape = {1024, 1024} INFO:hf-to-gguf:blk.17.attn_qkv.weight, torch.float16 --> BF16, shape = {1024, 3072} INFO:hf-to-gguf:blk.17.attn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.17.ffn_up.weight, torch.float16 --> BF16, shape = {1024, 5248} INFO:hf-to-gguf:blk.17.ffn_down.weight, torch.float16 --> BF16, shape = {2624, 1024} INFO:hf-to-gguf:blk.17.ffn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.18.attn_output.weight, torch.float16 --> BF16, shape = {1024, 1024} INFO:hf-to-gguf:blk.18.attn_qkv.weight, torch.float16 --> BF16, shape = {1024, 3072} INFO:hf-to-gguf:blk.18.attn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.18.ffn_up.weight, torch.float16 --> BF16, shape = {1024, 5248} INFO:hf-to-gguf:blk.18.ffn_down.weight, torch.float16 --> BF16, shape = {2624, 1024} INFO:hf-to-gguf:blk.18.ffn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.19.attn_output.weight, torch.float16 --> BF16, shape = {1024, 1024} INFO:hf-to-gguf:blk.19.attn_qkv.weight, torch.float16 --> BF16, shape = {1024, 3072} INFO:hf-to-gguf:blk.19.attn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.19.ffn_up.weight, torch.float16 --> BF16, shape = {1024, 5248} INFO:hf-to-gguf:blk.19.ffn_down.weight, torch.float16 --> BF16, shape = {2624, 1024} INFO:hf-to-gguf:blk.19.ffn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.2.attn_output.weight, torch.float16 --> BF16, shape = {1024, 1024} INFO:hf-to-gguf:blk.2.attn_qkv.weight, torch.float16 --> BF16, shape = {1024, 3072} INFO:hf-to-gguf:blk.2.attn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.2.ffn_up.weight, torch.float16 --> BF16, shape = {1024, 5248} INFO:hf-to-gguf:blk.2.ffn_down.weight, torch.float16 --> BF16, shape = {2624, 1024} INFO:hf-to-gguf:blk.2.ffn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.20.attn_output.weight, torch.float16 --> BF16, shape = {1024, 1024} INFO:hf-to-gguf:blk.20.attn_qkv.weight, torch.float16 --> BF16, shape = {1024, 3072} INFO:hf-to-gguf:blk.20.attn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.20.ffn_up.weight, torch.float16 --> BF16, shape = {1024, 5248} INFO:hf-to-gguf:blk.20.ffn_down.weight, torch.float16 --> BF16, shape = {2624, 1024} INFO:hf-to-gguf:blk.20.ffn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.21.attn_output.weight, torch.float16 --> BF16, shape = {1024, 1024} INFO:hf-to-gguf:blk.21.attn_qkv.weight, torch.float16 --> BF16, shape = {1024, 3072} INFO:hf-to-gguf:blk.21.attn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.21.ffn_up.weight, torch.float16 --> BF16, shape = {1024, 5248} INFO:hf-to-gguf:blk.21.ffn_down.weight, torch.float16 --> BF16, shape = {2624, 1024} INFO:hf-to-gguf:blk.21.ffn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.22.attn_output.weight, torch.float16 --> BF16, shape = {1024, 1024} INFO:hf-to-gguf:blk.22.attn_qkv.weight, torch.float16 --> BF16, shape = {1024, 3072} INFO:hf-to-gguf:blk.22.attn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.22.ffn_up.weight, torch.float16 --> BF16, shape = {1024, 5248} INFO:hf-to-gguf:blk.22.ffn_down.weight, torch.float16 --> BF16, shape = {2624, 1024} INFO:hf-to-gguf:blk.22.ffn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.23.attn_output.weight, torch.float16 --> BF16, shape = {1024, 1024} INFO:hf-to-gguf:blk.23.attn_qkv.weight, torch.float16 --> BF16, shape = {1024, 3072} INFO:hf-to-gguf:blk.23.attn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.23.ffn_up.weight, torch.float16 --> BF16, shape = {1024, 5248} INFO:hf-to-gguf:blk.23.ffn_down.weight, torch.float16 --> BF16, shape = {2624, 1024} INFO:hf-to-gguf:blk.23.ffn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.24.attn_output.weight, torch.float16 --> BF16, shape = {1024, 1024} INFO:hf-to-gguf:blk.24.attn_qkv.weight, torch.float16 --> BF16, shape = {1024, 3072} INFO:hf-to-gguf:blk.24.attn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.24.ffn_up.weight, torch.float16 --> BF16, shape = {1024, 5248} INFO:hf-to-gguf:blk.24.ffn_down.weight, torch.float16 --> BF16, shape = {2624, 1024} INFO:hf-to-gguf:blk.24.ffn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.25.attn_output.weight, torch.float16 --> BF16, shape = {1024, 1024} INFO:hf-to-gguf:blk.25.attn_qkv.weight, torch.float16 --> BF16, shape = {1024, 3072} INFO:hf-to-gguf:blk.25.attn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.25.ffn_up.weight, torch.float16 --> BF16, shape = {1024, 5248} INFO:hf-to-gguf:blk.25.ffn_down.weight, torch.float16 --> BF16, shape = {2624, 1024} INFO:hf-to-gguf:blk.25.ffn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.26.attn_output.weight, torch.float16 --> BF16, shape = {1024, 1024} INFO:hf-to-gguf:blk.26.attn_qkv.weight, torch.float16 --> BF16, shape = {1024, 3072} INFO:hf-to-gguf:blk.26.attn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.26.ffn_up.weight, torch.float16 --> BF16, shape = {1024, 5248} INFO:hf-to-gguf:blk.26.ffn_down.weight, torch.float16 --> BF16, shape = {2624, 1024} INFO:hf-to-gguf:blk.26.ffn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.27.attn_output.weight, torch.float16 --> BF16, shape = {1024, 1024} INFO:hf-to-gguf:blk.27.attn_qkv.weight, torch.float16 --> BF16, shape = {1024, 3072} INFO:hf-to-gguf:blk.27.attn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.27.ffn_up.weight, torch.float16 --> BF16, shape = {1024, 5248} INFO:hf-to-gguf:blk.27.ffn_down.weight, torch.float16 --> BF16, shape = {2624, 1024} INFO:hf-to-gguf:blk.27.ffn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.3.attn_output.weight, torch.float16 --> BF16, shape = {1024, 1024} INFO:hf-to-gguf:blk.3.attn_qkv.weight, torch.float16 --> BF16, shape = {1024, 3072} INFO:hf-to-gguf:blk.3.attn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.3.ffn_up.weight, torch.float16 --> BF16, shape = {1024, 5248} INFO:hf-to-gguf:blk.3.ffn_down.weight, torch.float16 --> BF16, shape = {2624, 1024} INFO:hf-to-gguf:blk.3.ffn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.4.attn_output.weight, torch.float16 --> BF16, shape = {1024, 1024} INFO:hf-to-gguf:blk.4.attn_qkv.weight, torch.float16 --> BF16, shape = {1024, 3072} INFO:hf-to-gguf:blk.4.attn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.4.ffn_up.weight, torch.float16 --> BF16, shape = {1024, 5248} INFO:hf-to-gguf:blk.4.ffn_down.weight, torch.float16 --> BF16, shape = {2624, 1024} INFO:hf-to-gguf:blk.4.ffn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.5.attn_output.weight, torch.float16 --> BF16, shape = {1024, 1024} INFO:hf-to-gguf:blk.5.attn_qkv.weight, torch.float16 --> BF16, shape = {1024, 3072} INFO:hf-to-gguf:blk.5.attn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.5.ffn_up.weight, torch.float16 --> BF16, shape = {1024, 5248} INFO:hf-to-gguf:blk.5.ffn_down.weight, torch.float16 --> BF16, shape = {2624, 1024} INFO:hf-to-gguf:blk.5.ffn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.6.attn_output.weight, torch.float16 --> BF16, shape = {1024, 1024} INFO:hf-to-gguf:blk.6.attn_qkv.weight, torch.float16 --> BF16, shape = {1024, 3072} INFO:hf-to-gguf:blk.6.attn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.6.ffn_up.weight, torch.float16 --> BF16, shape = {1024, 5248} INFO:hf-to-gguf:blk.6.ffn_down.weight, torch.float16 --> BF16, shape = {2624, 1024} INFO:hf-to-gguf:blk.6.ffn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.7.attn_output.weight, torch.float16 --> BF16, shape = {1024, 1024} INFO:hf-to-gguf:blk.7.attn_qkv.weight, torch.float16 --> BF16, shape = {1024, 3072} INFO:hf-to-gguf:blk.7.attn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.7.ffn_up.weight, torch.float16 --> BF16, shape = {1024, 5248} INFO:hf-to-gguf:blk.7.ffn_down.weight, torch.float16 --> BF16, shape = {2624, 1024} INFO:hf-to-gguf:blk.7.ffn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.8.attn_output.weight, torch.float16 --> BF16, shape = {1024, 1024} INFO:hf-to-gguf:blk.8.attn_qkv.weight, torch.float16 --> BF16, shape = {1024, 3072} INFO:hf-to-gguf:blk.8.attn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.8.ffn_up.weight, torch.float16 --> BF16, shape = {1024, 5248} INFO:hf-to-gguf:blk.8.ffn_down.weight, torch.float16 --> BF16, shape = {2624, 1024} INFO:hf-to-gguf:blk.8.ffn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.9.attn_output.weight, torch.float16 --> BF16, shape = {1024, 1024} INFO:hf-to-gguf:blk.9.attn_qkv.weight, torch.float16 --> BF16, shape = {1024, 3072} INFO:hf-to-gguf:blk.9.attn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.9.ffn_up.weight, torch.float16 --> BF16, shape = {1024, 5248} INFO:hf-to-gguf:blk.9.ffn_down.weight, torch.float16 --> BF16, shape = {2624, 1024} INFO:hf-to-gguf:blk.9.ffn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.28.ffn_up.bias, torch.float16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.28.ffn_up.weight, torch.float16 --> BF16, shape = {1024, 4096} INFO:hf-to-gguf:blk.28.ffn_down.bias, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.28.ffn_down.weight, torch.float16 --> BF16, shape = {4096, 1024} INFO:hf-to-gguf:blk.28.attn_norm.bias, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.28.attn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.28.ffn_norm.bias, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.28.ffn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.28.attn_qkv.bias, torch.float16 --> F32, shape = {3072} INFO:hf-to-gguf:blk.28.attn_qkv.weight, torch.float16 --> BF16, shape = {1024, 3072} INFO:hf-to-gguf:blk.28.attn_output.bias, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.28.attn_output.weight, torch.float16 --> BF16, shape = {1024, 1024} INFO:hf-to-gguf:blk.29.ffn_up.bias, torch.float16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.29.ffn_up.weight, torch.float16 --> BF16, shape = {1024, 4096} INFO:hf-to-gguf:blk.29.ffn_down.bias, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.29.ffn_down.weight, torch.float16 --> BF16, shape = {4096, 1024} INFO:hf-to-gguf:blk.29.attn_norm.bias, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.29.attn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.29.ffn_norm.bias, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.29.ffn_norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.29.attn_qkv.bias, torch.float16 --> F32, shape = {3072} INFO:hf-to-gguf:blk.29.attn_qkv.weight, torch.float16 --> BF16, shape = {1024, 3072} INFO:hf-to-gguf:blk.29.attn_output.bias, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:blk.29.attn_output.weight, torch.float16 --> BF16, shape = {1024, 1024} INFO:hf-to-gguf:cls.norm.bias, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:cls.norm.weight, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:cls.bias, torch.float16 --> F32, shape = {1024} INFO:hf-to-gguf:cls.weight, torch.float16 --> BF16, shape = {1024, 1024} INFO:hf-to-gguf:cls.output.bias, torch.float16 --> F32, shape = {1} INFO:hf-to-gguf:cls.output.weight, torch.float16 --> BF16, shape = {1024, 1} INFO:hf-to-gguf:token_types.weight, torch.float16 --> F32, shape = {1024, 3} INFO:hf-to-gguf:Set meta model INFO:hf-to-gguf:Set model parameters INFO:hf-to-gguf:gguf: context length = 8192 INFO:hf-to-gguf:gguf: embedding length = 1024 INFO:hf-to-gguf:gguf: feed forward length = [2624, 2624, 2624, 2624, 2624, 2624, 2624, 2624, 2624, 2624, 2624, 2624, 2624, 2624, 2624, 2624, 2624, 2624, 2624, 2624, 2624, 2624, 2624, 2624, 2624, 2624, 2624, 2624, 4096, 4096] INFO:hf-to-gguf:gguf: head count = 16 WARNING:hf-to-gguf:Unknown RoPE type: default INFO:hf-to-gguf:gguf: rope scaling type = NONE INFO:hf-to-gguf:gguf: rope theta = 160000.0 INFO:hf-to-gguf:gguf: rope theta swa = 10000.0 INFO:hf-to-gguf:gguf: rms norm epsilon = 1e-05 INFO:hf-to-gguf:gguf: layer norm epsilon = 1e-05 INFO:hf-to-gguf:gguf: file type = 32 INFO:hf-to-gguf:Set model quantization version INFO:hf-to-gguf:Set model tokenizer [transformers] Ignoring clean_up_tokenization_spaces=True for BPE tokenizer TokenizersBackend. The clean_up_tokenization post-processing step is designed for WordPiece tokenizers and is destructive for BPE (it strips spaces before punctuation). Set clean_up_tokenization_spaces=False to suppress this warning, or set clean_up_tokenization_spaces_for_bpe_even_though_it_will_corrupt_output=True to force cleanup anyway. INFO:gguf.vocab:Adding 50009 merge(s). INFO:gguf.vocab:Setting special token type bos to 50281 INFO:gguf.vocab:Setting special token type eos to 50282 INFO:gguf.vocab:Setting special token type unk to 50280 INFO:gguf.vocab:Setting special token type sep to 50282 INFO:gguf.vocab:Setting special token type pad to 50283 WARNING:gguf.vocab:No handler for special token type cls with id 50281 - skipping INFO:gguf.vocab:Setting special token type mask to 50284 INFO:gguf.vocab:Setting add_bos_token to True WARNING:gguf.gguf_writer:Duplicated key name 'tokenizer.ggml.add_bos_token', overwriting it with new value True of type BOOL INFO:gguf.vocab:Setting add_eos_token to True WARNING:gguf.gguf_writer:Duplicated key name 'tokenizer.ggml.add_eos_token', overwriting it with new value True of type BOOL INFO:gguf.vocab:Setting add_sep_token to False WARNING:gguf.gguf_writer:Duplicated key name 'tokenizer.ggml.add_sep_token', overwriting it with new value False of type BOOL INFO:gguf.vocab:Setting normalizer_nfc to True INFO:gguf.vocab:Setting clean_spaces to True INFO:gguf.gguf_writer:Writing the following files: INFO:gguf.gguf_writer:upload-Laya/Laya-BF16.gguf: n_tensors = 201, total_size = 842.2M Writing: 0%| | 0.00/842M [00:00", "... llama_model_loader: - kv 43: tokenizer.ggml.token_type arr[i32,50368] = [4, 3, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 44: tokenizer.ggml.merges arr[str,50009] = ["Ġ Ġ", "Ġ t", "Ġ a", "h e", "i n... llama_model_loader: - kv 45: tokenizer.ggml.bos_token_id u32 = 50281 llama_model_loader: - kv 46: tokenizer.ggml.eos_token_id u32 = 50282 llama_model_loader: - kv 47: tokenizer.ggml.unknown_token_id u32 = 50280 llama_model_loader: - kv 48: tokenizer.ggml.seperator_token_id u32 = 50282 llama_model_loader: - kv 49: tokenizer.ggml.padding_token_id u32 = 50283 llama_model_loader: - kv 50: tokenizer.ggml.mask_token_id u32 = 50284 llama_model_loader: - kv 51: tokenizer.ggml.normalizer.nfc bool = true llama_model_loader: - kv 52: tokenizer.ggml.clean_spaces bool = true llama_model_loader: - kv 53: tokenizer.ggml.token_type_count u32 = 3 llama_model_loader: - kv 54: tokenizer.chat_template.systemone str = [CLS]{{ type }} question: {{ instruct... llama_model_loader: - kv 55: tokenizer.chat_templates arr[str,1] = ["systemone"] llama_model_loader: - type f32: 78 tensors llama_model_loader: - type bf16: 123 tensors [ 1/ 201] cls.bias - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 2/ 201] cls.norm.bias - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 3/ 201] cls.norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 4/ 201] cls.output.bias - [ 1, 1, 1, 1], type = f32, size = 0.000 MiB [ 5/ 201] cls.output.weight - [ 1024, 1, 1, 1], type = bf16, size = 0.002 MiB [ 6/ 201] cls.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB [ 7/ 201] output_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 8/ 201] token_embd.weight - [ 1024, 50368, 1, 1], type = bf16, converting to q8_0 .. size = 98.38 MiB -> 52.26 MiB [ 9/ 201] token_embd_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 10/ 201] token_types.weight - [ 1024, 3, 1, 1], type = f32, size = 0.012 MiB [ 11/ 201] blk.0.attn_output.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB [ 12/ 201] blk.0.attn_qkv.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB [ 13/ 201] blk.0.ffn_down.weight - [ 2624, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 5.12 MiB -> 2.72 MiB [ 14/ 201] blk.0.ffn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 15/ 201] blk.0.ffn_up.weight - [ 1024, 5248, 1, 1], type = bf16, converting to q8_0 .. size = 10.25 MiB -> 5.45 MiB [ 16/ 201] blk.1.attn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 17/ 201] blk.1.attn_output.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB [ 18/ 201] blk.1.attn_qkv.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB [ 19/ 201] blk.1.ffn_down.weight - [ 2624, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 5.12 MiB -> 2.72 MiB [ 20/ 201] blk.1.ffn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 21/ 201] blk.1.ffn_up.weight - [ 1024, 5248, 1, 1], type = bf16, converting to q8_0 .. size = 10.25 MiB -> 5.45 MiB [ 22/ 201] blk.2.attn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 23/ 201] blk.2.attn_output.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB [ 24/ 201] blk.2.attn_qkv.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB [ 25/ 201] blk.2.ffn_down.weight - [ 2624, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 5.12 MiB -> 2.72 MiB [ 26/ 201] blk.2.ffn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 27/ 201] blk.2.ffn_up.weight - [ 1024, 5248, 1, 1], type = bf16, converting to q8_0 .. size = 10.25 MiB -> 5.45 MiB [ 28/ 201] blk.3.attn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 29/ 201] blk.3.attn_output.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB [ 30/ 201] blk.3.attn_qkv.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB [ 31/ 201] blk.3.ffn_down.weight - [ 2624, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 5.12 MiB -> 2.72 MiB [ 32/ 201] blk.3.ffn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 33/ 201] blk.3.ffn_up.weight - [ 1024, 5248, 1, 1], type = bf16, converting to q8_0 .. size = 10.25 MiB -> 5.45 MiB [ 34/ 201] blk.4.attn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 35/ 201] blk.4.attn_output.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB [ 36/ 201] blk.4.attn_qkv.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB [ 37/ 201] blk.4.ffn_down.weight - [ 2624, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 5.12 MiB -> 2.72 MiB [ 38/ 201] blk.4.ffn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 39/ 201] blk.4.ffn_up.weight - [ 1024, 5248, 1, 1], type = bf16, converting to q8_0 .. size = 10.25 MiB -> 5.45 MiB [ 40/ 201] blk.5.attn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 41/ 201] blk.5.attn_output.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB [ 42/ 201] blk.5.attn_qkv.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB [ 43/ 201] blk.5.ffn_down.weight - [ 2624, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 5.12 MiB -> 2.72 MiB [ 44/ 201] blk.5.ffn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 45/ 201] blk.5.ffn_up.weight - [ 1024, 5248, 1, 1], type = bf16, converting to q8_0 .. size = 10.25 MiB -> 5.45 MiB [ 46/ 201] blk.6.attn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 47/ 201] blk.6.attn_output.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB [ 48/ 201] blk.6.attn_qkv.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB [ 49/ 201] blk.6.ffn_down.weight - [ 2624, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 5.12 MiB -> 2.72 MiB [ 50/ 201] blk.6.ffn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 51/ 201] blk.6.ffn_up.weight - [ 1024, 5248, 1, 1], type = bf16, converting to q8_0 .. size = 10.25 MiB -> 5.45 MiB [ 52/ 201] blk.7.attn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 53/ 201] blk.7.attn_output.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB [ 54/ 201] blk.7.attn_qkv.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB [ 55/ 201] blk.7.ffn_down.weight - [ 2624, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 5.12 MiB -> 2.72 MiB [ 56/ 201] blk.7.ffn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 57/ 201] blk.7.ffn_up.weight - [ 1024, 5248, 1, 1], type = bf16, converting to q8_0 .. size = 10.25 MiB -> 5.45 MiB [ 58/ 201] blk.8.attn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 59/ 201] blk.8.attn_output.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB [ 60/ 201] blk.8.attn_qkv.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB [ 61/ 201] blk.8.ffn_down.weight - [ 2624, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 5.12 MiB -> 2.72 MiB [ 62/ 201] blk.8.ffn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 63/ 201] blk.8.ffn_up.weight - [ 1024, 5248, 1, 1], type = bf16, converting to q8_0 .. size = 10.25 MiB -> 5.45 MiB [ 64/ 201] blk.9.attn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 65/ 201] blk.9.attn_output.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB [ 66/ 201] blk.9.attn_qkv.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB [ 67/ 201] blk.9.ffn_down.weight - [ 2624, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 5.12 MiB -> 2.72 MiB [ 68/ 201] blk.9.ffn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 69/ 201] blk.9.ffn_up.weight - [ 1024, 5248, 1, 1], type = bf16, converting to q8_0 .. size = 10.25 MiB -> 5.45 MiB [ 70/ 201] blk.10.attn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 71/ 201] blk.10.attn_output.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB [ 72/ 201] blk.10.attn_qkv.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB [ 73/ 201] blk.10.ffn_down.weight - [ 2624, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 5.12 MiB -> 2.72 MiB [ 74/ 201] blk.10.ffn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 75/ 201] blk.10.ffn_up.weight - [ 1024, 5248, 1, 1], type = bf16, converting to q8_0 .. size = 10.25 MiB -> 5.45 MiB [ 76/ 201] blk.11.attn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 77/ 201] blk.11.attn_output.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB [ 78/ 201] blk.11.attn_qkv.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB [ 79/ 201] blk.11.ffn_down.weight - [ 2624, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 5.12 MiB -> 2.72 MiB [ 80/ 201] blk.11.ffn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 81/ 201] blk.11.ffn_up.weight - [ 1024, 5248, 1, 1], type = bf16, converting to q8_0 .. size = 10.25 MiB -> 5.45 MiB [ 82/ 201] blk.12.attn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 83/ 201] blk.12.attn_output.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB [ 84/ 201] blk.12.attn_qkv.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB [ 85/ 201] blk.12.ffn_down.weight - [ 2624, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 5.12 MiB -> 2.72 MiB [ 86/ 201] blk.12.ffn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 87/ 201] blk.12.ffn_up.weight - [ 1024, 5248, 1, 1], type = bf16, converting to q8_0 .. size = 10.25 MiB -> 5.45 MiB [ 88/ 201] blk.13.attn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 89/ 201] blk.13.attn_output.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB [ 90/ 201] blk.13.attn_qkv.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB [ 91/ 201] blk.13.ffn_down.weight - [ 2624, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 5.12 MiB -> 2.72 MiB [ 92/ 201] blk.13.ffn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 93/ 201] blk.13.ffn_up.weight - [ 1024, 5248, 1, 1], type = bf16, converting to q8_0 .. size = 10.25 MiB -> 5.45 MiB [ 94/ 201] blk.14.attn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 95/ 201] blk.14.attn_output.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB [ 96/ 201] blk.14.attn_qkv.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB [ 97/ 201] blk.14.ffn_down.weight - [ 2624, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 5.12 MiB -> 2.72 MiB [ 98/ 201] blk.14.ffn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 99/ 201] blk.14.ffn_up.weight - [ 1024, 5248, 1, 1], type = bf16, converting to q8_0 .. size = 10.25 MiB -> 5.45 MiB [ 100/ 201] blk.15.attn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 101/ 201] blk.15.attn_output.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB [ 102/ 201] blk.15.attn_qkv.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB [ 103/ 201] blk.15.ffn_down.weight - [ 2624, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 5.12 MiB -> 2.72 MiB [ 104/ 201] blk.15.ffn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 105/ 201] blk.15.ffn_up.weight - [ 1024, 5248, 1, 1], type = bf16, converting to q8_0 .. size = 10.25 MiB -> 5.45 MiB [ 106/ 201] blk.16.attn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 107/ 201] blk.16.attn_output.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB [ 108/ 201] blk.16.attn_qkv.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB [ 109/ 201] blk.16.ffn_down.weight - [ 2624, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 5.12 MiB -> 2.72 MiB [ 110/ 201] blk.16.ffn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 111/ 201] blk.16.ffn_up.weight - [ 1024, 5248, 1, 1], type = bf16, converting to q8_0 .. size = 10.25 MiB -> 5.45 MiB [ 112/ 201] blk.17.attn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 113/ 201] blk.17.attn_output.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB [ 114/ 201] blk.17.attn_qkv.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB [ 115/ 201] blk.17.ffn_down.weight - [ 2624, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 5.12 MiB -> 2.72 MiB [ 116/ 201] blk.17.ffn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 117/ 201] blk.17.ffn_up.weight - [ 1024, 5248, 1, 1], type = bf16, converting to q8_0 .. size = 10.25 MiB -> 5.45 MiB [ 118/ 201] blk.18.attn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 119/ 201] blk.18.attn_output.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB [ 120/ 201] blk.18.attn_qkv.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB [ 121/ 201] blk.18.ffn_down.weight - [ 2624, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 5.12 MiB -> 2.72 MiB [ 122/ 201] blk.18.ffn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 123/ 201] blk.18.ffn_up.weight - [ 1024, 5248, 1, 1], type = bf16, converting to q8_0 .. size = 10.25 MiB -> 5.45 MiB [ 124/ 201] blk.19.attn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 125/ 201] blk.19.attn_output.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB [ 126/ 201] blk.19.attn_qkv.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB [ 127/ 201] blk.19.ffn_down.weight - [ 2624, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 5.12 MiB -> 2.72 MiB [ 128/ 201] blk.19.ffn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 129/ 201] blk.19.ffn_up.weight - [ 1024, 5248, 1, 1], type = bf16, converting to q8_0 .. size = 10.25 MiB -> 5.45 MiB [ 130/ 201] blk.20.attn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 131/ 201] blk.20.attn_output.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB [ 132/ 201] blk.20.attn_qkv.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB [ 133/ 201] blk.20.ffn_down.weight - [ 2624, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 5.12 MiB -> 2.72 MiB [ 134/ 201] blk.20.ffn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 135/ 201] blk.20.ffn_up.weight - [ 1024, 5248, 1, 1], type = bf16, converting to q8_0 .. size = 10.25 MiB -> 5.45 MiB [ 136/ 201] blk.21.attn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 137/ 201] blk.21.attn_output.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB [ 138/ 201] blk.21.attn_qkv.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB [ 139/ 201] blk.21.ffn_down.weight - [ 2624, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 5.12 MiB -> 2.72 MiB [ 140/ 201] blk.21.ffn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 141/ 201] blk.21.ffn_up.weight - [ 1024, 5248, 1, 1], type = bf16, converting to q8_0 .. size = 10.25 MiB -> 5.45 MiB [ 142/ 201] blk.22.attn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 143/ 201] blk.22.attn_output.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB [ 144/ 201] blk.22.attn_qkv.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB [ 145/ 201] blk.22.ffn_down.weight - [ 2624, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 5.12 MiB -> 2.72 MiB [ 146/ 201] blk.22.ffn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 147/ 201] blk.22.ffn_up.weight - [ 1024, 5248, 1, 1], type = bf16, converting to q8_0 .. size = 10.25 MiB -> 5.45 MiB [ 148/ 201] blk.23.attn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 149/ 201] blk.23.attn_output.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB [ 150/ 201] blk.23.attn_qkv.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB [ 151/ 201] blk.23.ffn_down.weight - [ 2624, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 5.12 MiB -> 2.72 MiB [ 152/ 201] blk.23.ffn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 153/ 201] blk.23.ffn_up.weight - [ 1024, 5248, 1, 1], type = bf16, converting to q8_0 .. size = 10.25 MiB -> 5.45 MiB [ 154/ 201] blk.24.attn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 155/ 201] blk.24.attn_output.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB [ 156/ 201] blk.24.attn_qkv.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB [ 157/ 201] blk.24.ffn_down.weight - [ 2624, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 5.12 MiB -> 2.72 MiB [ 158/ 201] blk.24.ffn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 159/ 201] blk.24.ffn_up.weight - [ 1024, 5248, 1, 1], type = bf16, converting to q8_0 .. size = 10.25 MiB -> 5.45 MiB [ 160/ 201] blk.25.attn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 161/ 201] blk.25.attn_output.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB [ 162/ 201] blk.25.attn_qkv.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB [ 163/ 201] blk.25.ffn_down.weight - [ 2624, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 5.12 MiB -> 2.72 MiB [ 164/ 201] blk.25.ffn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 165/ 201] blk.25.ffn_up.weight - [ 1024, 5248, 1, 1], type = bf16, converting to q8_0 .. size = 10.25 MiB -> 5.45 MiB [ 166/ 201] blk.26.attn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 167/ 201] blk.26.attn_output.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB [ 168/ 201] blk.26.attn_qkv.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB [ 169/ 201] blk.26.ffn_down.weight - [ 2624, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 5.12 MiB -> 2.72 MiB [ 170/ 201] blk.26.ffn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 171/ 201] blk.26.ffn_up.weight - [ 1024, 5248, 1, 1], type = bf16, converting to q8_0 .. size = 10.25 MiB -> 5.45 MiB [ 172/ 201] blk.27.attn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 173/ 201] blk.27.attn_output.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB [ 174/ 201] blk.27.attn_qkv.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB [ 175/ 201] blk.27.ffn_down.weight - [ 2624, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 5.12 MiB -> 2.72 MiB [ 176/ 201] blk.27.ffn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 177/ 201] blk.27.ffn_up.weight - [ 1024, 5248, 1, 1], type = bf16, converting to q8_0 .. size = 10.25 MiB -> 5.45 MiB [ 178/ 201] blk.28.attn_norm.bias - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 179/ 201] blk.28.attn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 180/ 201] blk.28.attn_output.bias - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 181/ 201] blk.28.attn_output.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB [ 182/ 201] blk.28.attn_qkv.bias - [ 3072, 1, 1, 1], type = f32, size = 0.012 MiB [ 183/ 201] blk.28.attn_qkv.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB [ 184/ 201] blk.28.ffn_down.bias - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 185/ 201] blk.28.ffn_down.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB [ 186/ 201] blk.28.ffn_norm.bias - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 187/ 201] blk.28.ffn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 188/ 201] blk.28.ffn_up.bias - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB [ 189/ 201] blk.28.ffn_up.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB [ 190/ 201] blk.29.attn_norm.bias - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 191/ 201] blk.29.attn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 192/ 201] blk.29.attn_output.bias - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 193/ 201] blk.29.attn_output.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB [ 194/ 201] blk.29.attn_qkv.bias - [ 3072, 1, 1, 1], type = f32, size = 0.012 MiB [ 195/ 201] blk.29.attn_qkv.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB [ 196/ 201] blk.29.ffn_down.bias - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 197/ 201] blk.29.ffn_down.weight - [ 4096, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB [ 198/ 201] blk.29.ffn_norm.bias - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 199/ 201] blk.29.ffn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB [ 200/ 201] blk.29.ffn_up.bias - [ 4096, 1, 1, 1], type = f32, size = 0.016 MiB [ 201/ 201] blk.29.ffn_up.weight - [ 1024, 4096, 1, 1], type = bf16, converting to q8_0 .. size = 8.00 MiB -> 4.25 MiB llama_model_quantize_impl: model size = 803.22 MiB (16.00 BPW) llama_model_quantize_impl: quant size = 426.88 MiB (8.51 BPW) llama_quantize: quantize time = 813.54 ms llama_quantize: total time = 813.54 ms + echo Laya-BF16.gguf + echo Laya-Q8_0.gguf