+ OUTPUT_DIR=./upload-NVIDIA_Nemotron_3.5_Super_VL_120B_A12B + LLAMA_CPP=llama.cpp + DISPLAY_NAME=NVIDIA-Nemotron-3.5-Super-VL-120B-A12B + QUANTIZE=llama.cpp/build/bin/llama-quantize + python3 llama.cpp/convert_hf_to_gguf.py ./model-temp-NVIDIA_Nemotron_3.5_Super_VL_120B_A12B-PRIMARY --outtype bf16 --outfile ./upload-NVIDIA_Nemotron_3.5_Super_VL_120B_A12B/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16.gguf --no-mtp --model-name NVIDIA-Nemotron-3.5-Super-VL-120B-A12B INFO:hf-to-gguf:Loading model: model-temp-NVIDIA_Nemotron_3.5_Super_VL_120B_A12B-PRIMARY WARNING:hf-to-gguf:Failed to load model config from model-temp-NVIDIA_Nemotron_3.5_Super_VL_120B_A12B-PRIMARY: The repository model-temp-NVIDIA_Nemotron_3.5_Super_VL_120B_A12B-PRIMARY contains custom code which must be executed to correctly load the model. You can inspect the repository content at /tmp/convert/model-temp-NVIDIA_Nemotron_3.5_Super_VL_120B_A12B-PRIMARY . You can inspect the repository content at https://hf.co/model-temp-NVIDIA_Nemotron_3.5_Super_VL_120B_A12B-PRIMARY. Please pass the argument `trust_remote_code=True` to allow custom code to be run. WARNING:hf-to-gguf:Trying to load config.json instead INFO:hf-to-gguf:Model architecture: NemotronHForCausalLM WARNING:hf-to-gguf:Failed to load model config from model-temp-NVIDIA_Nemotron_3.5_Super_VL_120B_A12B-PRIMARY: The repository model-temp-NVIDIA_Nemotron_3.5_Super_VL_120B_A12B-PRIMARY contains custom code which must be executed to correctly load the model. You can inspect the repository content at /tmp/convert/model-temp-NVIDIA_Nemotron_3.5_Super_VL_120B_A12B-PRIMARY . You can inspect the repository content at https://hf.co/model-temp-NVIDIA_Nemotron_3.5_Super_VL_120B_A12B-PRIMARY. Please pass the argument `trust_remote_code=True` to allow custom code to be run. WARNING:hf-to-gguf:Trying to load config.json instead INFO:hf-to-gguf:gguf: loading model weight map from 'model.safetensors.index.json' INFO:hf-to-gguf:gguf: indexing model part 'model-00001-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00002-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00003-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00004-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00005-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00006-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00007-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00008-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00009-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00010-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00011-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00012-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00013-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00014-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00015-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00016-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00017-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00018-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00019-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00020-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00021-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00022-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00023-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00024-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00025-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00026-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00027-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00028-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00029-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00030-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00031-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00032-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00033-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00034-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00035-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00036-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00037-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00038-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00039-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00040-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00041-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00042-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00043-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00044-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00045-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00046-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00047-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00048-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00049-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00050-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00051-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00052-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00053-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00054-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00055-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00056-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00057-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00058-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00059-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00060-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00061-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00062-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-00063-of-00063.safetensors' INFO:hf-to-gguf:gguf: indexing model part 'model-summary-idxs.safetensors' INFO:gguf.gguf_writer:gguf: This GGUF file is for Little Endian only WARNING:hf-to-gguf:Failed to load model config from model-temp-NVIDIA_Nemotron_3.5_Super_VL_120B_A12B-PRIMARY: The repository model-temp-NVIDIA_Nemotron_3.5_Super_VL_120B_A12B-PRIMARY contains custom code which must be executed to correctly load the model. You can inspect the repository content at /tmp/convert/model-temp-NVIDIA_Nemotron_3.5_Super_VL_120B_A12B-PRIMARY . You can inspect the repository content at https://hf.co/model-temp-NVIDIA_Nemotron_3.5_Super_VL_120B_A12B-PRIMARY. Please pass the argument `trust_remote_code=True` to allow custom code to be run. WARNING:hf-to-gguf:Trying to load config.json instead INFO:hf-to-gguf:Exporting model... INFO:hf-to-gguf:token_embd.weight, torch.bfloat16 --> BF16, shape = {4096, 131072} INFO:hf-to-gguf:blk.0.ssm_a, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.0.ssm_d, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.0.ssm_conv1d.bias, torch.bfloat16 --> F32, shape = {10240} INFO:hf-to-gguf:blk.0.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 10240} INFO:hf-to-gguf:blk.0.ssm_dt.bias, torch.bfloat16 --> F32, shape = {128} INFO:hf-to-gguf:blk.0.ssm_in.weight, torch.bfloat16 --> BF16, shape = {4096, 18560} INFO:hf-to-gguf:blk.0.ssm_norm.weight, torch.bfloat16 --> F32, shape = {1024, 8} INFO:hf-to-gguf:blk.0.ssm_out.weight, torch.bfloat16 --> BF16, shape = {8192, 4096} INFO:hf-to-gguf:blk.0.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.1.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.1.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {2688, 1024, 512} INFO:hf-to-gguf:blk.1.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1024, 2688, 512} INFO:hf-to-gguf:blk.1.ffn_latent_down.weight, torch.bfloat16 --> BF16, shape = {4096, 1024} INFO:hf-to-gguf:blk.1.ffn_latent_up.weight, torch.bfloat16 --> BF16, shape = {1024, 4096} INFO:hf-to-gguf:blk.1.exp_probs_b.bias, torch.float32 --> F32, shape = {512} INFO:hf-to-gguf:blk.1.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {4096, 512} INFO:hf-to-gguf:blk.1.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {5376, 4096} INFO:hf-to-gguf:blk.1.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {4096, 5376} INFO:hf-to-gguf:blk.2.ssm_a, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.2.ssm_d, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.2.ssm_conv1d.bias, torch.bfloat16 --> F32, shape = {10240} INFO:hf-to-gguf:blk.2.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 10240} INFO:hf-to-gguf:blk.2.ssm_dt.bias, torch.bfloat16 --> F32, shape = {128} INFO:hf-to-gguf:blk.2.ssm_in.weight, torch.bfloat16 --> BF16, shape = {4096, 18560} INFO:hf-to-gguf:blk.2.ssm_norm.weight, torch.bfloat16 --> F32, shape = {1024, 8} INFO:hf-to-gguf:blk.2.ssm_out.weight, torch.bfloat16 --> BF16, shape = {8192, 4096} INFO:hf-to-gguf:blk.2.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.3.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.3.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {2688, 1024, 512} INFO:hf-to-gguf:blk.3.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1024, 2688, 512} INFO:hf-to-gguf:blk.3.ffn_latent_down.weight, torch.bfloat16 --> BF16, shape = {4096, 1024} INFO:hf-to-gguf:blk.3.ffn_latent_up.weight, torch.bfloat16 --> BF16, shape = {1024, 4096} INFO:hf-to-gguf:blk.3.exp_probs_b.bias, torch.float32 --> F32, shape = {512} INFO:hf-to-gguf:blk.3.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {4096, 512} INFO:hf-to-gguf:blk.3.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {5376, 4096} INFO:hf-to-gguf:blk.3.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {4096, 5376} INFO:hf-to-gguf:blk.4.ssm_a, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.4.ssm_d, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.4.ssm_conv1d.bias, torch.bfloat16 --> F32, shape = {10240} INFO:hf-to-gguf:blk.4.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 10240} INFO:hf-to-gguf:blk.4.ssm_dt.bias, torch.bfloat16 --> F32, shape = {128} INFO:hf-to-gguf:blk.4.ssm_in.weight, torch.bfloat16 --> BF16, shape = {4096, 18560} INFO:hf-to-gguf:blk.4.ssm_norm.weight, torch.bfloat16 --> F32, shape = {1024, 8} INFO:hf-to-gguf:blk.4.ssm_out.weight, torch.bfloat16 --> BF16, shape = {8192, 4096} INFO:hf-to-gguf:blk.4.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.5.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.5.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {2688, 1024, 512} INFO:hf-to-gguf:blk.5.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1024, 2688, 512} INFO:hf-to-gguf:blk.5.ffn_latent_down.weight, torch.bfloat16 --> BF16, shape = {4096, 1024} INFO:hf-to-gguf:blk.5.ffn_latent_up.weight, torch.bfloat16 --> BF16, shape = {1024, 4096} INFO:hf-to-gguf:blk.5.exp_probs_b.bias, torch.float32 --> F32, shape = {512} INFO:hf-to-gguf:blk.5.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {4096, 512} INFO:hf-to-gguf:blk.5.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {5376, 4096} INFO:hf-to-gguf:blk.5.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {4096, 5376} INFO:hf-to-gguf:blk.6.ssm_a, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.6.ssm_d, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.6.ssm_conv1d.bias, torch.bfloat16 --> F32, shape = {10240} INFO:hf-to-gguf:blk.6.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 10240} INFO:hf-to-gguf:blk.6.ssm_dt.bias, torch.bfloat16 --> F32, shape = {128} INFO:hf-to-gguf:blk.6.ssm_in.weight, torch.bfloat16 --> BF16, shape = {4096, 18560} INFO:hf-to-gguf:blk.6.ssm_norm.weight, torch.bfloat16 --> F32, shape = {1024, 8} INFO:hf-to-gguf:blk.6.ssm_out.weight, torch.bfloat16 --> BF16, shape = {8192, 4096} INFO:hf-to-gguf:blk.6.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.7.attn_k.weight, torch.bfloat16 --> BF16, shape = {4096, 256} INFO:hf-to-gguf:blk.7.attn_output.weight, torch.bfloat16 --> BF16, shape = {4096, 4096} INFO:hf-to-gguf:blk.7.attn_q.weight, torch.bfloat16 --> BF16, shape = {4096, 4096} INFO:hf-to-gguf:blk.7.attn_v.weight, torch.bfloat16 --> BF16, shape = {4096, 256} INFO:hf-to-gguf:blk.7.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.8.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.10.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.8.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {2688, 1024, 512} INFO:hf-to-gguf:blk.8.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1024, 2688, 512} INFO:hf-to-gguf:blk.8.ffn_latent_down.weight, torch.bfloat16 --> BF16, shape = {4096, 1024} INFO:hf-to-gguf:blk.8.ffn_latent_up.weight, torch.bfloat16 --> BF16, shape = {1024, 4096} INFO:hf-to-gguf:blk.8.exp_probs_b.bias, torch.float32 --> F32, shape = {512} INFO:hf-to-gguf:blk.8.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {4096, 512} INFO:hf-to-gguf:blk.8.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {5376, 4096} INFO:hf-to-gguf:blk.8.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {4096, 5376} INFO:hf-to-gguf:blk.9.ssm_a, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.9.ssm_d, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.9.ssm_conv1d.bias, torch.bfloat16 --> F32, shape = {10240} INFO:hf-to-gguf:blk.9.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 10240} INFO:hf-to-gguf:blk.9.ssm_dt.bias, torch.bfloat16 --> F32, shape = {128} INFO:hf-to-gguf:blk.9.ssm_in.weight, torch.bfloat16 --> BF16, shape = {4096, 18560} INFO:hf-to-gguf:blk.9.ssm_norm.weight, torch.bfloat16 --> F32, shape = {1024, 8} INFO:hf-to-gguf:blk.9.ssm_out.weight, torch.bfloat16 --> BF16, shape = {8192, 4096} INFO:hf-to-gguf:blk.9.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.10.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {2688, 1024, 512} INFO:hf-to-gguf:blk.10.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1024, 2688, 512} INFO:hf-to-gguf:blk.10.ffn_latent_down.weight, torch.bfloat16 --> BF16, shape = {4096, 1024} INFO:hf-to-gguf:blk.10.ffn_latent_up.weight, torch.bfloat16 --> BF16, shape = {1024, 4096} INFO:hf-to-gguf:blk.10.exp_probs_b.bias, torch.float32 --> F32, shape = {512} INFO:hf-to-gguf:blk.10.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {4096, 512} INFO:hf-to-gguf:blk.10.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {5376, 4096} INFO:hf-to-gguf:blk.10.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {4096, 5376} INFO:hf-to-gguf:blk.11.ssm_a, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.11.ssm_d, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.11.ssm_conv1d.bias, torch.bfloat16 --> F32, shape = {10240} INFO:hf-to-gguf:blk.11.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 10240} INFO:hf-to-gguf:blk.11.ssm_dt.bias, torch.bfloat16 --> F32, shape = {128} INFO:hf-to-gguf:blk.11.ssm_in.weight, torch.bfloat16 --> BF16, shape = {4096, 18560} INFO:hf-to-gguf:blk.11.ssm_norm.weight, torch.bfloat16 --> F32, shape = {1024, 8} INFO:hf-to-gguf:blk.11.ssm_out.weight, torch.bfloat16 --> BF16, shape = {8192, 4096} INFO:hf-to-gguf:blk.11.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.12.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.12.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {2688, 1024, 512} INFO:hf-to-gguf:blk.12.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1024, 2688, 512} INFO:hf-to-gguf:blk.12.ffn_latent_down.weight, torch.bfloat16 --> BF16, shape = {4096, 1024} INFO:hf-to-gguf:blk.12.ffn_latent_up.weight, torch.bfloat16 --> BF16, shape = {1024, 4096} INFO:hf-to-gguf:blk.12.exp_probs_b.bias, torch.float32 --> F32, shape = {512} INFO:hf-to-gguf:blk.12.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {4096, 512} INFO:hf-to-gguf:blk.12.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {5376, 4096} INFO:hf-to-gguf:blk.12.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {4096, 5376} INFO:hf-to-gguf:blk.13.ssm_a, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.13.ssm_d, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.13.ssm_conv1d.bias, torch.bfloat16 --> F32, shape = {10240} INFO:hf-to-gguf:blk.13.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 10240} INFO:hf-to-gguf:blk.13.ssm_dt.bias, torch.bfloat16 --> F32, shape = {128} INFO:hf-to-gguf:blk.13.ssm_in.weight, torch.bfloat16 --> BF16, shape = {4096, 18560} INFO:hf-to-gguf:blk.13.ssm_norm.weight, torch.bfloat16 --> F32, shape = {1024, 8} INFO:hf-to-gguf:blk.13.ssm_out.weight, torch.bfloat16 --> BF16, shape = {8192, 4096} INFO:hf-to-gguf:blk.13.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.14.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.14.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {2688, 1024, 512} INFO:hf-to-gguf:blk.14.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1024, 2688, 512} INFO:hf-to-gguf:blk.14.ffn_latent_down.weight, torch.bfloat16 --> BF16, shape = {4096, 1024} INFO:hf-to-gguf:blk.14.ffn_latent_up.weight, torch.bfloat16 --> BF16, shape = {1024, 4096} INFO:hf-to-gguf:blk.14.exp_probs_b.bias, torch.float32 --> F32, shape = {512} INFO:hf-to-gguf:blk.14.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {4096, 512} INFO:hf-to-gguf:blk.14.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {5376, 4096} INFO:hf-to-gguf:blk.14.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {4096, 5376} INFO:hf-to-gguf:blk.15.ssm_a, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.15.ssm_d, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.15.ssm_conv1d.bias, torch.bfloat16 --> F32, shape = {10240} INFO:hf-to-gguf:blk.15.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 10240} INFO:hf-to-gguf:blk.15.ssm_dt.bias, torch.bfloat16 --> F32, shape = {128} INFO:hf-to-gguf:blk.15.ssm_in.weight, torch.bfloat16 --> BF16, shape = {4096, 18560} INFO:hf-to-gguf:blk.15.ssm_norm.weight, torch.bfloat16 --> F32, shape = {1024, 8} INFO:hf-to-gguf:blk.15.ssm_out.weight, torch.bfloat16 --> BF16, shape = {8192, 4096} INFO:hf-to-gguf:blk.15.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.16.attn_k.weight, torch.bfloat16 --> BF16, shape = {4096, 256} INFO:hf-to-gguf:blk.16.attn_output.weight, torch.bfloat16 --> BF16, shape = {4096, 4096} INFO:hf-to-gguf:blk.16.attn_q.weight, torch.bfloat16 --> BF16, shape = {4096, 4096} INFO:hf-to-gguf:blk.16.attn_v.weight, torch.bfloat16 --> BF16, shape = {4096, 256} INFO:hf-to-gguf:blk.16.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.17.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.17.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {2688, 1024, 512} INFO:hf-to-gguf:blk.17.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1024, 2688, 512} INFO:hf-to-gguf:blk.17.ffn_latent_down.weight, torch.bfloat16 --> BF16, shape = {4096, 1024} INFO:hf-to-gguf:blk.17.ffn_latent_up.weight, torch.bfloat16 --> BF16, shape = {1024, 4096} INFO:hf-to-gguf:blk.17.exp_probs_b.bias, torch.float32 --> F32, shape = {512} INFO:hf-to-gguf:blk.17.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {4096, 512} INFO:hf-to-gguf:blk.17.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {5376, 4096} INFO:hf-to-gguf:blk.17.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {4096, 5376} INFO:hf-to-gguf:blk.18.ssm_a, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.18.ssm_d, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.18.ssm_conv1d.bias, torch.bfloat16 --> F32, shape = {10240} INFO:hf-to-gguf:blk.18.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 10240} INFO:hf-to-gguf:blk.18.ssm_dt.bias, torch.bfloat16 --> F32, shape = {128} INFO:hf-to-gguf:blk.18.ssm_in.weight, torch.bfloat16 --> BF16, shape = {4096, 18560} INFO:hf-to-gguf:blk.18.ssm_norm.weight, torch.bfloat16 --> F32, shape = {1024, 8} INFO:hf-to-gguf:blk.18.ssm_out.weight, torch.bfloat16 --> BF16, shape = {8192, 4096} INFO:hf-to-gguf:blk.18.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.19.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.19.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {2688, 1024, 512} INFO:hf-to-gguf:blk.19.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1024, 2688, 512} INFO:hf-to-gguf:blk.19.ffn_latent_down.weight, torch.bfloat16 --> BF16, shape = {4096, 1024} INFO:hf-to-gguf:blk.19.ffn_latent_up.weight, torch.bfloat16 --> BF16, shape = {1024, 4096} INFO:hf-to-gguf:blk.19.exp_probs_b.bias, torch.float32 --> F32, shape = {512} INFO:hf-to-gguf:blk.19.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {4096, 512} INFO:hf-to-gguf:blk.19.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {5376, 4096} INFO:hf-to-gguf:blk.19.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {4096, 5376} INFO:hf-to-gguf:blk.20.ssm_a, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.20.ssm_d, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.20.ssm_conv1d.bias, torch.bfloat16 --> F32, shape = {10240} INFO:hf-to-gguf:blk.20.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 10240} INFO:hf-to-gguf:blk.20.ssm_dt.bias, torch.bfloat16 --> F32, shape = {128} INFO:hf-to-gguf:blk.20.ssm_in.weight, torch.bfloat16 --> BF16, shape = {4096, 18560} INFO:hf-to-gguf:blk.20.ssm_norm.weight, torch.bfloat16 --> F32, shape = {1024, 8} INFO:hf-to-gguf:blk.20.ssm_out.weight, torch.bfloat16 --> BF16, shape = {8192, 4096} INFO:hf-to-gguf:blk.20.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.21.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.21.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {2688, 1024, 512} INFO:hf-to-gguf:blk.21.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1024, 2688, 512} INFO:hf-to-gguf:blk.21.ffn_latent_down.weight, torch.bfloat16 --> BF16, shape = {4096, 1024} INFO:hf-to-gguf:blk.21.ffn_latent_up.weight, torch.bfloat16 --> BF16, shape = {1024, 4096} INFO:hf-to-gguf:blk.21.exp_probs_b.bias, torch.float32 --> F32, shape = {512} INFO:hf-to-gguf:blk.21.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {4096, 512} INFO:hf-to-gguf:blk.21.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {5376, 4096} INFO:hf-to-gguf:blk.21.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {4096, 5376} INFO:hf-to-gguf:blk.22.ssm_a, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.22.ssm_d, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.22.ssm_conv1d.bias, torch.bfloat16 --> F32, shape = {10240} INFO:hf-to-gguf:blk.22.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 10240} INFO:hf-to-gguf:blk.22.ssm_dt.bias, torch.bfloat16 --> F32, shape = {128} INFO:hf-to-gguf:blk.22.ssm_in.weight, torch.bfloat16 --> BF16, shape = {4096, 18560} INFO:hf-to-gguf:blk.22.ssm_norm.weight, torch.bfloat16 --> F32, shape = {1024, 8} INFO:hf-to-gguf:blk.22.ssm_out.weight, torch.bfloat16 --> BF16, shape = {8192, 4096} INFO:hf-to-gguf:blk.22.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.23.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.23.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {2688, 1024, 512} INFO:hf-to-gguf:blk.23.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1024, 2688, 512} INFO:hf-to-gguf:blk.23.ffn_latent_down.weight, torch.bfloat16 --> BF16, shape = {4096, 1024} INFO:hf-to-gguf:blk.23.ffn_latent_up.weight, torch.bfloat16 --> BF16, shape = {1024, 4096} INFO:hf-to-gguf:blk.23.exp_probs_b.bias, torch.float32 --> F32, shape = {512} INFO:hf-to-gguf:blk.23.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {4096, 512} INFO:hf-to-gguf:blk.23.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {5376, 4096} INFO:hf-to-gguf:blk.23.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {4096, 5376} INFO:hf-to-gguf:blk.24.ssm_a, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.24.ssm_d, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.24.ssm_conv1d.bias, torch.bfloat16 --> F32, shape = {10240} INFO:hf-to-gguf:blk.24.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 10240} INFO:hf-to-gguf:blk.24.ssm_dt.bias, torch.bfloat16 --> F32, shape = {128} INFO:hf-to-gguf:blk.24.ssm_in.weight, torch.bfloat16 --> BF16, shape = {4096, 18560} INFO:hf-to-gguf:blk.24.ssm_norm.weight, torch.bfloat16 --> F32, shape = {1024, 8} INFO:hf-to-gguf:blk.24.ssm_out.weight, torch.bfloat16 --> BF16, shape = {8192, 4096} INFO:hf-to-gguf:blk.24.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.25.attn_k.weight, torch.bfloat16 --> BF16, shape = {4096, 256} INFO:hf-to-gguf:blk.25.attn_output.weight, torch.bfloat16 --> BF16, shape = {4096, 4096} INFO:hf-to-gguf:blk.25.attn_q.weight, torch.bfloat16 --> BF16, shape = {4096, 4096} INFO:hf-to-gguf:blk.25.attn_v.weight, torch.bfloat16 --> BF16, shape = {4096, 256} INFO:hf-to-gguf:blk.25.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.26.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.26.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {2688, 1024, 512} INFO:hf-to-gguf:blk.26.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1024, 2688, 512} INFO:hf-to-gguf:blk.26.ffn_latent_down.weight, torch.bfloat16 --> BF16, shape = {4096, 1024} INFO:hf-to-gguf:blk.26.ffn_latent_up.weight, torch.bfloat16 --> BF16, shape = {1024, 4096} INFO:hf-to-gguf:blk.26.exp_probs_b.bias, torch.float32 --> F32, shape = {512} INFO:hf-to-gguf:blk.26.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {4096, 512} INFO:hf-to-gguf:blk.26.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {5376, 4096} INFO:hf-to-gguf:blk.26.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {4096, 5376} INFO:hf-to-gguf:blk.27.ssm_a, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.27.ssm_d, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.27.ssm_conv1d.bias, torch.bfloat16 --> F32, shape = {10240} INFO:hf-to-gguf:blk.27.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 10240} INFO:hf-to-gguf:blk.27.ssm_dt.bias, torch.bfloat16 --> F32, shape = {128} INFO:hf-to-gguf:blk.27.ssm_in.weight, torch.bfloat16 --> BF16, shape = {4096, 18560} INFO:hf-to-gguf:blk.27.ssm_norm.weight, torch.bfloat16 --> F32, shape = {1024, 8} INFO:hf-to-gguf:blk.27.ssm_out.weight, torch.bfloat16 --> BF16, shape = {8192, 4096} INFO:hf-to-gguf:blk.27.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.28.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.28.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {2688, 1024, 512} INFO:hf-to-gguf:blk.28.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1024, 2688, 512} INFO:hf-to-gguf:blk.28.ffn_latent_down.weight, torch.bfloat16 --> BF16, shape = {4096, 1024} INFO:hf-to-gguf:blk.28.ffn_latent_up.weight, torch.bfloat16 --> BF16, shape = {1024, 4096} INFO:hf-to-gguf:blk.28.exp_probs_b.bias, torch.float32 --> F32, shape = {512} INFO:hf-to-gguf:blk.28.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {4096, 512} INFO:hf-to-gguf:blk.28.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {5376, 4096} INFO:hf-to-gguf:blk.28.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {4096, 5376} INFO:hf-to-gguf:blk.29.ssm_a, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.29.ssm_d, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.29.ssm_conv1d.bias, torch.bfloat16 --> F32, shape = {10240} INFO:hf-to-gguf:blk.29.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 10240} INFO:hf-to-gguf:blk.29.ssm_dt.bias, torch.bfloat16 --> F32, shape = {128} INFO:hf-to-gguf:blk.29.ssm_in.weight, torch.bfloat16 --> BF16, shape = {4096, 18560} INFO:hf-to-gguf:blk.29.ssm_norm.weight, torch.bfloat16 --> F32, shape = {1024, 8} INFO:hf-to-gguf:blk.29.ssm_out.weight, torch.bfloat16 --> BF16, shape = {8192, 4096} INFO:hf-to-gguf:blk.29.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.30.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.30.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {2688, 1024, 512} INFO:hf-to-gguf:blk.30.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1024, 2688, 512} INFO:hf-to-gguf:blk.30.ffn_latent_down.weight, torch.bfloat16 --> BF16, shape = {4096, 1024} INFO:hf-to-gguf:blk.30.ffn_latent_up.weight, torch.bfloat16 --> BF16, shape = {1024, 4096} INFO:hf-to-gguf:blk.30.exp_probs_b.bias, torch.float32 --> F32, shape = {512} INFO:hf-to-gguf:blk.30.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {4096, 512} INFO:hf-to-gguf:blk.30.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {5376, 4096} INFO:hf-to-gguf:blk.30.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {4096, 5376} INFO:hf-to-gguf:blk.31.ssm_a, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.31.ssm_d, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.31.ssm_conv1d.bias, torch.bfloat16 --> F32, shape = {10240} INFO:hf-to-gguf:blk.31.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 10240} INFO:hf-to-gguf:blk.31.ssm_dt.bias, torch.bfloat16 --> F32, shape = {128} INFO:hf-to-gguf:blk.31.ssm_in.weight, torch.bfloat16 --> BF16, shape = {4096, 18560} INFO:hf-to-gguf:blk.31.ssm_norm.weight, torch.bfloat16 --> F32, shape = {1024, 8} INFO:hf-to-gguf:blk.31.ssm_out.weight, torch.bfloat16 --> BF16, shape = {8192, 4096} INFO:hf-to-gguf:blk.31.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.32.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.32.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {2688, 1024, 512} INFO:hf-to-gguf:blk.32.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1024, 2688, 512} INFO:hf-to-gguf:blk.32.ffn_latent_down.weight, torch.bfloat16 --> BF16, shape = {4096, 1024} INFO:hf-to-gguf:blk.32.ffn_latent_up.weight, torch.bfloat16 --> BF16, shape = {1024, 4096} INFO:hf-to-gguf:blk.32.exp_probs_b.bias, torch.float32 --> F32, shape = {512} INFO:hf-to-gguf:blk.32.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {4096, 512} INFO:hf-to-gguf:blk.32.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {5376, 4096} INFO:hf-to-gguf:blk.32.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {4096, 5376} INFO:hf-to-gguf:blk.33.ssm_a, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.33.ssm_d, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.33.ssm_conv1d.bias, torch.bfloat16 --> F32, shape = {10240} INFO:hf-to-gguf:blk.33.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 10240} INFO:hf-to-gguf:blk.33.ssm_dt.bias, torch.bfloat16 --> F32, shape = {128} INFO:hf-to-gguf:blk.33.ssm_in.weight, torch.bfloat16 --> BF16, shape = {4096, 18560} INFO:hf-to-gguf:blk.33.ssm_norm.weight, torch.bfloat16 --> F32, shape = {1024, 8} INFO:hf-to-gguf:blk.33.ssm_out.weight, torch.bfloat16 --> BF16, shape = {8192, 4096} INFO:hf-to-gguf:blk.33.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.34.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.34.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {2688, 1024, 512} INFO:hf-to-gguf:blk.34.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1024, 2688, 512} INFO:hf-to-gguf:blk.34.ffn_latent_down.weight, torch.bfloat16 --> BF16, shape = {4096, 1024} INFO:hf-to-gguf:blk.34.ffn_latent_up.weight, torch.bfloat16 --> BF16, shape = {1024, 4096} INFO:hf-to-gguf:blk.34.exp_probs_b.bias, torch.float32 --> F32, shape = {512} INFO:hf-to-gguf:blk.34.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {4096, 512} INFO:hf-to-gguf:blk.34.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {5376, 4096} INFO:hf-to-gguf:blk.34.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {4096, 5376} INFO:hf-to-gguf:blk.35.ssm_a, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.35.ssm_d, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.35.ssm_conv1d.bias, torch.bfloat16 --> F32, shape = {10240} INFO:hf-to-gguf:blk.35.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 10240} INFO:hf-to-gguf:blk.35.ssm_dt.bias, torch.bfloat16 --> F32, shape = {128} INFO:hf-to-gguf:blk.35.ssm_in.weight, torch.bfloat16 --> BF16, shape = {4096, 18560} INFO:hf-to-gguf:blk.35.ssm_norm.weight, torch.bfloat16 --> F32, shape = {1024, 8} INFO:hf-to-gguf:blk.35.ssm_out.weight, torch.bfloat16 --> BF16, shape = {8192, 4096} INFO:hf-to-gguf:blk.35.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.36.attn_k.weight, torch.bfloat16 --> BF16, shape = {4096, 256} INFO:hf-to-gguf:blk.36.attn_output.weight, torch.bfloat16 --> BF16, shape = {4096, 4096} INFO:hf-to-gguf:blk.36.attn_q.weight, torch.bfloat16 --> BF16, shape = {4096, 4096} INFO:hf-to-gguf:blk.36.attn_v.weight, torch.bfloat16 --> BF16, shape = {4096, 256} INFO:hf-to-gguf:blk.36.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.37.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.37.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {2688, 1024, 512} INFO:hf-to-gguf:blk.37.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1024, 2688, 512} INFO:hf-to-gguf:blk.37.ffn_latent_down.weight, torch.bfloat16 --> BF16, shape = {4096, 1024} INFO:hf-to-gguf:blk.37.ffn_latent_up.weight, torch.bfloat16 --> BF16, shape = {1024, 4096} INFO:hf-to-gguf:blk.37.exp_probs_b.bias, torch.float32 --> F32, shape = {512} INFO:hf-to-gguf:blk.37.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {4096, 512} INFO:hf-to-gguf:blk.37.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {5376, 4096} INFO:hf-to-gguf:blk.37.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {4096, 5376} INFO:hf-to-gguf:blk.38.ssm_a, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.38.ssm_d, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.38.ssm_conv1d.bias, torch.bfloat16 --> F32, shape = {10240} INFO:hf-to-gguf:blk.38.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 10240} INFO:hf-to-gguf:blk.38.ssm_dt.bias, torch.bfloat16 --> F32, shape = {128} INFO:hf-to-gguf:blk.38.ssm_in.weight, torch.bfloat16 --> BF16, shape = {4096, 18560} INFO:hf-to-gguf:blk.38.ssm_norm.weight, torch.bfloat16 --> F32, shape = {1024, 8} INFO:hf-to-gguf:blk.38.ssm_out.weight, torch.bfloat16 --> BF16, shape = {8192, 4096} INFO:hf-to-gguf:blk.38.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.39.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.39.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {2688, 1024, 512} INFO:hf-to-gguf:blk.39.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1024, 2688, 512} INFO:hf-to-gguf:blk.39.ffn_latent_down.weight, torch.bfloat16 --> BF16, shape = {4096, 1024} INFO:hf-to-gguf:blk.39.ffn_latent_up.weight, torch.bfloat16 --> BF16, shape = {1024, 4096} INFO:hf-to-gguf:blk.39.exp_probs_b.bias, torch.float32 --> F32, shape = {512} INFO:hf-to-gguf:blk.39.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {4096, 512} INFO:hf-to-gguf:blk.39.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {5376, 4096} INFO:hf-to-gguf:blk.39.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {4096, 5376} INFO:hf-to-gguf:blk.40.ssm_a, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.40.ssm_d, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.40.ssm_conv1d.bias, torch.bfloat16 --> F32, shape = {10240} INFO:hf-to-gguf:blk.40.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 10240} INFO:hf-to-gguf:blk.40.ssm_dt.bias, torch.bfloat16 --> F32, shape = {128} INFO:hf-to-gguf:blk.40.ssm_in.weight, torch.bfloat16 --> BF16, shape = {4096, 18560} INFO:hf-to-gguf:blk.40.ssm_norm.weight, torch.bfloat16 --> F32, shape = {1024, 8} INFO:hf-to-gguf:blk.40.ssm_out.weight, torch.bfloat16 --> BF16, shape = {8192, 4096} INFO:hf-to-gguf:blk.40.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.41.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.41.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {2688, 1024, 512} INFO:hf-to-gguf:blk.41.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1024, 2688, 512} INFO:hf-to-gguf:blk.41.ffn_latent_down.weight, torch.bfloat16 --> BF16, shape = {4096, 1024} INFO:hf-to-gguf:blk.41.ffn_latent_up.weight, torch.bfloat16 --> BF16, shape = {1024, 4096} INFO:hf-to-gguf:blk.41.exp_probs_b.bias, torch.float32 --> F32, shape = {512} INFO:hf-to-gguf:blk.41.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {4096, 512} INFO:hf-to-gguf:blk.41.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {5376, 4096} INFO:hf-to-gguf:blk.41.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {4096, 5376} INFO:hf-to-gguf:blk.42.ssm_a, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.42.ssm_d, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.42.ssm_conv1d.bias, torch.bfloat16 --> F32, shape = {10240} INFO:hf-to-gguf:blk.42.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 10240} INFO:hf-to-gguf:blk.42.ssm_dt.bias, torch.bfloat16 --> F32, shape = {128} INFO:hf-to-gguf:blk.42.ssm_in.weight, torch.bfloat16 --> BF16, shape = {4096, 18560} INFO:hf-to-gguf:blk.42.ssm_norm.weight, torch.bfloat16 --> F32, shape = {1024, 8} INFO:hf-to-gguf:blk.42.ssm_out.weight, torch.bfloat16 --> BF16, shape = {8192, 4096} INFO:hf-to-gguf:blk.42.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.43.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.43.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {2688, 1024, 512} INFO:hf-to-gguf:blk.43.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1024, 2688, 512} INFO:hf-to-gguf:blk.43.ffn_latent_down.weight, torch.bfloat16 --> BF16, shape = {4096, 1024} INFO:hf-to-gguf:blk.43.ffn_latent_up.weight, torch.bfloat16 --> BF16, shape = {1024, 4096} INFO:hf-to-gguf:blk.43.exp_probs_b.bias, torch.float32 --> F32, shape = {512} INFO:hf-to-gguf:blk.43.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {4096, 512} INFO:hf-to-gguf:blk.43.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {5376, 4096} INFO:hf-to-gguf:blk.43.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {4096, 5376} INFO:hf-to-gguf:blk.44.ssm_a, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.44.ssm_d, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.44.ssm_conv1d.bias, torch.bfloat16 --> F32, shape = {10240} INFO:hf-to-gguf:blk.44.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 10240} INFO:hf-to-gguf:blk.44.ssm_dt.bias, torch.bfloat16 --> F32, shape = {128} INFO:hf-to-gguf:blk.44.ssm_in.weight, torch.bfloat16 --> BF16, shape = {4096, 18560} INFO:hf-to-gguf:blk.44.ssm_norm.weight, torch.bfloat16 --> F32, shape = {1024, 8} INFO:hf-to-gguf:blk.44.ssm_out.weight, torch.bfloat16 --> BF16, shape = {8192, 4096} INFO:hf-to-gguf:blk.44.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.45.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.45.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {2688, 1024, 512} INFO:hf-to-gguf:blk.45.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1024, 2688, 512} INFO:hf-to-gguf:blk.45.ffn_latent_down.weight, torch.bfloat16 --> BF16, shape = {4096, 1024} INFO:hf-to-gguf:blk.45.ffn_latent_up.weight, torch.bfloat16 --> BF16, shape = {1024, 4096} INFO:hf-to-gguf:blk.45.exp_probs_b.bias, torch.float32 --> F32, shape = {512} INFO:hf-to-gguf:blk.45.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {4096, 512} INFO:hf-to-gguf:blk.45.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {5376, 4096} INFO:hf-to-gguf:blk.45.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {4096, 5376} INFO:hf-to-gguf:blk.46.ssm_a, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.46.ssm_d, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.46.ssm_conv1d.bias, torch.bfloat16 --> F32, shape = {10240} INFO:hf-to-gguf:blk.46.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 10240} INFO:hf-to-gguf:blk.46.ssm_dt.bias, torch.bfloat16 --> F32, shape = {128} INFO:hf-to-gguf:blk.46.ssm_in.weight, torch.bfloat16 --> BF16, shape = {4096, 18560} INFO:hf-to-gguf:blk.46.ssm_norm.weight, torch.bfloat16 --> F32, shape = {1024, 8} INFO:hf-to-gguf:blk.46.ssm_out.weight, torch.bfloat16 --> BF16, shape = {8192, 4096} INFO:hf-to-gguf:blk.46.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.47.attn_k.weight, torch.bfloat16 --> BF16, shape = {4096, 256} INFO:hf-to-gguf:blk.47.attn_output.weight, torch.bfloat16 --> BF16, shape = {4096, 4096} INFO:hf-to-gguf:blk.47.attn_q.weight, torch.bfloat16 --> BF16, shape = {4096, 4096} INFO:hf-to-gguf:blk.47.attn_v.weight, torch.bfloat16 --> BF16, shape = {4096, 256} INFO:hf-to-gguf:blk.47.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.48.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.48.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {2688, 1024, 512} INFO:hf-to-gguf:blk.48.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1024, 2688, 512} INFO:hf-to-gguf:blk.48.ffn_latent_down.weight, torch.bfloat16 --> BF16, shape = {4096, 1024} INFO:hf-to-gguf:blk.48.ffn_latent_up.weight, torch.bfloat16 --> BF16, shape = {1024, 4096} INFO:hf-to-gguf:blk.48.exp_probs_b.bias, torch.float32 --> F32, shape = {512} INFO:hf-to-gguf:blk.48.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {4096, 512} INFO:hf-to-gguf:blk.48.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {5376, 4096} INFO:hf-to-gguf:blk.48.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {4096, 5376} INFO:hf-to-gguf:blk.49.ssm_a, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.49.ssm_d, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.49.ssm_conv1d.bias, torch.bfloat16 --> F32, shape = {10240} INFO:hf-to-gguf:blk.49.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 10240} INFO:hf-to-gguf:blk.49.ssm_dt.bias, torch.bfloat16 --> F32, shape = {128} INFO:hf-to-gguf:blk.49.ssm_in.weight, torch.bfloat16 --> BF16, shape = {4096, 18560} INFO:hf-to-gguf:blk.49.ssm_norm.weight, torch.bfloat16 --> F32, shape = {1024, 8} INFO:hf-to-gguf:blk.49.ssm_out.weight, torch.bfloat16 --> BF16, shape = {8192, 4096} INFO:hf-to-gguf:blk.49.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.50.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.50.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {2688, 1024, 512} INFO:hf-to-gguf:blk.50.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1024, 2688, 512} INFO:hf-to-gguf:blk.50.ffn_latent_down.weight, torch.bfloat16 --> BF16, shape = {4096, 1024} INFO:hf-to-gguf:blk.50.ffn_latent_up.weight, torch.bfloat16 --> BF16, shape = {1024, 4096} INFO:hf-to-gguf:blk.50.exp_probs_b.bias, torch.float32 --> F32, shape = {512} INFO:hf-to-gguf:blk.50.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {4096, 512} INFO:hf-to-gguf:blk.50.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {5376, 4096} INFO:hf-to-gguf:blk.50.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {4096, 5376} INFO:hf-to-gguf:blk.51.ssm_a, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.51.ssm_d, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.51.ssm_conv1d.bias, torch.bfloat16 --> F32, shape = {10240} INFO:hf-to-gguf:blk.51.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 10240} INFO:hf-to-gguf:blk.51.ssm_dt.bias, torch.bfloat16 --> F32, shape = {128} INFO:hf-to-gguf:blk.51.ssm_in.weight, torch.bfloat16 --> BF16, shape = {4096, 18560} INFO:hf-to-gguf:blk.51.ssm_norm.weight, torch.bfloat16 --> F32, shape = {1024, 8} INFO:hf-to-gguf:blk.51.ssm_out.weight, torch.bfloat16 --> BF16, shape = {8192, 4096} INFO:hf-to-gguf:blk.51.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.52.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.52.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {2688, 1024, 512} INFO:hf-to-gguf:blk.52.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1024, 2688, 512} INFO:hf-to-gguf:blk.52.ffn_latent_down.weight, torch.bfloat16 --> BF16, shape = {4096, 1024} INFO:hf-to-gguf:blk.52.ffn_latent_up.weight, torch.bfloat16 --> BF16, shape = {1024, 4096} INFO:hf-to-gguf:blk.52.exp_probs_b.bias, torch.float32 --> F32, shape = {512} INFO:hf-to-gguf:blk.52.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {4096, 512} INFO:hf-to-gguf:blk.52.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {5376, 4096} INFO:hf-to-gguf:blk.52.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {4096, 5376} INFO:hf-to-gguf:blk.53.ssm_a, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.53.ssm_d, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.53.ssm_conv1d.bias, torch.bfloat16 --> F32, shape = {10240} INFO:hf-to-gguf:blk.53.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 10240} INFO:hf-to-gguf:blk.53.ssm_dt.bias, torch.bfloat16 --> F32, shape = {128} INFO:hf-to-gguf:blk.53.ssm_in.weight, torch.bfloat16 --> BF16, shape = {4096, 18560} INFO:hf-to-gguf:blk.53.ssm_norm.weight, torch.bfloat16 --> F32, shape = {1024, 8} INFO:hf-to-gguf:blk.53.ssm_out.weight, torch.bfloat16 --> BF16, shape = {8192, 4096} INFO:hf-to-gguf:blk.53.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.54.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.54.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {2688, 1024, 512} INFO:hf-to-gguf:blk.54.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1024, 2688, 512} INFO:hf-to-gguf:blk.54.ffn_latent_down.weight, torch.bfloat16 --> BF16, shape = {4096, 1024} INFO:hf-to-gguf:blk.54.ffn_latent_up.weight, torch.bfloat16 --> BF16, shape = {1024, 4096} INFO:hf-to-gguf:blk.54.exp_probs_b.bias, torch.float32 --> F32, shape = {512} INFO:hf-to-gguf:blk.54.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {4096, 512} INFO:hf-to-gguf:blk.54.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {5376, 4096} INFO:hf-to-gguf:blk.54.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {4096, 5376} INFO:hf-to-gguf:blk.55.ssm_a, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.55.ssm_d, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.55.ssm_conv1d.bias, torch.bfloat16 --> F32, shape = {10240} INFO:hf-to-gguf:blk.55.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 10240} INFO:hf-to-gguf:blk.55.ssm_dt.bias, torch.bfloat16 --> F32, shape = {128} INFO:hf-to-gguf:blk.55.ssm_in.weight, torch.bfloat16 --> BF16, shape = {4096, 18560} INFO:hf-to-gguf:blk.55.ssm_norm.weight, torch.bfloat16 --> F32, shape = {1024, 8} INFO:hf-to-gguf:blk.55.ssm_out.weight, torch.bfloat16 --> BF16, shape = {8192, 4096} INFO:hf-to-gguf:blk.55.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.56.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.56.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {2688, 1024, 512} INFO:hf-to-gguf:blk.56.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1024, 2688, 512} INFO:hf-to-gguf:blk.56.ffn_latent_down.weight, torch.bfloat16 --> BF16, shape = {4096, 1024} INFO:hf-to-gguf:blk.56.ffn_latent_up.weight, torch.bfloat16 --> BF16, shape = {1024, 4096} INFO:hf-to-gguf:blk.56.exp_probs_b.bias, torch.float32 --> F32, shape = {512} INFO:hf-to-gguf:blk.56.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {4096, 512} INFO:hf-to-gguf:blk.56.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {5376, 4096} INFO:hf-to-gguf:blk.56.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {4096, 5376} INFO:hf-to-gguf:blk.57.ssm_a, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.57.ssm_d, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.57.ssm_conv1d.bias, torch.bfloat16 --> F32, shape = {10240} INFO:hf-to-gguf:blk.57.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 10240} INFO:hf-to-gguf:blk.57.ssm_dt.bias, torch.bfloat16 --> F32, shape = {128} INFO:hf-to-gguf:blk.57.ssm_in.weight, torch.bfloat16 --> BF16, shape = {4096, 18560} INFO:hf-to-gguf:blk.57.ssm_norm.weight, torch.bfloat16 --> F32, shape = {1024, 8} INFO:hf-to-gguf:blk.57.ssm_out.weight, torch.bfloat16 --> BF16, shape = {8192, 4096} INFO:hf-to-gguf:blk.57.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.58.attn_k.weight, torch.bfloat16 --> BF16, shape = {4096, 256} INFO:hf-to-gguf:blk.58.attn_output.weight, torch.bfloat16 --> BF16, shape = {4096, 4096} INFO:hf-to-gguf:blk.58.attn_q.weight, torch.bfloat16 --> BF16, shape = {4096, 4096} INFO:hf-to-gguf:blk.58.attn_v.weight, torch.bfloat16 --> BF16, shape = {4096, 256} INFO:hf-to-gguf:blk.58.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.59.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.59.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {2688, 1024, 512} INFO:hf-to-gguf:blk.59.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1024, 2688, 512} INFO:hf-to-gguf:blk.59.ffn_latent_down.weight, torch.bfloat16 --> BF16, shape = {4096, 1024} INFO:hf-to-gguf:blk.59.ffn_latent_up.weight, torch.bfloat16 --> BF16, shape = {1024, 4096} INFO:hf-to-gguf:blk.59.exp_probs_b.bias, torch.float32 --> F32, shape = {512} INFO:hf-to-gguf:blk.59.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {4096, 512} INFO:hf-to-gguf:blk.59.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {5376, 4096} INFO:hf-to-gguf:blk.59.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {4096, 5376} INFO:hf-to-gguf:blk.60.ssm_a, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.60.ssm_d, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.60.ssm_conv1d.bias, torch.bfloat16 --> F32, shape = {10240} INFO:hf-to-gguf:blk.60.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 10240} INFO:hf-to-gguf:blk.60.ssm_dt.bias, torch.bfloat16 --> F32, shape = {128} INFO:hf-to-gguf:blk.60.ssm_in.weight, torch.bfloat16 --> BF16, shape = {4096, 18560} INFO:hf-to-gguf:blk.60.ssm_norm.weight, torch.bfloat16 --> F32, shape = {1024, 8} INFO:hf-to-gguf:blk.60.ssm_out.weight, torch.bfloat16 --> BF16, shape = {8192, 4096} INFO:hf-to-gguf:blk.60.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.61.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.61.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {2688, 1024, 512} INFO:hf-to-gguf:blk.61.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1024, 2688, 512} INFO:hf-to-gguf:blk.61.ffn_latent_down.weight, torch.bfloat16 --> BF16, shape = {4096, 1024} INFO:hf-to-gguf:blk.61.ffn_latent_up.weight, torch.bfloat16 --> BF16, shape = {1024, 4096} INFO:hf-to-gguf:blk.61.exp_probs_b.bias, torch.float32 --> F32, shape = {512} INFO:hf-to-gguf:blk.61.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {4096, 512} INFO:hf-to-gguf:blk.61.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {5376, 4096} INFO:hf-to-gguf:blk.61.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {4096, 5376} INFO:hf-to-gguf:blk.62.ssm_a, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.62.ssm_d, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.62.ssm_conv1d.bias, torch.bfloat16 --> F32, shape = {10240} INFO:hf-to-gguf:blk.62.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 10240} INFO:hf-to-gguf:blk.62.ssm_dt.bias, torch.bfloat16 --> F32, shape = {128} INFO:hf-to-gguf:blk.62.ssm_in.weight, torch.bfloat16 --> BF16, shape = {4096, 18560} INFO:hf-to-gguf:blk.62.ssm_norm.weight, torch.bfloat16 --> F32, shape = {1024, 8} INFO:hf-to-gguf:blk.62.ssm_out.weight, torch.bfloat16 --> BF16, shape = {8192, 4096} INFO:hf-to-gguf:blk.62.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.63.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.63.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {2688, 1024, 512} INFO:hf-to-gguf:blk.63.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1024, 2688, 512} INFO:hf-to-gguf:blk.63.ffn_latent_down.weight, torch.bfloat16 --> BF16, shape = {4096, 1024} INFO:hf-to-gguf:blk.63.ffn_latent_up.weight, torch.bfloat16 --> BF16, shape = {1024, 4096} INFO:hf-to-gguf:blk.63.exp_probs_b.bias, torch.float32 --> F32, shape = {512} INFO:hf-to-gguf:blk.63.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {4096, 512} INFO:hf-to-gguf:blk.63.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {5376, 4096} INFO:hf-to-gguf:blk.63.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {4096, 5376} INFO:hf-to-gguf:blk.64.ssm_a, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.64.ssm_d, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.64.ssm_conv1d.bias, torch.bfloat16 --> F32, shape = {10240} INFO:hf-to-gguf:blk.64.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 10240} INFO:hf-to-gguf:blk.64.ssm_dt.bias, torch.bfloat16 --> F32, shape = {128} INFO:hf-to-gguf:blk.64.ssm_in.weight, torch.bfloat16 --> BF16, shape = {4096, 18560} INFO:hf-to-gguf:blk.64.ssm_norm.weight, torch.bfloat16 --> F32, shape = {1024, 8} INFO:hf-to-gguf:blk.64.ssm_out.weight, torch.bfloat16 --> BF16, shape = {8192, 4096} INFO:hf-to-gguf:blk.64.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.65.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.65.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {2688, 1024, 512} INFO:hf-to-gguf:blk.65.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1024, 2688, 512} INFO:hf-to-gguf:blk.65.ffn_latent_down.weight, torch.bfloat16 --> BF16, shape = {4096, 1024} INFO:hf-to-gguf:blk.65.ffn_latent_up.weight, torch.bfloat16 --> BF16, shape = {1024, 4096} INFO:hf-to-gguf:blk.65.exp_probs_b.bias, torch.float32 --> F32, shape = {512} INFO:hf-to-gguf:blk.65.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {4096, 512} INFO:hf-to-gguf:blk.65.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {5376, 4096} INFO:hf-to-gguf:blk.65.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {4096, 5376} INFO:hf-to-gguf:blk.66.ssm_a, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.66.ssm_d, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.66.ssm_conv1d.bias, torch.bfloat16 --> F32, shape = {10240} INFO:hf-to-gguf:blk.66.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 10240} INFO:hf-to-gguf:blk.66.ssm_dt.bias, torch.bfloat16 --> F32, shape = {128} INFO:hf-to-gguf:blk.66.ssm_in.weight, torch.bfloat16 --> BF16, shape = {4096, 18560} INFO:hf-to-gguf:blk.66.ssm_norm.weight, torch.bfloat16 --> F32, shape = {1024, 8} INFO:hf-to-gguf:blk.66.ssm_out.weight, torch.bfloat16 --> BF16, shape = {8192, 4096} INFO:hf-to-gguf:blk.66.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.67.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.67.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {2688, 1024, 512} INFO:hf-to-gguf:blk.67.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1024, 2688, 512} INFO:hf-to-gguf:blk.67.ffn_latent_down.weight, torch.bfloat16 --> BF16, shape = {4096, 1024} INFO:hf-to-gguf:blk.67.ffn_latent_up.weight, torch.bfloat16 --> BF16, shape = {1024, 4096} INFO:hf-to-gguf:blk.67.exp_probs_b.bias, torch.float32 --> F32, shape = {512} INFO:hf-to-gguf:blk.67.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {4096, 512} INFO:hf-to-gguf:blk.67.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {5376, 4096} INFO:hf-to-gguf:blk.67.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {4096, 5376} INFO:hf-to-gguf:blk.68.ssm_a, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.68.ssm_d, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.68.ssm_conv1d.bias, torch.bfloat16 --> F32, shape = {10240} INFO:hf-to-gguf:blk.68.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 10240} INFO:hf-to-gguf:blk.68.ssm_dt.bias, torch.bfloat16 --> F32, shape = {128} INFO:hf-to-gguf:blk.68.ssm_in.weight, torch.bfloat16 --> BF16, shape = {4096, 18560} INFO:hf-to-gguf:blk.68.ssm_norm.weight, torch.bfloat16 --> F32, shape = {1024, 8} INFO:hf-to-gguf:blk.68.ssm_out.weight, torch.bfloat16 --> BF16, shape = {8192, 4096} INFO:hf-to-gguf:blk.68.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.69.attn_k.weight, torch.bfloat16 --> BF16, shape = {4096, 256} INFO:hf-to-gguf:blk.69.attn_output.weight, torch.bfloat16 --> BF16, shape = {4096, 4096} INFO:hf-to-gguf:blk.69.attn_q.weight, torch.bfloat16 --> BF16, shape = {4096, 4096} INFO:hf-to-gguf:blk.69.attn_v.weight, torch.bfloat16 --> BF16, shape = {4096, 256} INFO:hf-to-gguf:blk.69.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.70.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.70.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {2688, 1024, 512} INFO:hf-to-gguf:blk.70.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1024, 2688, 512} INFO:hf-to-gguf:blk.70.ffn_latent_down.weight, torch.bfloat16 --> BF16, shape = {4096, 1024} INFO:hf-to-gguf:blk.70.ffn_latent_up.weight, torch.bfloat16 --> BF16, shape = {1024, 4096} INFO:hf-to-gguf:blk.70.exp_probs_b.bias, torch.float32 --> F32, shape = {512} INFO:hf-to-gguf:blk.70.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {4096, 512} INFO:hf-to-gguf:blk.70.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {5376, 4096} INFO:hf-to-gguf:blk.70.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {4096, 5376} INFO:hf-to-gguf:blk.71.ssm_a, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.71.ssm_d, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.71.ssm_conv1d.bias, torch.bfloat16 --> F32, shape = {10240} INFO:hf-to-gguf:blk.71.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 10240} INFO:hf-to-gguf:blk.71.ssm_dt.bias, torch.bfloat16 --> F32, shape = {128} INFO:hf-to-gguf:blk.71.ssm_in.weight, torch.bfloat16 --> BF16, shape = {4096, 18560} INFO:hf-to-gguf:blk.71.ssm_norm.weight, torch.bfloat16 --> F32, shape = {1024, 8} INFO:hf-to-gguf:blk.71.ssm_out.weight, torch.bfloat16 --> BF16, shape = {8192, 4096} INFO:hf-to-gguf:blk.71.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.72.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.72.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {2688, 1024, 512} INFO:hf-to-gguf:blk.72.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1024, 2688, 512} INFO:hf-to-gguf:blk.72.ffn_latent_down.weight, torch.bfloat16 --> BF16, shape = {4096, 1024} INFO:hf-to-gguf:blk.72.ffn_latent_up.weight, torch.bfloat16 --> BF16, shape = {1024, 4096} INFO:hf-to-gguf:blk.72.exp_probs_b.bias, torch.float32 --> F32, shape = {512} INFO:hf-to-gguf:blk.72.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {4096, 512} INFO:hf-to-gguf:blk.72.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {5376, 4096} INFO:hf-to-gguf:blk.72.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {4096, 5376} INFO:hf-to-gguf:blk.73.ssm_a, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.73.ssm_d, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.73.ssm_conv1d.bias, torch.bfloat16 --> F32, shape = {10240} INFO:hf-to-gguf:blk.73.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 10240} INFO:hf-to-gguf:blk.73.ssm_dt.bias, torch.bfloat16 --> F32, shape = {128} INFO:hf-to-gguf:blk.73.ssm_in.weight, torch.bfloat16 --> BF16, shape = {4096, 18560} INFO:hf-to-gguf:blk.73.ssm_norm.weight, torch.bfloat16 --> F32, shape = {1024, 8} INFO:hf-to-gguf:blk.73.ssm_out.weight, torch.bfloat16 --> BF16, shape = {8192, 4096} INFO:hf-to-gguf:blk.73.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.74.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.74.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {2688, 1024, 512} INFO:hf-to-gguf:blk.74.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1024, 2688, 512} INFO:hf-to-gguf:blk.74.ffn_latent_down.weight, torch.bfloat16 --> BF16, shape = {4096, 1024} INFO:hf-to-gguf:blk.74.ffn_latent_up.weight, torch.bfloat16 --> BF16, shape = {1024, 4096} INFO:hf-to-gguf:blk.74.exp_probs_b.bias, torch.float32 --> F32, shape = {512} INFO:hf-to-gguf:blk.74.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {4096, 512} INFO:hf-to-gguf:blk.74.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {5376, 4096} INFO:hf-to-gguf:blk.74.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {4096, 5376} INFO:hf-to-gguf:blk.75.ssm_a, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.75.ssm_d, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.75.ssm_conv1d.bias, torch.bfloat16 --> F32, shape = {10240} INFO:hf-to-gguf:blk.75.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 10240} INFO:hf-to-gguf:blk.75.ssm_dt.bias, torch.bfloat16 --> F32, shape = {128} INFO:hf-to-gguf:blk.75.ssm_in.weight, torch.bfloat16 --> BF16, shape = {4096, 18560} INFO:hf-to-gguf:blk.75.ssm_norm.weight, torch.bfloat16 --> F32, shape = {1024, 8} INFO:hf-to-gguf:blk.75.ssm_out.weight, torch.bfloat16 --> BF16, shape = {8192, 4096} INFO:hf-to-gguf:blk.75.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.76.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.76.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {2688, 1024, 512} INFO:hf-to-gguf:blk.76.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1024, 2688, 512} INFO:hf-to-gguf:blk.76.ffn_latent_down.weight, torch.bfloat16 --> BF16, shape = {4096, 1024} INFO:hf-to-gguf:blk.76.ffn_latent_up.weight, torch.bfloat16 --> BF16, shape = {1024, 4096} INFO:hf-to-gguf:blk.76.exp_probs_b.bias, torch.float32 --> F32, shape = {512} INFO:hf-to-gguf:blk.76.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {4096, 512} INFO:hf-to-gguf:blk.76.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {5376, 4096} INFO:hf-to-gguf:blk.76.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {4096, 5376} INFO:hf-to-gguf:blk.77.ssm_a, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.77.ssm_d, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.77.ssm_conv1d.bias, torch.bfloat16 --> F32, shape = {10240} INFO:hf-to-gguf:blk.77.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 10240} INFO:hf-to-gguf:blk.77.ssm_dt.bias, torch.bfloat16 --> F32, shape = {128} INFO:hf-to-gguf:blk.77.ssm_in.weight, torch.bfloat16 --> BF16, shape = {4096, 18560} INFO:hf-to-gguf:blk.77.ssm_norm.weight, torch.bfloat16 --> F32, shape = {1024, 8} INFO:hf-to-gguf:blk.77.ssm_out.weight, torch.bfloat16 --> BF16, shape = {8192, 4096} INFO:hf-to-gguf:blk.77.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.78.attn_k.weight, torch.bfloat16 --> BF16, shape = {4096, 256} INFO:hf-to-gguf:blk.78.attn_output.weight, torch.bfloat16 --> BF16, shape = {4096, 4096} INFO:hf-to-gguf:blk.78.attn_q.weight, torch.bfloat16 --> BF16, shape = {4096, 4096} INFO:hf-to-gguf:blk.78.attn_v.weight, torch.bfloat16 --> BF16, shape = {4096, 256} INFO:hf-to-gguf:blk.78.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.79.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.79.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {2688, 1024, 512} INFO:hf-to-gguf:blk.79.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1024, 2688, 512} INFO:hf-to-gguf:blk.79.ffn_latent_down.weight, torch.bfloat16 --> BF16, shape = {4096, 1024} INFO:hf-to-gguf:blk.79.ffn_latent_up.weight, torch.bfloat16 --> BF16, shape = {1024, 4096} INFO:hf-to-gguf:blk.79.exp_probs_b.bias, torch.float32 --> F32, shape = {512} INFO:hf-to-gguf:blk.79.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {4096, 512} INFO:hf-to-gguf:blk.79.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {5376, 4096} INFO:hf-to-gguf:blk.79.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {4096, 5376} INFO:hf-to-gguf:blk.80.ssm_a, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.80.ssm_d, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.80.ssm_conv1d.bias, torch.bfloat16 --> F32, shape = {10240} INFO:hf-to-gguf:blk.80.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 10240} INFO:hf-to-gguf:blk.80.ssm_dt.bias, torch.bfloat16 --> F32, shape = {128} INFO:hf-to-gguf:blk.80.ssm_in.weight, torch.bfloat16 --> BF16, shape = {4096, 18560} INFO:hf-to-gguf:blk.80.ssm_norm.weight, torch.bfloat16 --> F32, shape = {1024, 8} INFO:hf-to-gguf:blk.80.ssm_out.weight, torch.bfloat16 --> BF16, shape = {8192, 4096} INFO:hf-to-gguf:blk.80.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.81.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.81.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {2688, 1024, 512} INFO:hf-to-gguf:blk.81.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1024, 2688, 512} INFO:hf-to-gguf:blk.81.ffn_latent_down.weight, torch.bfloat16 --> BF16, shape = {4096, 1024} INFO:hf-to-gguf:blk.81.ffn_latent_up.weight, torch.bfloat16 --> BF16, shape = {1024, 4096} INFO:hf-to-gguf:blk.81.exp_probs_b.bias, torch.float32 --> F32, shape = {512} INFO:hf-to-gguf:blk.81.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {4096, 512} INFO:hf-to-gguf:blk.81.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {5376, 4096} INFO:hf-to-gguf:blk.81.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {4096, 5376} INFO:hf-to-gguf:blk.82.ssm_a, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.82.ssm_d, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.82.ssm_conv1d.bias, torch.bfloat16 --> F32, shape = {10240} INFO:hf-to-gguf:blk.82.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 10240} INFO:hf-to-gguf:blk.82.ssm_dt.bias, torch.bfloat16 --> F32, shape = {128} INFO:hf-to-gguf:blk.82.ssm_in.weight, torch.bfloat16 --> BF16, shape = {4096, 18560} INFO:hf-to-gguf:blk.82.ssm_norm.weight, torch.bfloat16 --> F32, shape = {1024, 8} INFO:hf-to-gguf:blk.82.ssm_out.weight, torch.bfloat16 --> BF16, shape = {8192, 4096} INFO:hf-to-gguf:blk.82.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.83.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.83.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {2688, 1024, 512} INFO:hf-to-gguf:blk.83.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1024, 2688, 512} INFO:hf-to-gguf:blk.83.ffn_latent_down.weight, torch.bfloat16 --> BF16, shape = {4096, 1024} INFO:hf-to-gguf:blk.83.ffn_latent_up.weight, torch.bfloat16 --> BF16, shape = {1024, 4096} INFO:hf-to-gguf:blk.83.exp_probs_b.bias, torch.float32 --> F32, shape = {512} INFO:hf-to-gguf:blk.83.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {4096, 512} INFO:hf-to-gguf:blk.83.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {5376, 4096} INFO:hf-to-gguf:blk.83.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {4096, 5376} INFO:hf-to-gguf:blk.84.ssm_a, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.84.ssm_d, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.84.ssm_conv1d.bias, torch.bfloat16 --> F32, shape = {10240} INFO:hf-to-gguf:blk.84.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 10240} INFO:hf-to-gguf:blk.84.ssm_dt.bias, torch.bfloat16 --> F32, shape = {128} INFO:hf-to-gguf:blk.84.ssm_in.weight, torch.bfloat16 --> BF16, shape = {4096, 18560} INFO:hf-to-gguf:blk.84.ssm_norm.weight, torch.bfloat16 --> F32, shape = {1024, 8} INFO:hf-to-gguf:blk.84.ssm_out.weight, torch.bfloat16 --> BF16, shape = {8192, 4096} INFO:hf-to-gguf:blk.84.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.85.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.85.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {2688, 1024, 512} INFO:hf-to-gguf:blk.85.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1024, 2688, 512} INFO:hf-to-gguf:blk.85.ffn_latent_down.weight, torch.bfloat16 --> BF16, shape = {4096, 1024} INFO:hf-to-gguf:blk.85.ffn_latent_up.weight, torch.bfloat16 --> BF16, shape = {1024, 4096} INFO:hf-to-gguf:blk.85.exp_probs_b.bias, torch.float32 --> F32, shape = {512} INFO:hf-to-gguf:blk.85.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {4096, 512} INFO:hf-to-gguf:blk.85.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {5376, 4096} INFO:hf-to-gguf:blk.85.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {4096, 5376} INFO:hf-to-gguf:blk.86.ssm_a, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.86.ssm_d, torch.bfloat16 --> F32, shape = {1, 128} INFO:hf-to-gguf:blk.86.ssm_conv1d.bias, torch.bfloat16 --> F32, shape = {10240} INFO:hf-to-gguf:blk.86.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 10240} INFO:hf-to-gguf:blk.86.ssm_dt.bias, torch.bfloat16 --> F32, shape = {128} INFO:hf-to-gguf:blk.86.ssm_in.weight, torch.bfloat16 --> BF16, shape = {4096, 18560} INFO:hf-to-gguf:blk.86.ssm_norm.weight, torch.bfloat16 --> F32, shape = {1024, 8} INFO:hf-to-gguf:blk.86.ssm_out.weight, torch.bfloat16 --> BF16, shape = {8192, 4096} INFO:hf-to-gguf:blk.86.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.87.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:blk.87.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {2688, 1024, 512} INFO:hf-to-gguf:blk.87.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1024, 2688, 512} INFO:hf-to-gguf:blk.87.ffn_latent_down.weight, torch.bfloat16 --> BF16, shape = {4096, 1024} INFO:hf-to-gguf:blk.87.ffn_latent_up.weight, torch.bfloat16 --> BF16, shape = {1024, 4096} INFO:hf-to-gguf:blk.87.exp_probs_b.bias, torch.float32 --> F32, shape = {512} INFO:hf-to-gguf:blk.87.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {4096, 512} INFO:hf-to-gguf:blk.87.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {5376, 4096} INFO:hf-to-gguf:blk.87.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {4096, 5376} INFO:hf-to-gguf:output_norm.weight, torch.bfloat16 --> F32, shape = {4096} INFO:hf-to-gguf:output.weight, torch.bfloat16 --> BF16, shape = {4096, 131072} INFO:hf-to-gguf:Set meta model INFO:hf-to-gguf:Set model parameters WARNING:hf-to-gguf:Ignoring head_dim (128) from config for Granite INFO:hf-to-gguf:gguf: context length = 1048576 INFO:hf-to-gguf:gguf: embedding length = 4096 INFO:hf-to-gguf:gguf: feed forward length = 2688 INFO:hf-to-gguf:gguf: head count = 32 INFO:hf-to-gguf:gguf: key-value head count = 2 INFO:hf-to-gguf:gguf: layer norm epsilon = 1e-05 INFO:hf-to-gguf:gguf: expert count = 512 INFO:hf-to-gguf:gguf: experts used count = 22 INFO:hf-to-gguf:gguf: expert groups count = 1 INFO:hf-to-gguf:gguf: expert groups used count = 1 INFO:hf-to-gguf:gguf: file type = 32 WARNING:gguf.gguf_writer:Duplicated key name 'nemotron_h_moe.attention.head_count_kv', overwriting it with new value [0, 0, 0, 0, 0, 0, 0, 2, 0, 0, 0, 0, 0, 0, 0, 0, 2, 0, 0, 0, 0, 0, 0, 0, 0, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 2, 0, 0, 0, 0, 0, 0, 0, 0, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0] of type ARRAY WARNING:gguf.gguf_writer:Duplicated key name 'nemotron_h_moe.context_length', overwriting it with new value 1048576 of type UINT32 WARNING:gguf.gguf_writer:Duplicated key name 'nemotron_h_moe.feed_forward_length', overwriting it with new value [0, 2688, 0, 2688, 0, 2688, 0, 0, 2688, 0, 2688, 0, 2688, 0, 2688, 0, 0, 2688, 0, 2688, 0, 2688, 0, 2688, 0, 0, 2688, 0, 2688, 0, 2688, 0, 2688, 0, 2688, 0, 0, 2688, 0, 2688, 0, 2688, 0, 2688, 0, 2688, 0, 0, 2688, 0, 2688, 0, 2688, 0, 2688, 0, 2688, 0, 0, 2688, 0, 2688, 0, 2688, 0, 2688, 0, 2688, 0, 0, 2688, 0, 2688, 0, 2688, 0, 2688, 0, 0, 2688, 0, 2688, 0, 2688, 0, 2688, 0, 2688] of type ARRAY WARNING:gguf.gguf_writer:Duplicated key name 'nemotron_h_moe.expert_used_count', overwriting it with new value 22 of type UINT32 WARNING:gguf.gguf_writer:Duplicated key name 'nemotron_h_moe.expert_count', overwriting it with new value 512 of type UINT32 WARNING:gguf.gguf_writer:Duplicated key name 'nemotron_h_moe.expert_group_count', overwriting it with new value 1 of type UINT32 WARNING:gguf.gguf_writer:Duplicated key name 'nemotron_h_moe.expert_used_count', overwriting it with new value 22 of type UINT32 INFO:hf-to-gguf:Set model quantization version INFO:hf-to-gguf:Set model tokenizer INFO:gguf.vocab:Adding 269443 merge(s). INFO:gguf.vocab:Setting special token type bos to 1 INFO:gguf.vocab:Setting special token type eos to 11 INFO:gguf.vocab:Setting special token type unk to 0 INFO:gguf.vocab:Setting special token type pad to 11 INFO:gguf.vocab:Setting add_bos_token to False INFO:gguf.vocab:Setting add_eos_token to False INFO:gguf.vocab:Setting chat_template to {% macro render_extra_keys(json_dict, handled_keys) %} {%- if json_dict is mapping %} {%- for json_key in json_dict if json_key not in handled_keys %} {%- if json_dict[json_key] is mapping or (json_dict[json_key] is sequence and json_dict[json_key] is not string) %} {{- '\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | tojson | safe) ~ '' }} {%- else %} {{-'\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | string) ~ '' }} {%- endif %} {%- endfor %} {%- endif %} {% endmacro %} {%- macro render_content(content) -%} {%- if content is none -%} {{- '' -}} {%- elif content is string -%} {{- content | string -}} {%- else -%} {%- set text_ns = namespace(val='') -%} {%- set counters = namespace(images=0, videos=0) -%} {%- for part in content -%} {%- if part['type'] == 'image' or part['type'] == 'image_url' or part['type'] == 'input_image' -%} {%- set counters.images = counters.images + 1 -%} {%- elif part['type'] == 'video' or part['type'] == 'video_url' or part['type'] == 'input_video' -%} {%- set counters.videos = counters.videos + 1 -%} {%- elif part['type'] == 'text' or part['type'] == 'input_text' -%} {%- set text_ns.val = text_ns.val + (part['text'] | default('', true)) -%} {%- endif -%} {%- endfor -%} {%- if '' in text_ns.val -%} {%- set counters.images = 0 -%} {%- endif -%} {%- if '