lingtiny30vq3 / results /convert_std.log
HelloSun's picture
LUT-VQ3-64: machine-tuned (threads/NUMA/ubatch), full 128k ctx data, one-click build, results
511ba50 verified
Raw History Blame Contribute Delete
68.2 kB
INFO:hf-to-gguf:Loading model: model
WARNING:hf-to-gguf:Failed to load model config from hf-ling/model: The repository hf-ling/model contains custom code which must be executed to correctly load the model. You can inspect the repository content at /mnt/disk3/work/21434/temp/work1/A/hf-ling/model .
You can inspect the repository content at https://hf.co/hf-ling/model.
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: BailingMoeV3ForCausalLM
WARNING:hf-to-gguf:Failed to load model config from hf-ling/model: The repository hf-ling/model contains custom code which must be executed to correctly load the model. You can inspect the repository content at /mnt/disk3/work/21434/temp/work1/A/hf-ling/model .
You can inspect the repository content at https://hf.co/hf-ling/model.
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-00000-of-00032.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00001-of-00032.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00002-of-00032.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00003-of-00032.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00004-of-00032.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00005-of-00032.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00006-of-00032.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00007-of-00032.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00008-of-00032.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00009-of-00032.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00010-of-00032.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00011-of-00032.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00012-of-00032.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00013-of-00032.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00014-of-00032.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00015-of-00032.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00016-of-00032.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00017-of-00032.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00018-of-00032.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00019-of-00032.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00020-of-00032.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00021-of-00032.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00022-of-00032.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00023-of-00032.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00024-of-00032.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00025-of-00032.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00026-of-00032.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00027-of-00032.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00028-of-00032.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00029-of-00032.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00030-of-00032.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00031-of-00032.safetensors'
INFO:gguf.gguf_writer:gguf: This GGUF file is for Little Endian only
INFO:hf-to-gguf:Exporting model...
INFO:hf-to-gguf:blk.0.ssm_a, torch.float32 --> F32, shape = {1, 16}
INFO:hf-to-gguf:blk.0.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {1536, 16}
INFO:hf-to-gguf:blk.0.ssm_dt.bias, torch.float32 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.0.ssm_f_a.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.0.ssm_g_a.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.0.ssm_conv1d_k.weight, torch.bfloat16 --> F32, shape = {4, 1, 2048, 1}
INFO:hf-to-gguf:blk.0.attn_k.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.0.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.0.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 1536}
INFO:hf-to-gguf:blk.0.ssm_conv1d_q.weight, torch.bfloat16 --> F32, shape = {4, 1, 2048, 1}
INFO:hf-to-gguf:blk.0.attn_q.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.0.ssm_conv1d_v.weight, torch.bfloat16 --> F32, shape = {4, 1, 2048, 1}
INFO:hf-to-gguf:blk.0.attn_v.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.0.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536}
INFO:hf-to-gguf:blk.0.ffn_down.weight, torch.bfloat16 --> BF16, shape = {4608, 1536}
INFO:hf-to-gguf:blk.0.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {1536, 4608}
INFO:hf-to-gguf:blk.0.ffn_up.weight, torch.bfloat16 --> BF16, shape = {1536, 4608}
INFO:hf-to-gguf:blk.0.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536}
INFO:hf-to-gguf:blk.1.ssm_a, torch.float32 --> F32, shape = {1, 16}
INFO:hf-to-gguf:blk.1.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {1536, 16}
INFO:hf-to-gguf:blk.1.ssm_dt.bias, torch.float32 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.1.ssm_f_a.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.1.ssm_g_a.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.1.ssm_conv1d_k.weight, torch.bfloat16 --> F32, shape = {4, 1, 2048, 1}
INFO:hf-to-gguf:blk.1.attn_k.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.1.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.1.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 1536}
INFO:hf-to-gguf:blk.1.ssm_conv1d_q.weight, torch.bfloat16 --> F32, shape = {4, 1, 2048, 1}
INFO:hf-to-gguf:blk.1.attn_q.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.1.ssm_conv1d_v.weight, torch.bfloat16 --> F32, shape = {4, 1, 2048, 1}
INFO:hf-to-gguf:blk.1.attn_v.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.1.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536}
INFO:hf-to-gguf:blk.1.exp_probs_b.bias, torch.float32 --> F32, shape = {128}
INFO:hf-to-gguf:blk.1.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {1536, 128}
INFO:hf-to-gguf:blk.1.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 1536}
INFO:hf-to-gguf:blk.1.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {1536, 512}
INFO:hf-to-gguf:blk.1.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {1536, 512}
INFO:hf-to-gguf:blk.1.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536}
INFO:hf-to-gguf:blk.2.ssm_a, torch.float32 --> F32, shape = {1, 16}
INFO:hf-to-gguf:blk.2.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {1536, 16}
INFO:hf-to-gguf:blk.2.ssm_dt.bias, torch.float32 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.2.ssm_f_a.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.2.ssm_g_a.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.2.ssm_conv1d_k.weight, torch.bfloat16 --> F32, shape = {4, 1, 2048, 1}
INFO:hf-to-gguf:blk.2.attn_k.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.2.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.2.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 1536}
INFO:hf-to-gguf:blk.2.ssm_conv1d_q.weight, torch.bfloat16 --> F32, shape = {4, 1, 2048, 1}
INFO:hf-to-gguf:blk.2.attn_q.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.2.ssm_conv1d_v.weight, torch.bfloat16 --> F32, shape = {4, 1, 2048, 1}
INFO:hf-to-gguf:blk.2.attn_v.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.2.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536}
INFO:hf-to-gguf:blk.2.exp_probs_b.bias, torch.float32 --> F32, shape = {128}
INFO:hf-to-gguf:blk.2.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {1536, 128}
INFO:hf-to-gguf:blk.2.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 1536}
INFO:hf-to-gguf:blk.2.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {1536, 512}
INFO:hf-to-gguf:blk.2.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {1536, 512}
INFO:hf-to-gguf:blk.2.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536}
INFO:hf-to-gguf:blk.3.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 1536}
INFO:hf-to-gguf:blk.3.attn_gate.weight, torch.bfloat16 --> BF16, shape = {1536, 16}
INFO:hf-to-gguf:blk.3.attn_kv_a_norm.weight, torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.3.attn_kv_a_mqa.weight, torch.bfloat16 --> BF16, shape = {1536, 576}
INFO:hf-to-gguf:blk.3.attn_k_b.weight, torch.bfloat16 --> BF16, shape = {128, 512, 16}
INFO:hf-to-gguf:blk.3.attn_v_b.weight, torch.bfloat16 --> BF16, shape = {512, 128, 16}
INFO:hf-to-gguf:blk.3.attn_q_a_norm.weight, torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.3.attn_q_a.weight, torch.bfloat16 --> BF16, shape = {1536, 256}
INFO:hf-to-gguf:blk.3.attn_q_b.weight, torch.bfloat16 --> BF16, shape = {256, 3072}
INFO:hf-to-gguf:blk.3.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536}
INFO:hf-to-gguf:blk.3.exp_probs_b.bias, torch.float32 --> F32, shape = {128}
INFO:hf-to-gguf:blk.3.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {1536, 128}
INFO:hf-to-gguf:blk.3.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 1536}
INFO:hf-to-gguf:blk.3.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {1536, 512}
INFO:hf-to-gguf:blk.3.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {1536, 512}
INFO:hf-to-gguf:blk.3.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536}
INFO:hf-to-gguf:blk.4.ssm_a, torch.float32 --> F32, shape = {1, 16}
INFO:hf-to-gguf:blk.4.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {1536, 16}
INFO:hf-to-gguf:blk.4.ssm_dt.bias, torch.float32 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.4.ssm_f_a.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.4.ssm_g_a.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.4.ssm_conv1d_k.weight, torch.bfloat16 --> F32, shape = {4, 1, 2048, 1}
INFO:hf-to-gguf:blk.4.attn_k.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.4.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.4.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 1536}
INFO:hf-to-gguf:blk.4.ssm_conv1d_q.weight, torch.bfloat16 --> F32, shape = {4, 1, 2048, 1}
INFO:hf-to-gguf:blk.4.attn_q.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.4.ssm_conv1d_v.weight, torch.bfloat16 --> F32, shape = {4, 1, 2048, 1}
INFO:hf-to-gguf:blk.4.attn_v.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.4.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536}
INFO:hf-to-gguf:blk.4.exp_probs_b.bias, torch.float32 --> F32, shape = {128}
INFO:hf-to-gguf:blk.4.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {1536, 128}
INFO:hf-to-gguf:blk.4.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 1536}
INFO:hf-to-gguf:blk.4.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {1536, 512}
INFO:hf-to-gguf:blk.4.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {1536, 512}
INFO:hf-to-gguf:blk.4.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536}
INFO:hf-to-gguf:blk.5.ssm_a, torch.float32 --> F32, shape = {1, 16}
INFO:hf-to-gguf:blk.5.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {1536, 16}
INFO:hf-to-gguf:blk.5.ssm_dt.bias, torch.float32 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.5.ssm_f_a.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.5.ssm_g_a.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.5.ssm_conv1d_k.weight, torch.bfloat16 --> F32, shape = {4, 1, 2048, 1}
INFO:hf-to-gguf:blk.5.attn_k.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.5.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.5.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 1536}
INFO:hf-to-gguf:blk.5.ssm_conv1d_q.weight, torch.bfloat16 --> F32, shape = {4, 1, 2048, 1}
INFO:hf-to-gguf:blk.5.attn_q.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.5.ssm_conv1d_v.weight, torch.bfloat16 --> F32, shape = {4, 1, 2048, 1}
INFO:hf-to-gguf:blk.5.attn_v.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.5.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536}
INFO:hf-to-gguf:blk.5.exp_probs_b.bias, torch.float32 --> F32, shape = {128}
INFO:hf-to-gguf:blk.5.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {1536, 128}
INFO:hf-to-gguf:blk.5.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 1536}
INFO:hf-to-gguf:blk.5.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {1536, 512}
INFO:hf-to-gguf:blk.5.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {1536, 512}
INFO:hf-to-gguf:blk.5.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536}
INFO:hf-to-gguf:token_embd.weight, torch.bfloat16 --> BF16, shape = {1536, 157184}
INFO:hf-to-gguf:blk.1.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 1536, 128}
INFO:hf-to-gguf:blk.1.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {1536, 512, 128}
INFO:hf-to-gguf:blk.1.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1536, 512, 128}
INFO:hf-to-gguf:blk.2.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 1536, 128}
INFO:hf-to-gguf:blk.2.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {1536, 512, 128}
INFO:hf-to-gguf:blk.2.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1536, 512, 128}
INFO:hf-to-gguf:blk.3.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 1536, 128}
INFO:hf-to-gguf:blk.3.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {1536, 512, 128}
INFO:hf-to-gguf:blk.3.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1536, 512, 128}
INFO:hf-to-gguf:blk.4.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 1536, 128}
INFO:hf-to-gguf:blk.4.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {1536, 512, 128}
INFO:hf-to-gguf:blk.4.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1536, 512, 128}
INFO:hf-to-gguf:blk.5.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 1536, 128}
INFO:hf-to-gguf:blk.5.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {1536, 512, 128}
INFO:hf-to-gguf:blk.5.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1536, 512, 128}
INFO:hf-to-gguf:blk.10.ssm_a, torch.float32 --> F32, shape = {1, 16}
INFO:hf-to-gguf:blk.10.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {1536, 16}
INFO:hf-to-gguf:blk.10.ssm_dt.bias, torch.float32 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.10.ssm_f_a.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.10.ssm_g_a.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.10.ssm_conv1d_k.weight, torch.bfloat16 --> F32, shape = {4, 1, 2048, 1}
INFO:hf-to-gguf:blk.10.attn_k.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.10.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.10.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 1536}
INFO:hf-to-gguf:blk.10.ssm_conv1d_q.weight, torch.bfloat16 --> F32, shape = {4, 1, 2048, 1}
INFO:hf-to-gguf:blk.10.attn_q.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.10.ssm_conv1d_v.weight, torch.bfloat16 --> F32, shape = {4, 1, 2048, 1}
INFO:hf-to-gguf:blk.10.attn_v.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.10.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536}
INFO:hf-to-gguf:blk.10.exp_probs_b.bias, torch.float32 --> F32, shape = {128}
INFO:hf-to-gguf:blk.10.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {1536, 128}
INFO:hf-to-gguf:blk.10.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 1536}
INFO:hf-to-gguf:blk.10.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {1536, 512}
INFO:hf-to-gguf:blk.10.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {1536, 512}
INFO:hf-to-gguf:blk.10.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536}
INFO:hf-to-gguf:blk.11.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 1536}
INFO:hf-to-gguf:blk.11.attn_gate.weight, torch.bfloat16 --> BF16, shape = {1536, 16}
INFO:hf-to-gguf:blk.11.attn_kv_a_norm.weight, torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.11.attn_kv_a_mqa.weight, torch.bfloat16 --> BF16, shape = {1536, 576}
INFO:hf-to-gguf:blk.11.attn_k_b.weight, torch.bfloat16 --> BF16, shape = {128, 512, 16}
INFO:hf-to-gguf:blk.11.attn_v_b.weight, torch.bfloat16 --> BF16, shape = {512, 128, 16}
INFO:hf-to-gguf:blk.11.attn_q_a_norm.weight, torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.11.attn_q_a.weight, torch.bfloat16 --> BF16, shape = {1536, 256}
INFO:hf-to-gguf:blk.11.attn_q_b.weight, torch.bfloat16 --> BF16, shape = {256, 3072}
INFO:hf-to-gguf:blk.11.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536}
INFO:hf-to-gguf:blk.11.exp_probs_b.bias, torch.float32 --> F32, shape = {128}
INFO:hf-to-gguf:blk.11.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {1536, 128}
INFO:hf-to-gguf:blk.11.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 1536}
INFO:hf-to-gguf:blk.11.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {1536, 512}
INFO:hf-to-gguf:blk.11.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {1536, 512}
INFO:hf-to-gguf:blk.11.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536}
INFO:hf-to-gguf:blk.6.ssm_a, torch.float32 --> F32, shape = {1, 16}
INFO:hf-to-gguf:blk.6.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {1536, 16}
INFO:hf-to-gguf:blk.6.ssm_dt.bias, torch.float32 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.6.ssm_f_a.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.6.ssm_g_a.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.6.ssm_conv1d_k.weight, torch.bfloat16 --> F32, shape = {4, 1, 2048, 1}
INFO:hf-to-gguf:blk.6.attn_k.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.6.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.6.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 1536}
INFO:hf-to-gguf:blk.6.ssm_conv1d_q.weight, torch.bfloat16 --> F32, shape = {4, 1, 2048, 1}
INFO:hf-to-gguf:blk.6.attn_q.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.6.ssm_conv1d_v.weight, torch.bfloat16 --> F32, shape = {4, 1, 2048, 1}
INFO:hf-to-gguf:blk.6.attn_v.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.6.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536}
INFO:hf-to-gguf:blk.6.exp_probs_b.bias, torch.float32 --> F32, shape = {128}
INFO:hf-to-gguf:blk.6.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {1536, 128}
INFO:hf-to-gguf:blk.6.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 1536}
INFO:hf-to-gguf:blk.6.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {1536, 512}
INFO:hf-to-gguf:blk.6.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {1536, 512}
INFO:hf-to-gguf:blk.6.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536}
INFO:hf-to-gguf:blk.7.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 1536}
INFO:hf-to-gguf:blk.7.attn_gate.weight, torch.bfloat16 --> BF16, shape = {1536, 16}
INFO:hf-to-gguf:blk.7.attn_kv_a_norm.weight, torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.7.attn_kv_a_mqa.weight, torch.bfloat16 --> BF16, shape = {1536, 576}
INFO:hf-to-gguf:blk.7.attn_k_b.weight, torch.bfloat16 --> BF16, shape = {128, 512, 16}
INFO:hf-to-gguf:blk.7.attn_v_b.weight, torch.bfloat16 --> BF16, shape = {512, 128, 16}
INFO:hf-to-gguf:blk.7.attn_q_a_norm.weight, torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.7.attn_q_a.weight, torch.bfloat16 --> BF16, shape = {1536, 256}
INFO:hf-to-gguf:blk.7.attn_q_b.weight, torch.bfloat16 --> BF16, shape = {256, 3072}
INFO:hf-to-gguf:blk.7.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536}
INFO:hf-to-gguf:blk.7.exp_probs_b.bias, torch.float32 --> F32, shape = {128}
INFO:hf-to-gguf:blk.7.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {1536, 128}
INFO:hf-to-gguf:blk.7.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 1536}
INFO:hf-to-gguf:blk.7.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {1536, 512}
INFO:hf-to-gguf:blk.7.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {1536, 512}
INFO:hf-to-gguf:blk.7.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536}
INFO:hf-to-gguf:blk.8.ssm_a, torch.float32 --> F32, shape = {1, 16}
INFO:hf-to-gguf:blk.8.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {1536, 16}
INFO:hf-to-gguf:blk.8.ssm_dt.bias, torch.float32 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.8.ssm_f_a.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.8.ssm_g_a.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.8.ssm_conv1d_k.weight, torch.bfloat16 --> F32, shape = {4, 1, 2048, 1}
INFO:hf-to-gguf:blk.8.attn_k.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.8.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.8.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 1536}
INFO:hf-to-gguf:blk.8.ssm_conv1d_q.weight, torch.bfloat16 --> F32, shape = {4, 1, 2048, 1}
INFO:hf-to-gguf:blk.8.attn_q.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.8.ssm_conv1d_v.weight, torch.bfloat16 --> F32, shape = {4, 1, 2048, 1}
INFO:hf-to-gguf:blk.8.attn_v.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.8.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536}
INFO:hf-to-gguf:blk.8.exp_probs_b.bias, torch.float32 --> F32, shape = {128}
INFO:hf-to-gguf:blk.8.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {1536, 128}
INFO:hf-to-gguf:blk.8.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 1536}
INFO:hf-to-gguf:blk.8.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {1536, 512}
INFO:hf-to-gguf:blk.8.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {1536, 512}
INFO:hf-to-gguf:blk.8.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536}
INFO:hf-to-gguf:blk.9.ssm_a, torch.float32 --> F32, shape = {1, 16}
INFO:hf-to-gguf:blk.9.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {1536, 16}
INFO:hf-to-gguf:blk.9.ssm_dt.bias, torch.float32 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.9.ssm_f_a.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.9.ssm_g_a.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.9.ssm_conv1d_k.weight, torch.bfloat16 --> F32, shape = {4, 1, 2048, 1}
INFO:hf-to-gguf:blk.9.attn_k.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.9.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.9.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 1536}
INFO:hf-to-gguf:blk.9.ssm_conv1d_q.weight, torch.bfloat16 --> F32, shape = {4, 1, 2048, 1}
INFO:hf-to-gguf:blk.9.attn_q.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.9.ssm_conv1d_v.weight, torch.bfloat16 --> F32, shape = {4, 1, 2048, 1}
INFO:hf-to-gguf:blk.9.attn_v.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.9.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536}
INFO:hf-to-gguf:blk.9.exp_probs_b.bias, torch.float32 --> F32, shape = {128}
INFO:hf-to-gguf:blk.9.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {1536, 128}
INFO:hf-to-gguf:blk.9.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 1536}
INFO:hf-to-gguf:blk.9.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {1536, 512}
INFO:hf-to-gguf:blk.9.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {1536, 512}
INFO:hf-to-gguf:blk.9.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536}
INFO:hf-to-gguf:blk.10.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 1536, 128}
INFO:hf-to-gguf:blk.10.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {1536, 512, 128}
INFO:hf-to-gguf:blk.10.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1536, 512, 128}
INFO:hf-to-gguf:blk.11.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 1536, 128}
INFO:hf-to-gguf:blk.11.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {1536, 512, 128}
INFO:hf-to-gguf:blk.11.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1536, 512, 128}
INFO:hf-to-gguf:blk.6.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 1536, 128}
INFO:hf-to-gguf:blk.6.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {1536, 512, 128}
INFO:hf-to-gguf:blk.6.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1536, 512, 128}
INFO:hf-to-gguf:blk.7.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 1536, 128}
INFO:hf-to-gguf:blk.7.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {1536, 512, 128}
INFO:hf-to-gguf:blk.7.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1536, 512, 128}
INFO:hf-to-gguf:blk.8.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 1536, 128}
INFO:hf-to-gguf:blk.8.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {1536, 512, 128}
INFO:hf-to-gguf:blk.8.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1536, 512, 128}
INFO:hf-to-gguf:blk.9.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 1536, 128}
INFO:hf-to-gguf:blk.9.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {1536, 512, 128}
INFO:hf-to-gguf:blk.9.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1536, 512, 128}
INFO:hf-to-gguf:blk.12.ssm_a, torch.float32 --> F32, shape = {1, 16}
INFO:hf-to-gguf:blk.12.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {1536, 16}
INFO:hf-to-gguf:blk.12.ssm_dt.bias, torch.float32 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.12.ssm_f_a.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.12.ssm_g_a.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.12.ssm_conv1d_k.weight, torch.bfloat16 --> F32, shape = {4, 1, 2048, 1}
INFO:hf-to-gguf:blk.12.attn_k.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.12.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.12.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 1536}
INFO:hf-to-gguf:blk.12.ssm_conv1d_q.weight, torch.bfloat16 --> F32, shape = {4, 1, 2048, 1}
INFO:hf-to-gguf:blk.12.attn_q.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.12.ssm_conv1d_v.weight, torch.bfloat16 --> F32, shape = {4, 1, 2048, 1}
INFO:hf-to-gguf:blk.12.attn_v.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.12.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536}
INFO:hf-to-gguf:blk.12.exp_probs_b.bias, torch.float32 --> F32, shape = {128}
INFO:hf-to-gguf:blk.12.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {1536, 128}
INFO:hf-to-gguf:blk.12.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 1536}
INFO:hf-to-gguf:blk.12.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {1536, 512}
INFO:hf-to-gguf:blk.12.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {1536, 512}
INFO:hf-to-gguf:blk.12.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536}
INFO:hf-to-gguf:blk.13.ssm_a, torch.float32 --> F32, shape = {1, 16}
INFO:hf-to-gguf:blk.13.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {1536, 16}
INFO:hf-to-gguf:blk.13.ssm_dt.bias, torch.float32 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.13.ssm_f_a.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.13.ssm_g_a.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.13.ssm_conv1d_k.weight, torch.bfloat16 --> F32, shape = {4, 1, 2048, 1}
INFO:hf-to-gguf:blk.13.attn_k.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.13.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.13.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 1536}
INFO:hf-to-gguf:blk.13.ssm_conv1d_q.weight, torch.bfloat16 --> F32, shape = {4, 1, 2048, 1}
INFO:hf-to-gguf:blk.13.attn_q.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.13.ssm_conv1d_v.weight, torch.bfloat16 --> F32, shape = {4, 1, 2048, 1}
INFO:hf-to-gguf:blk.13.attn_v.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.13.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536}
INFO:hf-to-gguf:blk.13.exp_probs_b.bias, torch.float32 --> F32, shape = {128}
INFO:hf-to-gguf:blk.13.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {1536, 128}
INFO:hf-to-gguf:blk.13.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 1536}
INFO:hf-to-gguf:blk.13.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {1536, 512}
INFO:hf-to-gguf:blk.13.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {1536, 512}
INFO:hf-to-gguf:blk.13.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536}
INFO:hf-to-gguf:blk.14.ssm_a, torch.float32 --> F32, shape = {1, 16}
INFO:hf-to-gguf:blk.14.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {1536, 16}
INFO:hf-to-gguf:blk.14.ssm_dt.bias, torch.float32 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.14.ssm_f_a.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.14.ssm_g_a.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.14.ssm_conv1d_k.weight, torch.bfloat16 --> F32, shape = {4, 1, 2048, 1}
INFO:hf-to-gguf:blk.14.attn_k.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.14.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.14.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 1536}
INFO:hf-to-gguf:blk.14.ssm_conv1d_q.weight, torch.bfloat16 --> F32, shape = {4, 1, 2048, 1}
INFO:hf-to-gguf:blk.14.attn_q.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.14.ssm_conv1d_v.weight, torch.bfloat16 --> F32, shape = {4, 1, 2048, 1}
INFO:hf-to-gguf:blk.14.attn_v.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.14.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536}
INFO:hf-to-gguf:blk.14.exp_probs_b.bias, torch.float32 --> F32, shape = {128}
INFO:hf-to-gguf:blk.14.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {1536, 128}
INFO:hf-to-gguf:blk.14.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 1536}
INFO:hf-to-gguf:blk.14.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {1536, 512}
INFO:hf-to-gguf:blk.14.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {1536, 512}
INFO:hf-to-gguf:blk.14.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536}
INFO:hf-to-gguf:blk.15.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 1536}
INFO:hf-to-gguf:blk.15.attn_gate.weight, torch.bfloat16 --> BF16, shape = {1536, 16}
INFO:hf-to-gguf:blk.15.attn_kv_a_norm.weight, torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.15.attn_kv_a_mqa.weight, torch.bfloat16 --> BF16, shape = {1536, 576}
INFO:hf-to-gguf:blk.15.attn_k_b.weight, torch.bfloat16 --> BF16, shape = {128, 512, 16}
INFO:hf-to-gguf:blk.15.attn_v_b.weight, torch.bfloat16 --> BF16, shape = {512, 128, 16}
INFO:hf-to-gguf:blk.15.attn_q_a_norm.weight, torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.15.attn_q_a.weight, torch.bfloat16 --> BF16, shape = {1536, 256}
INFO:hf-to-gguf:blk.15.attn_q_b.weight, torch.bfloat16 --> BF16, shape = {256, 3072}
INFO:hf-to-gguf:blk.15.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536}
INFO:hf-to-gguf:blk.15.exp_probs_b.bias, torch.float32 --> F32, shape = {128}
INFO:hf-to-gguf:blk.15.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {1536, 128}
INFO:hf-to-gguf:blk.15.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 1536}
INFO:hf-to-gguf:blk.15.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {1536, 512}
INFO:hf-to-gguf:blk.15.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {1536, 512}
INFO:hf-to-gguf:blk.15.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536}
INFO:hf-to-gguf:blk.16.ssm_a, torch.float32 --> F32, shape = {1, 16}
INFO:hf-to-gguf:blk.16.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {1536, 16}
INFO:hf-to-gguf:blk.16.ssm_dt.bias, torch.float32 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.16.ssm_f_a.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.16.ssm_g_a.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.16.ssm_conv1d_k.weight, torch.bfloat16 --> F32, shape = {4, 1, 2048, 1}
INFO:hf-to-gguf:blk.16.attn_k.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.16.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.16.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 1536}
INFO:hf-to-gguf:blk.16.ssm_conv1d_q.weight, torch.bfloat16 --> F32, shape = {4, 1, 2048, 1}
INFO:hf-to-gguf:blk.16.attn_q.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.16.ssm_conv1d_v.weight, torch.bfloat16 --> F32, shape = {4, 1, 2048, 1}
INFO:hf-to-gguf:blk.16.attn_v.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.16.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536}
INFO:hf-to-gguf:blk.16.exp_probs_b.bias, torch.float32 --> F32, shape = {128}
INFO:hf-to-gguf:blk.16.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {1536, 128}
INFO:hf-to-gguf:blk.16.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 1536}
INFO:hf-to-gguf:blk.16.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {1536, 512}
INFO:hf-to-gguf:blk.16.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {1536, 512}
INFO:hf-to-gguf:blk.16.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536}
INFO:hf-to-gguf:blk.17.ssm_a, torch.float32 --> F32, shape = {1, 16}
INFO:hf-to-gguf:blk.17.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {1536, 16}
INFO:hf-to-gguf:blk.17.ssm_dt.bias, torch.float32 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.17.ssm_f_a.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.17.ssm_g_a.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.17.ssm_conv1d_k.weight, torch.bfloat16 --> F32, shape = {4, 1, 2048, 1}
INFO:hf-to-gguf:blk.17.attn_k.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.17.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.17.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 1536}
INFO:hf-to-gguf:blk.17.ssm_conv1d_q.weight, torch.bfloat16 --> F32, shape = {4, 1, 2048, 1}
INFO:hf-to-gguf:blk.17.attn_q.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.17.ssm_conv1d_v.weight, torch.bfloat16 --> F32, shape = {4, 1, 2048, 1}
INFO:hf-to-gguf:blk.17.attn_v.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.17.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536}
INFO:hf-to-gguf:blk.17.exp_probs_b.bias, torch.float32 --> F32, shape = {128}
INFO:hf-to-gguf:blk.17.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {1536, 128}
INFO:hf-to-gguf:blk.17.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 1536}
INFO:hf-to-gguf:blk.17.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {1536, 512}
INFO:hf-to-gguf:blk.17.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {1536, 512}
INFO:hf-to-gguf:blk.17.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536}
INFO:hf-to-gguf:blk.12.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 1536, 128}
INFO:hf-to-gguf:blk.12.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {1536, 512, 128}
INFO:hf-to-gguf:blk.12.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1536, 512, 128}
INFO:hf-to-gguf:blk.13.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 1536, 128}
INFO:hf-to-gguf:blk.13.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {1536, 512, 128}
INFO:hf-to-gguf:blk.13.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1536, 512, 128}
INFO:hf-to-gguf:blk.14.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 1536, 128}
INFO:hf-to-gguf:blk.14.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {1536, 512, 128}
INFO:hf-to-gguf:blk.14.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1536, 512, 128}
INFO:hf-to-gguf:blk.15.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 1536, 128}
INFO:hf-to-gguf:blk.15.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {1536, 512, 128}
INFO:hf-to-gguf:blk.15.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1536, 512, 128}
INFO:hf-to-gguf:blk.16.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 1536, 128}
INFO:hf-to-gguf:blk.16.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {1536, 512, 128}
INFO:hf-to-gguf:blk.16.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1536, 512, 128}
INFO:hf-to-gguf:blk.17.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 1536, 128}
INFO:hf-to-gguf:blk.17.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {1536, 512, 128}
INFO:hf-to-gguf:blk.17.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1536, 512, 128}
INFO:hf-to-gguf:output.weight, torch.bfloat16 --> BF16, shape = {1536, 157184}
INFO:hf-to-gguf:blk.18.ssm_a, torch.float32 --> F32, shape = {1, 16}
INFO:hf-to-gguf:blk.18.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {1536, 16}
INFO:hf-to-gguf:blk.18.ssm_dt.bias, torch.float32 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.18.ssm_f_a.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.18.ssm_g_a.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.18.ssm_conv1d_k.weight, torch.bfloat16 --> F32, shape = {4, 1, 2048, 1}
INFO:hf-to-gguf:blk.18.attn_k.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.18.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.18.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 1536}
INFO:hf-to-gguf:blk.18.ssm_conv1d_q.weight, torch.bfloat16 --> F32, shape = {4, 1, 2048, 1}
INFO:hf-to-gguf:blk.18.attn_q.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.18.ssm_conv1d_v.weight, torch.bfloat16 --> F32, shape = {4, 1, 2048, 1}
INFO:hf-to-gguf:blk.18.attn_v.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.18.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536}
INFO:hf-to-gguf:blk.18.exp_probs_b.bias, torch.float32 --> F32, shape = {128}
INFO:hf-to-gguf:blk.18.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {1536, 128}
INFO:hf-to-gguf:blk.18.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 1536}
INFO:hf-to-gguf:blk.18.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {1536, 512}
INFO:hf-to-gguf:blk.18.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {1536, 512}
INFO:hf-to-gguf:blk.18.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536}
INFO:hf-to-gguf:blk.19.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 1536}
INFO:hf-to-gguf:blk.19.attn_gate.weight, torch.bfloat16 --> BF16, shape = {1536, 16}
INFO:hf-to-gguf:blk.19.attn_kv_a_norm.weight, torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.19.attn_kv_a_mqa.weight, torch.bfloat16 --> BF16, shape = {1536, 576}
INFO:hf-to-gguf:blk.19.attn_k_b.weight, torch.bfloat16 --> BF16, shape = {128, 512, 16}
INFO:hf-to-gguf:blk.19.attn_v_b.weight, torch.bfloat16 --> BF16, shape = {512, 128, 16}
INFO:hf-to-gguf:blk.19.attn_q_a_norm.weight, torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.19.attn_q_a.weight, torch.bfloat16 --> BF16, shape = {1536, 256}
INFO:hf-to-gguf:blk.19.attn_q_b.weight, torch.bfloat16 --> BF16, shape = {256, 3072}
INFO:hf-to-gguf:blk.19.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536}
INFO:hf-to-gguf:blk.19.exp_probs_b.bias, torch.float32 --> F32, shape = {128}
INFO:hf-to-gguf:blk.19.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {1536, 128}
INFO:hf-to-gguf:blk.19.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 1536}
INFO:hf-to-gguf:blk.19.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {1536, 512}
INFO:hf-to-gguf:blk.19.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {1536, 512}
INFO:hf-to-gguf:blk.19.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536}
INFO:hf-to-gguf:blk.20.ssm_a, torch.float32 --> F32, shape = {1, 16}
INFO:hf-to-gguf:blk.20.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {1536, 16}
INFO:hf-to-gguf:blk.20.ssm_dt.bias, torch.float32 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.20.ssm_f_a.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.20.ssm_g_a.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.20.ssm_conv1d_k.weight, torch.bfloat16 --> F32, shape = {4, 1, 2048, 1}
INFO:hf-to-gguf:blk.20.attn_k.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.20.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.20.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 1536}
INFO:hf-to-gguf:blk.20.ssm_conv1d_q.weight, torch.bfloat16 --> F32, shape = {4, 1, 2048, 1}
INFO:hf-to-gguf:blk.20.attn_q.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.20.ssm_conv1d_v.weight, torch.bfloat16 --> F32, shape = {4, 1, 2048, 1}
INFO:hf-to-gguf:blk.20.attn_v.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.20.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536}
INFO:hf-to-gguf:blk.20.exp_probs_b.bias, torch.float32 --> F32, shape = {128}
INFO:hf-to-gguf:blk.20.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {1536, 128}
INFO:hf-to-gguf:blk.20.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 1536}
INFO:hf-to-gguf:blk.20.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {1536, 512}
INFO:hf-to-gguf:blk.20.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {1536, 512}
INFO:hf-to-gguf:blk.20.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536}
INFO:hf-to-gguf:blk.21.ssm_a, torch.float32 --> F32, shape = {1, 16}
INFO:hf-to-gguf:blk.21.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {1536, 16}
INFO:hf-to-gguf:blk.21.ssm_dt.bias, torch.float32 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.21.ssm_f_a.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.21.ssm_g_a.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.21.ssm_conv1d_k.weight, torch.bfloat16 --> F32, shape = {4, 1, 2048, 1}
INFO:hf-to-gguf:blk.21.attn_k.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.21.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.21.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 1536}
INFO:hf-to-gguf:blk.21.ssm_conv1d_q.weight, torch.bfloat16 --> F32, shape = {4, 1, 2048, 1}
INFO:hf-to-gguf:blk.21.attn_q.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.21.ssm_conv1d_v.weight, torch.bfloat16 --> F32, shape = {4, 1, 2048, 1}
INFO:hf-to-gguf:blk.21.attn_v.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.21.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536}
INFO:hf-to-gguf:blk.21.exp_probs_b.bias, torch.float32 --> F32, shape = {128}
INFO:hf-to-gguf:blk.21.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {1536, 128}
INFO:hf-to-gguf:blk.21.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 1536}
INFO:hf-to-gguf:blk.21.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {1536, 512}
INFO:hf-to-gguf:blk.21.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {1536, 512}
INFO:hf-to-gguf:blk.21.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536}
INFO:hf-to-gguf:blk.22.ssm_a, torch.float32 --> F32, shape = {1, 16}
INFO:hf-to-gguf:blk.22.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {1536, 16}
INFO:hf-to-gguf:blk.22.ssm_dt.bias, torch.float32 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.22.ssm_f_a.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.22.ssm_g_a.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.22.ssm_conv1d_k.weight, torch.bfloat16 --> F32, shape = {4, 1, 2048, 1}
INFO:hf-to-gguf:blk.22.attn_k.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.22.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.22.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 1536}
INFO:hf-to-gguf:blk.22.ssm_conv1d_q.weight, torch.bfloat16 --> F32, shape = {4, 1, 2048, 1}
INFO:hf-to-gguf:blk.22.attn_q.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.22.ssm_conv1d_v.weight, torch.bfloat16 --> F32, shape = {4, 1, 2048, 1}
INFO:hf-to-gguf:blk.22.attn_v.weight, torch.bfloat16 --> BF16, shape = {1536, 2048}
INFO:hf-to-gguf:blk.22.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536}
INFO:hf-to-gguf:blk.22.exp_probs_b.bias, torch.float32 --> F32, shape = {128}
INFO:hf-to-gguf:blk.22.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {1536, 128}
INFO:hf-to-gguf:blk.22.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 1536}
INFO:hf-to-gguf:blk.22.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {1536, 512}
INFO:hf-to-gguf:blk.22.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {1536, 512}
INFO:hf-to-gguf:blk.22.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536}
INFO:hf-to-gguf:blk.23.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 1536}
INFO:hf-to-gguf:blk.23.attn_gate.weight, torch.bfloat16 --> BF16, shape = {1536, 16}
INFO:hf-to-gguf:blk.23.attn_kv_a_norm.weight, torch.bfloat16 --> F32, shape = {512}
INFO:hf-to-gguf:blk.23.attn_kv_a_mqa.weight, torch.bfloat16 --> BF16, shape = {1536, 576}
INFO:hf-to-gguf:blk.23.attn_k_b.weight, torch.bfloat16 --> BF16, shape = {128, 512, 16}
INFO:hf-to-gguf:blk.23.attn_v_b.weight, torch.bfloat16 --> BF16, shape = {512, 128, 16}
INFO:hf-to-gguf:blk.23.attn_q_a_norm.weight, torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.23.attn_q_a.weight, torch.bfloat16 --> BF16, shape = {1536, 256}
INFO:hf-to-gguf:blk.23.attn_q_b.weight, torch.bfloat16 --> BF16, shape = {256, 3072}
INFO:hf-to-gguf:blk.23.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536}
INFO:hf-to-gguf:blk.23.exp_probs_b.bias, torch.float32 --> F32, shape = {128}
INFO:hf-to-gguf:blk.23.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {1536, 128}
INFO:hf-to-gguf:blk.23.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 1536}
INFO:hf-to-gguf:blk.23.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {1536, 512}
INFO:hf-to-gguf:blk.23.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {1536, 512}
INFO:hf-to-gguf:blk.23.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536}
INFO:hf-to-gguf:output_norm.weight, torch.bfloat16 --> F32, shape = {1536}
INFO:hf-to-gguf:blk.18.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 1536, 128}
INFO:hf-to-gguf:blk.18.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {1536, 512, 128}
INFO:hf-to-gguf:blk.18.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1536, 512, 128}
INFO:hf-to-gguf:blk.19.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 1536, 128}
INFO:hf-to-gguf:blk.19.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {1536, 512, 128}
INFO:hf-to-gguf:blk.19.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1536, 512, 128}
INFO:hf-to-gguf:blk.20.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 1536, 128}
INFO:hf-to-gguf:blk.20.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {1536, 512, 128}
INFO:hf-to-gguf:blk.20.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1536, 512, 128}
INFO:hf-to-gguf:blk.21.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 1536, 128}
INFO:hf-to-gguf:blk.21.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {1536, 512, 128}
INFO:hf-to-gguf:blk.21.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1536, 512, 128}
INFO:hf-to-gguf:blk.22.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 1536, 128}
INFO:hf-to-gguf:blk.22.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {1536, 512, 128}
INFO:hf-to-gguf:blk.22.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1536, 512, 128}
INFO:hf-to-gguf:blk.23.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 1536, 128}
INFO:hf-to-gguf:blk.23.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {1536, 512, 128}
INFO:hf-to-gguf:blk.23.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {1536, 512, 128}
INFO:hf-to-gguf:Set meta model
INFO:hf-to-gguf:Set model parameters
INFO:hf-to-gguf:gguf: context length = 131072
INFO:hf-to-gguf:gguf: embedding length = 1536
INFO:hf-to-gguf:gguf: feed forward length = 4608
INFO:hf-to-gguf:gguf: head count = 16
INFO:hf-to-gguf:gguf: key-value head count = 1
INFO:hf-to-gguf:gguf: rope theta = 6000000
INFO:hf-to-gguf:gguf: rms norm epsilon = 1e-06
INFO:hf-to-gguf:gguf: expert count = 128
INFO:hf-to-gguf:gguf: experts used count = 8
INFO:hf-to-gguf:gguf: expert groups count = 8
INFO:hf-to-gguf:gguf: expert groups used count = 4
INFO:hf-to-gguf:gguf: expert score gating function = sigmoid
INFO:hf-to-gguf:gguf: file type = 32
WARNING:gguf.gguf_writer:Duplicated key name 'bailingmoe3.attention.head_count_kv', overwriting it with new value [0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 1] of type ARRAY
WARNING:gguf.gguf_writer:Duplicated key name 'bailingmoe3.attention.key_length', overwriting it with new value 576 of type UINT32
INFO:hf-to-gguf:Set model quantization version
INFO:hf-to-gguf:Set model tokenizer
INFO:gguf.vocab:Adding 156635 merge(s).
INFO:gguf.vocab:Setting special token type bos to 156891
INFO:gguf.vocab:Setting special token type eos to 156895
INFO:gguf.vocab:Setting special token type pad to 156892
WARNING:gguf.vocab:No handler for special token type cls with id 156893 - skipping
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 {#- Bailing V3 chat template -#}
{#- Supports: thinking option, tool calling -#}
{#- ==================== thinking option normalization ==================== -#}
{%- if enable_thinking is defined %}
{%- if enable_thinking %}
{%- set thinking_option = 'on' %}
{%- else %}
{%- set thinking_option = 'off' %}
{%- endif %}
{%- elif thinking_option is not defined %}
{%- set thinking_option = 'on' %}
{%- endif %}
{#- ==================== preserved thinking ==================== -#}
{% set preserved_thinking = true %}
{#- ==================== system message ==================== -#}
{{- '<role>SYSTEM</role>' }}
{%- if tools %}
{%- if messages[0].role == 'system' %}
{{- messages[0].content + '\n' }}
{%- endif %}
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
{%- for tool in tools %}
{{- "\n" }}
{{- tool | tojson }}
{%- endfor %}
{{- "\n</tools>\n\nIf none of the functions can be used, point it out. If the given question lacks the parameters required by the function, also point it out.\nIf you need to use a function, for each function call, output the function name and arguments within the following XML format:\n<tool_call>{function-name}\n<arg_key>{arg-key-1}</arg_key>\n<arg_value>{arg-value-1}</arg_value>\n<arg_key>{arg-key-2}</arg_key>\n<arg_value>{arg-value-2}</arg_value>\n...\n</tool_call>\n" }}
{%- if messages[0].role == 'system' and messages[0].content is string and ('detailed thinking on' in messages[0].content or 'detailed thinking off' in messages[0].content) %}
{{- '<|role_end|>' }}
{%- else %}
{{- 'detailed thinking ' + thinking_option + '<|role_end|>' }}
{%- endif %}
{%- else %}
{%- if messages[0].role == 'system' %}
{%- if 'detailed thinking on' in messages[0].content or 'detailed thinking off' in messages[0].content %}
{{- messages[0].content + '<|role_end|>' }}
{%- else %}
{{- messages[0].content + '\n' }}
{{- 'detailed thinking ' + thinking_option + '<|role_end|>' }}
{%- endif %}
{% else %}
{{- 'detailed thinking ' + thinking_option + '<|role_end|>' }}
{%- endif %}
{%- endif %}
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
{%- for message in messages[::-1] %}
{%- set index = (messages|length - 1) - loop.index0 %}
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
{%- set ns.multi_step_tool = false %}
{%- set ns.last_query_index = index %}
{%- endif %}
{%- endfor %}
{%- for message in messages %}
{%- if message.content is string %}
{%- set content = message.content %}
{%- else %}
{%- set content = '' %}
{%- endif %}
{%- if message.role == "user" %}
{{- '<role>HUMAN</role>' + message.content + '<|role_end|>' }}
{%- elif message.role == "system" and not loop.first %}
{{- '<role>SYSTEM</role>' + message.content + '<|role_end|>' }}
{%- elif message.role == "assistant" %}
{%- set reasoning_content = '' %}
{%- if message.reasoning_content is string and message.reasoning_content != '' %}
{%- set reasoning_content = message.reasoning_content %}
{%- else %}
{%- if '</think>' in content %}
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
{%- endif %}
{%- endif %}
{%- if preserved_thinking or loop.index0 > ns.last_query_index %}
{%- if reasoning_content != '' %}
{{- '<role>ASSISTANT</role>' + '\n<think>' + reasoning_content.strip('\n') + '</think>' + content.lstrip('\n') }}
{%- else %}
{{- '<role>ASSISTANT</role>\n<think></think>' + content }}
{%- endif %}
{%- else %}
{{- '<role>ASSISTANT</role>\n<think></think>' + content }}
{%- endif %}
{%- if message.tool_calls %}
{%- for tool_call in message.tool_calls %}
{%- if (loop.first and content) or (not loop.first) %}
{{- '\n' }}
{%- endif %}
{%- set tc = tool_call %}
{%- if tool_call.function %}
{%- set tc = tool_call.function %}
{%- endif %}
{{- '<tool_call>' + tc.name }}
{% set _args = tc.arguments %}
{%- for k, v in _args.items() %}
{{- '<arg_key>' + k + '</arg_key>' }}
{{- '\n<arg_value>' }}
{%- if v is string %}
{{- v }}
{%- else %}
{{- v | tojson(ensure_ascii=False) }}
{%- endif %}
{{- '</arg_value>' }}
{%- endfor %}
{{- '\n</tool_call>' }}
{%- endfor %}
{%- endif %}
{{- '<|role_end|>' }}
{%- elif message.role == "tool" %}
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
{{- '<role>OBSERVATION</role>' }}
{%- endif %}
{{- '\n<tool_response>\n' }}
{{- content }}
{{- '\n</tool_response>' }}
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
{{- '<|role_end|>' }}
{%- endif %}
{%- endif %}
{%- endfor %}
{#- ==================== generation prompt ==================== -#}
{%- if add_generation_prompt %}
{{- '<role>ASSISTANT</role>' }}
{%- if thinking_option == 'on' %}
{{- '\n<think>' }}
{%- elif thinking_option == 'off' %}
{{- '\n<think></think>' }}
{%- endif %}
{%- endif %}
INFO:gguf.vocab:Setting normalizer_nfc to True
INFO:gguf.vocab:Setting clean_spaces to False
INFO:gguf.gguf_writer:Writing the following files:
INFO:gguf.gguf_writer:/tmp/Ling-3.0-tiny-hfconv.gguf: n_tensors = 526, total_size = 15.8G
Writing: 0%| | 0.00/15.8G [00:00<?, ?byte/s] Writing: 0%| | 25.3M/15.8G [00:00<01:05, 242Mbyte/s] Writing: 0%| | 66.2M/15.8G [00:00<00:53, 297Mbyte/s] Writing: 1%| | 99.3M/15.8G [00:00<00:51, 307Mbyte/s] Writing: 1%| | 130M/15.8G [00:00<00:53, 291Mbyte/s] Writing: 1%| | 162M/15.8G [00:00<00:52, 296Mbyte/s] Writing: 1%| | 194M/15.8G [00:00<00:59, 263Mbyte/s] Writing: 1%|▏ | 225M/15.8G [00:00<00:56, 276Mbyte/s] Writing: 2%|▏ | 256M/15.8G [00:00<00:56, 276Mbyte/s] Writing: 5%|▍ | 757M/15.8G [00:02<00:47, 316Mbyte/s] Writing: 6%|β–Œ | 958M/15.8G [00:03<00:54, 270Mbyte/s] Writing: 7%|β–‹ | 1.16G/15.8G [00:04<00:55, 264Mbyte/s] Writing: 9%|β–Š | 1.36G/15.8G [00:04<00:54, 264Mbyte/s] Writing: 10%|β–‰ | 1.56G/15.8G [00:05<00:56, 252Mbyte/s] Writing: 11%|β–ˆ | 1.76G/15.8G [00:06<00:54, 257Mbyte/s] Writing: 12%|β–ˆβ– | 1.97G/15.8G [00:07<00:57, 241Mbyte/s] Writing: 14%|β–ˆβ–Ž | 2.17G/15.8G [00:08<00:56, 240Mbyte/s] Writing: 15%|β–ˆβ– | 2.37G/15.8G [00:09<00:53, 250Mbyte/s] Writing: 16%|β–ˆβ–‹ | 2.57G/15.8G [00:09<00:51, 258Mbyte/s] Writing: 18%|β–ˆβ–Š | 2.77G/15.8G [00:10<00:51, 252Mbyte/s] Writing: 19%|β–ˆβ–‰ | 2.97G/15.8G [00:11<00:49, 260Mbyte/s] Writing: 20%|β–ˆβ–ˆ | 3.17G/15.8G [00:12<00:47, 268Mbyte/s] Writing: 21%|β–ˆβ–ˆβ– | 3.37G/15.8G [00:12<00:47, 259Mbyte/s] Writing: 23%|β–ˆβ–ˆβ–Ž | 3.58G/15.8G [00:13<00:46, 266Mbyte/s] Writing: 24%|β–ˆβ–ˆβ– | 3.78G/15.8G [00:14<00:44, 271Mbyte/s] Writing: 24%|β–ˆβ–ˆβ– | 3.81G/15.8G [00:14<00:44, 269Mbyte/s] Writing: 24%|β–ˆβ–ˆβ– | 3.84G/15.8G [00:14<00:45, 264Mbyte/s] Writing: 24%|β–ˆβ–ˆβ– | 3.87G/15.8G [00:14<00:45, 265Mbyte/s] Writing: 25%|β–ˆβ–ˆβ– | 3.89G/15.8G [00:14<00:45, 263Mbyte/s] Writing: 25%|β–ˆβ–ˆβ– | 3.92G/15.8G [00:14<00:45, 263Mbyte/s] Writing: 25%|β–ˆβ–ˆβ–Œ | 3.95G/15.8G [00:15<00:44, 267Mbyte/s] Writing: 25%|β–ˆβ–ˆβ–Œ | 3.99G/15.8G [00:15<00:42, 275Mbyte/s] Writing: 27%|β–ˆβ–ˆβ–‹ | 4.19G/15.8G [00:16<00:45, 254Mbyte/s] Writing: 28%|β–ˆβ–ˆβ–Š | 4.39G/15.8G [00:16<00:42, 267Mbyte/s] Writing: 29%|β–ˆβ–ˆβ–‰ | 4.60G/15.8G [00:17<00:41, 272Mbyte/s] Writing: 30%|β–ˆβ–ˆβ–ˆ | 4.80G/15.8G [00:18<00:42, 262Mbyte/s] Writing: 32%|β–ˆβ–ˆβ–ˆβ– | 5.00G/15.8G [00:19<00:42, 253Mbyte/s] Writing: 33%|β–ˆβ–ˆβ–ˆβ–Ž | 5.20G/15.8G [00:19<00:41, 256Mbyte/s] Writing: 34%|β–ˆβ–ˆβ–ˆβ– | 5.40G/15.8G [00:20<00:42, 245Mbyte/s] Writing: 35%|β–ˆβ–ˆβ–ˆβ–Œ | 5.60G/15.8G [00:21<00:41, 248Mbyte/s] Writing: 37%|β–ˆβ–ˆβ–ˆβ–‹ | 5.80G/15.8G [00:22<00:39, 253Mbyte/s] Writing: 38%|β–ˆβ–ˆβ–ˆβ–Š | 6.00G/15.8G [00:23<00:40, 241Mbyte/s] Writing: 39%|β–ˆβ–ˆβ–ˆβ–‰ | 6.21G/15.8G [00:24<00:39, 244Mbyte/s] Writing: 41%|β–ˆβ–ˆβ–ˆβ–ˆ | 6.41G/15.8G [00:24<00:38, 246Mbyte/s] Writing: 42%|β–ˆβ–ˆβ–ˆβ–ˆβ– | 6.61G/15.8G [00:25<00:38, 237Mbyte/s] Writing: 43%|β–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 6.81G/15.8G [00:26<00:36, 244Mbyte/s] Writing: 44%|β–ˆβ–ˆβ–ˆβ–ˆβ– | 7.01G/15.8G [00:27<00:35, 250Mbyte/s] Writing: 46%|β–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 7.21G/15.8G [00:28<00:35, 245Mbyte/s] Writing: 47%|β–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 7.41G/15.8G [00:28<00:33, 251Mbyte/s] Writing: 48%|β–ˆβ–ˆβ–ˆβ–ˆβ–Š | 7.61G/15.8G [00:29<00:32, 252Mbyte/s] Writing: 48%|β–ˆβ–ˆβ–ˆβ–ˆβ–Š | 7.65G/15.8G [00:29<00:32, 252Mbyte/s] Writing: 49%|β–ˆβ–ˆβ–ˆβ–ˆβ–Š | 7.68G/15.8G [00:29<00:32, 251Mbyte/s] Writing: 49%|β–ˆβ–ˆβ–ˆβ–ˆβ–‰ | 7.71G/15.8G [00:30<00:32, 250Mbyte/s] Writing: 49%|β–ˆβ–ˆβ–ˆβ–ˆβ–‰ | 7.74G/15.8G [00:30<00:31, 253Mbyte/s] Writing: 49%|β–ˆβ–ˆβ–ˆβ–ˆβ–‰ | 7.77G/15.8G [00:30<00:32, 245Mbyte/s] Writing: 49%|β–ˆβ–ˆβ–ˆβ–ˆβ–‰ | 7.80G/15.8G [00:30<00:31, 254Mbyte/s] Writing: 50%|β–ˆβ–ˆβ–ˆβ–ˆβ–‰ | 7.83G/15.8G [00:30<00:30, 259Mbyte/s] Writing: 51%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 8.05G/15.8G [00:31<00:33, 230Mbyte/s] Writing: 52%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 8.25G/15.8G [00:32<00:31, 238Mbyte/s] Writing: 54%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 8.46G/15.8G [00:33<00:29, 245Mbyte/s] Writing: 55%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 8.66G/15.8G [00:34<00:30, 237Mbyte/s] Writing: 56%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 8.86G/15.8G [00:34<00:28, 241Mbyte/s] Writing: 57%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 9.06G/15.8G [00:35<00:27, 247Mbyte/s] Writing: 59%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š | 9.26G/15.8G [00:36<00:27, 242Mbyte/s] Writing: 60%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‰ | 9.46G/15.8G [00:37<00:25, 248Mbyte/s] Writing: 61%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 9.66G/15.8G [00:38<00:24, 254Mbyte/s] Writing: 62%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 9.87G/15.8G [00:39<00:26, 223Mbyte/s] Writing: 64%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 10.1G/15.8G [00:40<00:27, 212Mbyte/s] Writing: 65%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 10.3G/15.8G [00:41<00:26, 207Mbyte/s] Writing: 66%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 10.5G/15.8G [00:42<00:27, 197Mbyte/s] Writing: 68%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š | 10.7G/15.8G [00:43<00:24, 212Mbyte/s] Writing: 69%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‰ | 10.9G/15.8G [00:44<00:22, 220Mbyte/s] Writing: 70%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 11.1G/15.8G [00:46<00:28, 163Mbyte/s] Writing: 71%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 11.3G/15.8G [00:46<00:24, 183Mbyte/s] Writing: 73%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 11.5G/15.8G [00:49<00:31, 138Mbyte/s] Writing: 76%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 12.0G/15.8G [00:51<00:24, 159Mbyte/s] Writing: 76%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 12.0G/15.8G [00:51<00:23, 159Mbyte/s] Writing: 76%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 12.0G/15.8G [00:51<00:23, 164Mbyte/s] Writing: 76%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 12.0G/15.8G [00:52<00:22, 167Mbyte/s] Writing: 76%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 12.1G/15.8G [00:52<00:21, 175Mbyte/s] Writing: 77%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 12.1G/15.8G [00:52<00:20, 184Mbyte/s] Writing: 77%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 12.1G/15.8G [00:52<00:18, 194Mbyte/s] Writing: 77%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 12.2G/15.8G [00:52<00:17, 206Mbyte/s] Writing: 78%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š | 12.4G/15.8G [00:53<00:15, 228Mbyte/s] Writing: 80%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‰ | 12.6G/15.8G [00:54<00:13, 238Mbyte/s] Writing: 81%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 12.8G/15.8G [00:54<00:12, 238Mbyte/s] Writing: 82%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 13.0G/15.8G [00:55<00:12, 234Mbyte/s] Writing: 83%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 13.2G/15.8G [00:56<00:10, 240Mbyte/s] Writing: 85%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 13.4G/15.8G [00:57<00:09, 248Mbyte/s] Writing: 86%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 13.6G/15.8G [00:58<00:09, 245Mbyte/s] Writing: 87%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹ | 13.8G/15.8G [00:59<00:08, 242Mbyte/s] Writing: 89%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š | 14.0G/15.8G [01:00<00:07, 235Mbyte/s] Writing: 90%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‰ | 14.2G/15.8G [01:01<00:07, 215Mbyte/s] Writing: 91%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ | 14.4G/15.8G [01:02<00:06, 207Mbyte/s] Writing: 92%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–| 14.6G/15.8G [01:05<00:10, 114Mbyte/s] Writing: 94%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž| 14.8G/15.8G [01:06<00:07, 129Mbyte/s] Writing: 95%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–| 15.0G/15.8G [01:07<00:05, 149Mbyte/s] Writing: 96%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ| 15.2G/15.8G [01:08<00:03, 160Mbyte/s] Writing: 97%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹| 15.4G/15.8G [01:10<00:02, 162Mbyte/s] Writing: 99%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š| 15.6G/15.8G [01:11<00:01, 171Mbyte/s] Writing: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 15.8G/15.8G [01:11<00:00, 190Mbyte/s] Writing: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 15.8G/15.8G [01:11<00:00, 220Mbyte/s]
INFO:hf-to-gguf:Model successfully exported to /tmp/Ling-3.0-tiny-hfconv.gguf