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 ==================== -#} {{- 'SYSTEM' }} {%- 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 XML tags:\n" }} {%- for tool in tools %} {{- "\n" }} {{- tool | tojson }} {%- endfor %} {{- "\n\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{function-name}\n{arg-key-1}\n{arg-value-1}\n{arg-key-2}\n{arg-value-2}\n...\n\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('') and message.content.endswith('')) %} {%- 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" %} {{- 'HUMAN' + message.content + '<|role_end|>' }} {%- elif message.role == "system" and not loop.first %} {{- 'SYSTEM' + 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 '' in content %} {%- set reasoning_content = content.split('')[0].rstrip('\n').split('')[-1].lstrip('\n') %} {%- set content = content.split('')[-1].lstrip('\n') %} {%- endif %} {%- endif %} {%- if preserved_thinking or loop.index0 > ns.last_query_index %} {%- if reasoning_content != '' %} {{- 'ASSISTANT' + '\n' + reasoning_content.strip('\n') + '' + content.lstrip('\n') }} {%- else %} {{- 'ASSISTANT\n' + content }} {%- endif %} {%- else %} {{- 'ASSISTANT\n' + 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 %} {{- '' + tc.name }} {% set _args = tc.arguments %} {%- for k, v in _args.items() %} {{- '' + k + '' }} {{- '\n' }} {%- if v is string %} {{- v }} {%- else %} {{- v | tojson(ensure_ascii=False) }} {%- endif %} {{- '' }} {%- endfor %} {{- '\n' }} {%- endfor %} {%- endif %} {{- '<|role_end|>' }} {%- elif message.role == "tool" %} {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} {{- 'OBSERVATION' }} {%- endif %} {{- '\n\n' }} {{- content }} {{- '\n' }} {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} {{- '<|role_end|>' }} {%- endif %} {%- endif %} {%- endfor %} {#- ==================== generation prompt ==================== -#} {%- if add_generation_prompt %} {{- 'ASSISTANT' }} {%- if thinking_option == 'on' %} {{- '\n' }} {%- elif thinking_option == 'off' %} {{- '\n' }} {%- 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