Name and Version

(llama-cpp) ➜ bin git:(master) ./llama-cli -m /Users/qxy/release/RokidLLM_NLU_Chat_qwen3/models/tmp3.gguf
build: 5618 (1f63e75) with Apple clang version 14.0.3 (clang-1403.0.22.14.1) for x86_64-apple-darwin22.6.0
main: llama backend init
main: load the model and apply lora adapter, if any
llama_model_load_from_file_impl: using device Metal (Apple M1) - 10922 MiB free
llama_model_loader: loaded meta data with 32 key-value pairs and 220 tensors from /Users/qxy/release/RokidLLM_NLU_Chat_qwen3/models/tmp3.gguf (version GGUF V3 (latest))
llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
llama_model_loader: - kv 0: general.architecture str = minicpm
llama_model_loader: - kv 1: general.type str = model
llama_model_loader: - kv 2: general.name str = MiniCPM4 0.5B
llama_model_loader: - kv 3: general.organization str = Openbmb
llama_model_loader: - kv 4: general.basename str = MiniCPM4
llama_model_loader: - kv 5: general.size_label str = 0.5B
llama_model_loader: - kv 6: general.license str = apache-2.0
llama_model_loader: - kv 7: general.tags arr[str,1] = ["text-generation"]
llama_model_loader: - kv 8: general.languages arr[str,2] = ["zh", "en"]
llama_model_loader: - kv 9: minicpm.block_count u32 = 24
llama_model_loader: - kv 10: minicpm.context_length u32 = 32768
llama_model_loader: - kv 11: minicpm.embedding_length u32 = 1024
llama_model_loader: - kv 12: minicpm.feed_forward_length u32 = 4096
llama_model_loader: - kv 13: minicpm.attention.head_count u32 = 16
llama_model_loader: - kv 14: minicpm.attention.head_count_kv u32 = 2
llama_model_loader: - kv 15: minicpm.attention.layer_norm_rms_epsilon f32 = 0.000010
llama_model_loader: - kv 16: general.file_type u32 = 1
llama_model_loader: - kv 17: minicpm.embedding_scale f32 = 12.000000
llama_model_loader: - kv 18: minicpm.residual_scale f32 = 0.285774
llama_model_loader: - kv 19: minicpm.logit_scale f32 = 4.000000
llama_model_loader: - kv 20: general.quantization_version u32 = 2
llama_model_loader: - kv 21: tokenizer.ggml.model str = llama
llama_model_loader: - kv 22: tokenizer.ggml.pre str = default
llama_model_loader: - kv 23: tokenizer.ggml.tokens arr[str,73448] = ["", "", "", "", "<C...
llama_model_loader: - kv 24: tokenizer.ggml.scores arr[f32,73448] = [-1000.000000, -1000.000000, -1000.00...
llama_model_loader: - kv 25: tokenizer.ggml.token_type arr[i32,73448] = [3, 3, 3, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv 26: tokenizer.ggml.bos_token_id u32 = 1
llama_model_loader: - kv 27: tokenizer.ggml.eos_token_id u32 = 73440
llama_model_loader: - kv 28: tokenizer.ggml.unknown_token_id u32 = 0
llama_model_loader: - kv 29: tokenizer.ggml.add_bos_token bool = true
llama_model_loader: - kv 30: tokenizer.ggml.add_eos_token bool = false
llama_model_loader: - kv 31: tokenizer.chat_template str = {% for message in messages %}{{'<|im_...
llama_model_loader: - type f32: 51 tensors
llama_model_loader: - type f16: 169 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type = F16
print_info: file size = 827.64 MiB (16.00 BPW)
load: special tokens cache size = 11
load: token to piece cache size = 0.4344 MB
print_info: arch = minicpm
print_info: vocab_only = 0
print_info: n_ctx_train = 32768
print_info: n_embd = 1024
print_info: n_layer = 24
print_info: n_head = 16
print_info: n_head_kv = 2
print_info: n_rot = 64
print_info: n_swa = 0
print_info: is_swa_any = 0
print_info: n_embd_head_k = 64
print_info: n_embd_head_v = 64
print_info: n_gqa = 8
print_info: n_embd_k_gqa = 128
print_info: n_embd_v_gqa = 128
print_info: f_norm_eps = 0.0e+00
print_info: f_norm_rms_eps = 1.0e-05
print_info: f_clamp_kqv = 0.0e+00
print_info: f_max_alibi_bias = 0.0e+00
print_info: f_logit_scale = 4.0e+00
print_info: f_attn_scale = 0.0e+00
print_info: n_ff = 4096
print_info: n_expert = 0
print_info: n_expert_used = 0
print_info: causal attn = 1
print_info: pooling type = 0
print_info: rope type = 0
print_info: rope scaling = linear
print_info: freq_base_train = 10000.0
print_info: freq_scale_train = 1
print_info: n_ctx_orig_yarn = 32768
print_info: rope_finetuned = unknown
print_info: ssm_d_conv = 0
print_info: ssm_d_inner = 0
print_info: ssm_d_state = 0
print_info: ssm_dt_rank = 0
print_info: ssm_dt_b_c_rms = 0
print_info: model type = ?B
print_info: model params = 433.87 M
print_info: general.name = MiniCPM4 0.5B
print_info: f_embedding_scale = 12.000000
print_info: f_residual_scale = 0.285774
print_info: f_attention_scale = 0.000000
print_info: n_ff_shexp = 0
print_info: vocab type = SPM
print_info: n_vocab = 73448
print_info: n_merges = 0
print_info: BOS token = 1 ''
print_info: EOS token = 73440 '<|im_end|>'
print_info: EOT token = 73440 '<|im_end|>'
print_info: UNK token = 0 ''
print_info: LF token = 1099 '<0x0A>'
print_info: FIM PRE token = 73445 '<|fim_prefix|>'
print_info: FIM SUF token = 73447 '<|fim_suffix|>'
print_info: FIM MID token = 73446 '<|fim_middle|>'
print_info: EOG token = 73440 '<|im_end|>'
print_info: max token length = 48
load_tensors: loading model tensors, this can take a while... (mmap = true)
llama_model_load: error loading model: done_getting_tensors: wrong number of tensors; expected 220, got 218
llama_model_load_from_file_impl: failed to load model
common_init_from_params: failed to load model '/Users/qxy/release/RokidLLM_NLU_Chat_qwen3/models/tmp3.gguf'
main: error: unable to load model

./llama-cli -m /Users/qxy/release/RokidLLM_NLU_Chat_qwen3/models/tmp3.gguf (MiniCPM4 0.5B Q4_0

bug:
llama_model_load: error loading model: done_getting_tensors: wrong number of tensors; expected 220, got 218
llama_model_load_from_file_impl: failed to load model