llama.cpp/src/llama-arch.cpp

#include "llama-arch.h"

#include "llama-impl.h"

#include <map>

static const std::map<llm_arch, const char *> LLM_ARCH_NAMES = {
    { LLM_ARCH_LLAMA,            "llama"            },
    { LLM_ARCH_DECI,             "deci"             },
    { LLM_ARCH_FALCON,           "falcon"           },
    { LLM_ARCH_GROK,             "grok"             },
    { LLM_ARCH_GPT2,             "gpt2"             },
    { LLM_ARCH_GPTJ,             "gptj"             },
    { LLM_ARCH_GPTNEOX,          "gptneox"          },
    { LLM_ARCH_MPT,              "mpt"              },
    { LLM_ARCH_BAICHUAN,         "baichuan"         },
    { LLM_ARCH_STARCODER,        "starcoder"        },
    { LLM_ARCH_REFACT,           "refact"           },
    { LLM_ARCH_BERT,             "bert"             },
    { LLM_ARCH_NOMIC_BERT,       "nomic-bert"       },
    { LLM_ARCH_JINA_BERT_V2,     "jina-bert-v2"     },
    { LLM_ARCH_BLOOM,            "bloom"            },
    { LLM_ARCH_STABLELM,         "stablelm"         },
    { LLM_ARCH_QWEN,             "qwen"             },
    { LLM_ARCH_QWEN2,            "qwen2"            },
    { LLM_ARCH_QWEN2MOE,         "qwen2moe"         },
    { LLM_ARCH_QWEN2VL,          "qwen2vl"          },
    { LLM_ARCH_PHI2,             "phi2"             },
    { LLM_ARCH_PHI3,             "phi3"             },
    { LLM_ARCH_PHIMOE,           "phimoe"           },
    { LLM_ARCH_PLAMO,            "plamo"            },
    { LLM_ARCH_CODESHELL,        "codeshell"        },
    { LLM_ARCH_ORION,            "orion"            },
    { LLM_ARCH_INTERNLM2,        "internlm2"        },
    { LLM_ARCH_MINICPM,          "minicpm"          },
    { LLM_ARCH_MINICPM3,         "minicpm3"         },
    { LLM_ARCH_GEMMA,            "gemma"            },
    { LLM_ARCH_GEMMA2,           "gemma2"           },
    { LLM_ARCH_STARCODER2,       "starcoder2"       },
    { LLM_ARCH_MAMBA,            "mamba"            },
    { LLM_ARCH_XVERSE,           "xverse"           },
    { LLM_ARCH_COMMAND_R,        "command-r"        },
    { LLM_ARCH_COHERE2,          "cohere2"          },
    { LLM_ARCH_DBRX,             "dbrx"             },
    { LLM_ARCH_OLMO,             "olmo"             },
    { LLM_ARCH_OLMO2,            "olmo2"            },
    { LLM_ARCH_OLMOE,            "olmoe"            },
    { LLM_ARCH_OPENELM,          "openelm"          },
    { LLM_ARCH_ARCTIC,           "arctic"           },
    { LLM_ARCH_DEEPSEEK,         "deepseek"         },
    { LLM_ARCH_DEEPSEEK2,        "deepseek2"        },
    { LLM_ARCH_CHATGLM,          "chatglm"          },
    { LLM_ARCH_BITNET,           "bitnet"           },
    { LLM_ARCH_T5,               "t5"               },
    { LLM_ARCH_T5ENCODER,        "t5encoder"        },
    { LLM_ARCH_JAIS,             "jais"             },
    { LLM_ARCH_NEMOTRON,         "nemotron"         },
    { LLM_ARCH_EXAONE,           "exaone"           },
    { LLM_ARCH_RWKV6,            "rwkv6"            },
    { LLM_ARCH_RWKV6QWEN2,       "rwkv6qwen2"       },
    { LLM_ARCH_GRANITE,          "granite"          },
    { LLM_ARCH_GRANITE_MOE,      "granitemoe"       },
    { LLM_ARCH_CHAMELEON,        "chameleon"        },
    { LLM_ARCH_WAVTOKENIZER_DEC, "wavtokenizer-dec" },
    { LLM_ARCH_UNKNOWN,          "(unknown)"        },
};

static const std::map<llm_kv, const char *> LLM_KV_NAMES = {
    { LLM_KV_GENERAL_TYPE,                 "general.type"                          },
    { LLM_KV_GENERAL_ARCHITECTURE,         "general.architecture"                  },
    { LLM_KV_GENERAL_QUANTIZATION_VERSION, "general.quantization_version"          },
    { LLM_KV_GENERAL_ALIGNMENT,            "general.alignment"                     },
    { LLM_KV_GENERAL_NAME,                 "general.name"                          },
    { LLM_KV_GENERAL_AUTHOR,               "general.author"                        },
    { LLM_KV_GENERAL_VERSION,              "general.version"                       },
    { LLM_KV_GENERAL_URL,                  "general.url"                           },
    { LLM_KV_GENERAL_DESCRIPTION,          "general.description"                   },
    { LLM_KV_GENERAL_LICENSE,              "general.license"                       },
    { LLM_KV_GENERAL_SOURCE_URL,           "general.source.url"                    },
    { LLM_KV_GENERAL_SOURCE_HF_REPO,       "general.source.huggingface.repository" },

    { LLM_KV_VOCAB_SIZE,                        "%s.vocab_size"                        },
    { LLM_KV_CONTEXT_LENGTH,                    "%s.context_length"                    },
    { LLM_KV_EMBEDDING_LENGTH,                  "%s.embedding_length"                  },
    { LLM_KV_FEATURES_LENGTH,                   "%s.features_length"                   },
    { LLM_KV_BLOCK_COUNT,                       "%s.block_count"                       },
    { LLM_KV_LEADING_DENSE_BLOCK_COUNT,         "%s.leading_dense_block_count"         },
    { LLM_KV_FEED_FORWARD_LENGTH,               "%s.feed_forward_length"               },
    { LLM_KV_EXPERT_FEED_FORWARD_LENGTH,        "%s.expert_feed_forward_length"        },
    { LLM_KV_EXPERT_SHARED_FEED_FORWARD_LENGTH, "%s.expert_shared_feed_forward_length" },
    { LLM_KV_USE_PARALLEL_RESIDUAL,             "%s.use_parallel_residual"             },
    { LLM_KV_TENSOR_DATA_LAYOUT,                "%s.tensor_data_layout"                },
    { LLM_KV_EXPERT_COUNT,                      "%s.expert_count"                      },
    { LLM_KV_EXPERT_USED_COUNT,                 "%s.expert_used_count"                 },
    { LLM_KV_EXPERT_SHARED_COUNT,               "%s.expert_shared_count"               },
    { LLM_KV_EXPERT_WEIGHTS_SCALE,              "%s.expert_weights_scale"              },
    { LLM_KV_EXPERT_WEIGHTS_NORM,               "%s.expert_weights_norm"               },
    { LLM_KV_EXPERT_GATING_FUNC,                "%s.expert_gating_func"                },
    { LLM_KV_POOLING_TYPE,                      "%s.pooling_type"                      },
    { LLM_KV_LOGIT_SCALE,                       "%s.logit_scale"                       },
    { LLM_KV_DECODER_START_TOKEN_ID,            "%s.decoder_start_token_id"            },
    { LLM_KV_ATTN_LOGIT_SOFTCAPPING,            "%s.attn_logit_softcapping"            },
    { LLM_KV_FINAL_LOGIT_SOFTCAPPING,           "%s.final_logit_softcapping"           },
    { LLM_KV_SWIN_NORM,                         "%s.swin_norm"                         },
    { LLM_KV_RESCALE_EVERY_N_LAYERS,            "%s.rescale_every_n_layers"            },
    { LLM_KV_TIME_MIX_EXTRA_DIM,                "%s.time_mix_extra_dim"                },
    { LLM_KV_TIME_DECAY_EXTRA_DIM,              "%s.time_decay_extra_dim"              },
    { LLM_KV_RESIDUAL_SCALE,                    "%s.residual_scale"                    },
    { LLM_KV_EMBEDDING_SCALE,                   "%s.embedding_scale"                   },
    { LLM_KV_TOKEN_SHIFT_COUNT,                 "%s.token_shift_count"                 },

    { LLM_KV_ATTENTION_HEAD_COUNT,             "%s.attention.head_count"             },
    { LLM_KV_ATTENTION_HEAD_COUNT_KV,          "%s.attention.head_count_kv"          },
    { LLM_KV_ATTENTION_MAX_ALIBI_BIAS,         "%s.attention.max_alibi_bias"         },
    { LLM_KV_ATTENTION_CLAMP_KQV,              "%s.attention.clamp_kqv"              },
    { LLM_KV_ATTENTION_KEY_LENGTH,             "%s.attention.key_length"             },
    { LLM_KV_ATTENTION_VALUE_LENGTH,           "%s.attention.value_length"           },
    { LLM_KV_ATTENTION_LAYERNORM_EPS,          "%s.attention.layer_norm_epsilon"     },
    { LLM_KV_ATTENTION_LAYERNORM_RMS_EPS,      "%s.attention.layer_norm_rms_epsilon" },
    { LLM_KV_ATTENTION_GROUPNORM_EPS,          "%s.attention.group_norm_epsilon"     },
    { LLM_KV_ATTENTION_GROUPNORM_GROUPS,       "%s.attention.group_norm_groups"      },
    { LLM_KV_ATTENTION_CAUSAL,                 "%s.attention.causal"                 },
    { LLM_KV_ATTENTION_Q_LORA_RANK,            "%s.attention.q_lora_rank"            },
    { LLM_KV_ATTENTION_KV_LORA_RANK,           "%s.attention.kv_lora_rank"           },
    { LLM_KV_ATTENTION_RELATIVE_BUCKETS_COUNT, "%s.attention.relative_buckets_count" },
    { LLM_KV_ATTENTION_SLIDING_WINDOW,         "%s.attention.sliding_window"         },
    { LLM_KV_ATTENTION_SCALE,                  "%s.attention.scale"                  },

    { LLM_KV_ROPE_DIMENSION_COUNT,      "%s.rope.dimension_count"                 },
    { LLM_KV_ROPE_DIMENSION_SECTIONS,   "%s.rope.dimension_sections"              },
    { LLM_KV_ROPE_FREQ_BASE,            "%s.rope.freq_base"                       },
    { LLM_KV_ROPE_SCALE_LINEAR,         "%s.rope.scale_linear"                    },
    { LLM_KV_ROPE_SCALING_TYPE,         "%s.rope.scaling.type"                    },
    { LLM_KV_ROPE_SCALING_FACTOR,       "%s.rope.scaling.factor"                  },
    { LLM_KV_ROPE_SCALING_ATTN_FACTOR,  "%s.rope.scaling.attn_factor"             },
    { LLM_KV_ROPE_SCALING_ORIG_CTX_LEN, "%s.rope.scaling.original_context_length" },
    { LLM_KV_ROPE_SCALING_FINETUNED,    "%s.rope.scaling.finetuned"               },
    { LLM_KV_ROPE_SCALING_YARN_LOG_MUL, "%s.rope.scaling.yarn_log_multiplier"     },

    { LLM_KV_SPLIT_NO,            "split.no"            },
    { LLM_KV_SPLIT_COUNT,         "split.count"         },
    { LLM_KV_SPLIT_TENSORS_COUNT, "split.tensors.count" },

    { LLM_KV_SSM_CONV_KERNEL,    "%s.ssm.conv_kernel"    },
    { LLM_KV_SSM_INNER_SIZE,     "%s.ssm.inner_size"     },
    { LLM_KV_SSM_STATE_SIZE,     "%s.ssm.state_size"     },
    { LLM_KV_SSM_TIME_STEP_RANK, "%s.ssm.time_step_rank" },
    { LLM_KV_SSM_DT_B_C_RMS,     "%s.ssm.dt_b_c_rms"     },

    { LLM_KV_WKV_HEAD_SIZE, "%s.wkv.head_size" },

    { LLM_KV_POSNET_EMBEDDING_LENGTH, "%s.posnet.embedding_length" },
    { LLM_KV_POSNET_BLOCK_COUNT,      "%s.posnet.block_count"      },

    { LLM_KV_CONVNEXT_EMBEDDING_LENGTH, "%s.convnext.embedding_length" },
    { LLM_KV_CONVNEXT_BLOCK_COUNT,      "%s.convnext.block_count"      },

    { LLM_KV_TOKENIZER_MODEL,                "tokenizer.ggml.model"                    },
    { LLM_KV_TOKENIZER_PRE,                  "tokenizer.ggml.pre"                      },
    { LLM_KV_TOKENIZER_LIST,                 "tokenizer.ggml.tokens"                   },
    { LLM_KV_TOKENIZER_TOKEN_TYPE,           "tokenizer.ggml.token_type"               },
    { LLM_KV_TOKENIZER_TOKEN_TYPE_COUNT,     "tokenizer.ggml.token_type_count"         },
    { LLM_KV_TOKENIZER_SCORES,               "tokenizer.ggml.scores"                   },
    { LLM_KV_TOKENIZER_MERGES,               "tokenizer.ggml.merges"                   },
    { LLM_KV_TOKENIZER_BOS_ID,               "tokenizer.ggml.bos_token_id"             },
    { LLM_KV_TOKENIZER_EOS_ID,               "tokenizer.ggml.eos_token_id"             },
    { LLM_KV_TOKENIZER_EOT_ID,               "tokenizer.ggml.eot_token_id"             },
    { LLM_KV_TOKENIZER_EOM_ID,               "tokenizer.ggml.eom_token_id"             },
    { LLM_KV_TOKENIZER_UNK_ID,               "tokenizer.ggml.unknown_token_id"         },
    { LLM_KV_TOKENIZER_SEP_ID,               "tokenizer.ggml.seperator_token_id"       },
    { LLM_KV_TOKENIZER_PAD_ID,               "tokenizer.ggml.padding_token_id"         },
    { LLM_KV_TOKENIZER_CLS_ID,               "tokenizer.ggml.cls_token_id"             },
    { LLM_KV_TOKENIZER_MASK_ID,              "tokenizer.ggml.mask_token_id"            },
    { LLM_KV_TOKENIZER_ADD_BOS,              "tokenizer.ggml.add_bos_token"            },
    { LLM_KV_TOKENIZER_ADD_EOS,              "tokenizer.ggml.add_eos_token"            },
    { LLM_KV_TOKENIZER_ADD_PREFIX,           "tokenizer.ggml.add_space_prefix"         },
    { LLM_KV_TOKENIZER_REMOVE_EXTRA_WS,      "tokenizer.ggml.remove_extra_whitespaces" },
    { LLM_KV_TOKENIZER_PRECOMPILED_CHARSMAP, "tokenizer.ggml.precompiled_charsmap"     },
    { LLM_KV_TOKENIZER_HF_JSON,              "tokenizer.huggingface.json"              },
    { LLM_KV_TOKENIZER_RWKV,                 "tokenizer.rwkv.world"                    },
    { LLM_KV_TOKENIZER_CHAT_TEMPLATE,        "tokenizer.chat_template"                 },
    { LLM_KV_TOKENIZER_FIM_PRE_ID,           "tokenizer.ggml.fim_pre_token_id"         },
    { LLM_KV_TOKENIZER_FIM_SUF_ID,           "tokenizer.ggml.fim_suf_token_id"         },
    { LLM_KV_TOKENIZER_FIM_MID_ID,           "tokenizer.ggml.fim_mid_token_id"         },
    { LLM_KV_TOKENIZER_FIM_PAD_ID,           "tokenizer.ggml.fim_pad_token_id"         },
    { LLM_KV_TOKENIZER_FIM_REP_ID,           "tokenizer.ggml.fim_rep_token_id"         },
    { LLM_KV_TOKENIZER_FIM_SEP_ID,           "tokenizer.ggml.fim_sep_token_id"         },

    { LLM_KV_ADAPTER_TYPE,       "adapter.type"       },
    { LLM_KV_ADAPTER_LORA_ALPHA, "adapter.lora.alpha" },

    // deprecated
    { LLM_KV_TOKENIZER_PREFIX_ID, "tokenizer.ggml.prefix_token_id" },
    { LLM_KV_TOKENIZER_SUFFIX_ID, "tokenizer.ggml.suffix_token_id" },
    { LLM_KV_TOKENIZER_MIDDLE_ID, "tokenizer.ggml.middle_token_id" },
};

static const std::map<llm_arch, std::map<llm_tensor, const char *>> LLM_TENSOR_NAMES = {
    {
        LLM_ARCH_LLAMA,
        {
            { LLM_TENSOR_TOKEN_EMBD,      "token_embd" },
            { LLM_TENSOR_OUTPUT_NORM,     "output_norm" },
            { LLM_TENSOR_OUTPUT,          "output" },
            { LLM_TENSOR_ROPE_FREQS,      "rope_freqs" },
            { LLM_TENSOR_ATTN_NORM,       "blk.%d.attn_norm" },
            { LLM_TENSOR_ATTN_Q,          "blk.%d.attn_q" },
            { LLM_TENSOR_ATTN_K,          "blk.%d.attn_k" },
            { LLM_TENSOR_ATTN_V,          "blk.%d.attn_v" },
            { LLM_TENSOR_ATTN_OUT,        "blk.%d.attn_output" },
            { LLM_TENSOR_ATTN_ROT_EMBD,   "blk.%d.attn_rot_embd" },
            { LLM_TENSOR_FFN_GATE_INP,    "blk.%d.ffn_gate_inp" },
            { LLM_TENSOR_FFN_NORM,        "blk.%d.ffn_norm" },
            { LLM_TENSOR_FFN_GATE,        "blk.%d.ffn_gate" },
            { LLM_TENSOR_FFN_DOWN,        "blk.%d.ffn_down" },
            { LLM_TENSOR_FFN_UP,          "blk.%d.ffn_up" },
            { LLM_TENSOR_FFN_GATE_EXP,    "blk.%d.ffn_gate.%d" },
            { LLM_TENSOR_FFN_DOWN_EXP,    "blk.%d.ffn_down.%d" },
            { LLM_TENSOR_FFN_UP_EXP,      "blk.%d.ffn_up.%d" },
            { LLM_TENSOR_FFN_GATE_EXPS,   "blk.%d.ffn_gate_exps" },
            { LLM_TENSOR_FFN_DOWN_EXPS,   "blk.%d.ffn_down_exps" },
            { LLM_TENSOR_FFN_UP_EXPS,     "blk.%d.ffn_up_exps" },
        },
    },
    {
        LLM_ARCH_DECI,
        {
            { LLM_TENSOR_TOKEN_EMBD,      "token_embd" },
            { LLM_TENSOR_OUTPUT_NORM,     "output_norm" },
            { LLM_TENSOR_OUTPUT,          "output" },
            { LLM_TENSOR_ROPE_FREQS,      "rope_freqs" },
            { LLM_TENSOR_ATTN_NORM,       "blk.%d.attn_norm" },
            { LLM_TENSOR_ATTN_Q,          "blk.%d.attn_q" },
            { LLM_TENSOR_ATTN_K,          "blk.%d.attn_k" },
            { LLM_TENSOR_ATTN_V,          "blk.%d.attn_v" },
            { LLM_TENSOR_ATTN_OUT,        "blk.%d.attn_output" },
            { LLM_TENSOR_ATTN_ROT_EMBD,   "blk.%d.attn_rot_embd" },
            { LLM_TENSOR_FFN_GATE_INP,    "blk.%d.ffn_gate_inp" },
            { LLM_TENSOR_FFN_NORM,        "blk.%d.ffn_norm" },
            { LLM_TENSOR_FFN_GATE,        "blk.%d.ffn_gate" },
            { LLM_TENSOR_FFN_DOWN,        "blk.%d.ffn_down" },
            { LLM_TENSOR_FFN_UP,          "blk.%d.ffn_up" },
            { LLM_TENSOR_FFN_GATE_EXP,    "blk.%d.ffn_gate.%d" },
            { LLM_TENSOR_FFN_DOWN_EXP,    "blk.%d.ffn_down.%d" },
            { LLM_TENSOR_FFN_UP_EXP,      "blk.%d.ffn_up.%d" },
            { LLM_TENSOR_FFN_GATE_EXPS,   "blk.%d.ffn_gate_exps" },
            { LLM_TENSOR_FFN_DOWN_EXPS,   "blk.%d.ffn_down_exps" },
            { LLM_TENSOR_FFN_UP_EXPS,     "blk.%d.ffn_up_exps" },
        },
    },
    {
        LLM_ARCH_BAICHUAN,
        {
            { LLM_TENSOR_TOKEN_EMBD,      "token_embd" },
            { LLM_TENSOR_OUTPUT_NORM,     "output_norm" },
            { LLM_TENSOR_OUTPUT,          "output" },
            { LLM_TENSOR_ROPE_FREQS,      "rope_freqs" },
            { LLM_TENSOR_ATTN_NORM,       "blk.%d.attn_norm" },
            { LLM_TENSOR_ATTN_Q,          "blk.%d.attn_q" },
            { LLM_TENSOR_ATTN_K,          "blk.%d.attn_k" },
            { LLM_TENSOR_ATTN_V,          "blk.%d.attn_v" },
            { LLM_TENSOR_ATTN_OUT,        "blk.%d.attn_output" },
            { LLM_TENSOR_ATTN_ROT_EMBD,   "blk.%d.attn_rot_embd" },
            { LLM_TENSOR_FFN_NORM,        "blk.%d.ffn_norm" },
            { LLM_TENSOR_FFN_GATE,        "blk.%d.ffn_gate" },
            { LLM_TENSOR_FFN_DOWN,        "blk.%d.ffn_down" },
            { LLM_TENSOR_FFN_UP,          "blk.%d.ffn_up" },
        },
    },
    {
        LLM_ARCH_FALCON,
        {
            { LLM_TENSOR_TOKEN_EMBD,      "token_embd" },
            { LLM_TENSOR_OUTPUT_NORM,     "output_norm" },
            { LLM_TENSOR_OUTPUT,          "output" },
            { LLM_TENSOR_ATTN_NORM,       "blk.%d.attn_norm" },
            { LLM_TENSOR_ATTN_NORM_2,     "blk.%d.attn_norm_2" },
            { LLM_TENSOR_ATTN_QKV,        "blk.%d.attn_qkv" },
            { LLM_TENSOR_ATTN_OUT,        "blk.%d.attn_output" },
            { LLM_TENSOR_FFN_DOWN,        "blk.%d.ffn_down" },
            { LLM_TENSOR_FFN_UP,          "blk.%d.ffn_up" },
        },
    },
    {
        LLM_ARCH_GROK,
        {
            { LLM_TENSOR_TOKEN_EMBD,      "token_embd" },
            { LLM_TENSOR_OUTPUT_NORM,     "output_norm" },
            { LLM_TENSOR_OUTPUT,          "output" },
            { LLM_TENSOR_ROPE_FREQS,      "rope_freqs" },
            { LLM_TENSOR_ATTN_NORM,       "blk.%d.attn_norm" },
            { LLM_TENSOR_ATTN_Q,          "blk.%d.attn_q" },
            { LLM_TENSOR_ATTN_K,          "blk.%d.attn_k" },
            { LLM_TENSOR_ATTN_V,          "blk.%d.attn_v" },
            { LLM_TENSOR_ATTN_OUT,        "blk.%d.attn_output" },
            { LLM_TENSOR_ATTN_ROT_EMBD,   "blk.%d.attn_rot_embd" },
            { LLM_TENSOR_FFN_GATE_INP,    "blk.%d.ffn_gate_inp" },
            { LLM_TENSOR_FFN_NORM,        "blk.%d.ffn_norm" },
            { LLM_TENSOR_FFN_GATE_EXP,    "blk.%d.ffn_gate.%d" },
            { LLM_TENSOR_FFN_DOWN_EXP,    "blk.%d.ffn_down.%d" },
            { LLM_TENSOR_FFN_UP_EXP,      "blk.%d.ffn_up.%d" },
            { LLM_TENSOR_FFN_GATE_EXPS,   "blk.%d.ffn_gate_exps" },
            { LLM_TENSOR_FFN_DOWN_EXPS,   "blk.%d.ffn_down_exps" },
            { LLM_TENSOR_FFN_UP_EXPS,     "blk.%d.ffn_up_exps" },
            { LLM_TENSOR_LAYER_OUT_NORM,  "blk.%d.layer_output_norm" },
            { LLM_TENSOR_ATTN_OUT_NORM,   "blk.%d.attn_output_norm" },
        },
    },
    {
        LLM_ARCH_GPT2,
        {
            { LLM_TENSOR_TOKEN_EMBD,      "token_embd" },
            { LLM_TENSOR_POS_EMBD,        "position_embd" },
            { LLM_TENSOR_OUTPUT_NORM,     "output_norm" },
            { LLM_TENSOR_OUTPUT,          "output" },
            { LLM_TENSOR_ATTN_NORM,       "blk.%d.attn_norm" },
            { LLM_TENSOR_ATTN_QKV,        "blk.%d.attn_qkv" },
            { LLM_TENSOR_ATTN_OUT,        "blk.%d.attn_output" },
            { LLM_TENSOR_FFN_NORM,        "blk.%d.ffn_norm" },
            { LLM_TENSOR_FFN_UP,          "blk.%d.ffn_up" },
            { LLM_TENSOR_FFN_DOWN,        "blk.%d.ffn_down" },
        },
    },
    {
        LLM_ARCH_GPTJ,
        {
            { LLM_TENSOR_TOKEN_EMBD,      "token_embd" },
        },
    },
    {
        LLM_ARCH_GPTNEOX,
        {
            { LLM_TENSOR_TOKEN_EMBD,      "token_embd" },
            { LLM_TENSOR_OUTPUT_NORM,     "output_norm" },
            { LLM_TENSOR_OUTPUT,          "output" },
            { LLM_TENSOR_ATTN_NORM,       "blk.%d.attn_norm" },
            { LLM_TENSOR_ATTN_QKV,        "blk.%d.attn_qkv" },
            { LLM_TENSOR_ATTN_OUT,        "blk.%d.attn_output" },
            { LLM_TENSOR_FFN_NORM,        "blk.%d.ffn_norm" },
            { LLM_TENSOR_FFN_DOWN,        "blk.%d.ffn_down" },
            { LLM_TENSOR_FFN_UP,          "blk.%d.ffn_up" },
        },
    },
    {
        LLM_ARCH_MPT,
        {
            { LLM_TENSOR_TOKEN_EMBD,      "token_embd" },
            { LLM_TENSOR_OUTPUT_NORM,     "output_norm" },
            { LLM_TENSOR_OUTPUT,          "output"},
            { LLM_TENSOR_ATTN_NORM,       "blk.%d.attn_norm" },
            { LLM_TENSOR_FFN_NORM,        "blk.%d.ffn_norm" },
            { LLM_TENSOR_ATTN_QKV,        "blk.%d.attn_qkv" },
            { LLM_TENSOR_ATTN_OUT,        "blk.%d.attn_output" },
            { LLM_TENSOR_FFN_DOWN,        "blk.%d.ffn_down" },
            { LLM_TENSOR_FFN_UP,          "blk.%d.ffn_up" },
            { LLM_TENSOR_FFN_ACT,         "blk.%d.ffn.act" },
            { LLM_TENSOR_POS_EMBD,        "position_embd" },
            { LLM_TENSOR_ATTN_Q_NORM,     "blk.%d.attn_q_norm"},
            { LLM_TENSOR_ATTN_K_NORM,     "blk.%d.attn_k_norm"},
        },
    },
    {
        LLM_ARCH_STARCODER,
        {
            { LLM_TENSOR_TOKEN_EMBD,      "token_embd" },
            { LLM_TENSOR_POS_EMBD,        "position_embd" },
            { LLM_TENSOR_OUTPUT_NORM,     "output_norm" },
            { LLM_TENSOR_OUTPUT,          "output" },
            { LLM_TENSOR_ATTN_NORM,       "blk.%d.attn_norm" },
            { LLM_TENSOR_ATTN_QKV,        "blk.%d.attn_qkv" },
            { LLM_TENSOR_ATTN_OUT,        "blk.%d.attn_output" },
            { LLM_TENSOR_FFN_NORM,        "blk.%d.ffn_norm" },
            { LLM_TENSOR_FFN_UP,          "blk.%d.ffn_up" },
            { LLM_TENSOR_FFN_DOWN,        "blk.%d.ffn_down" },
        },
    },
    {
        LLM_ARCH_REFACT,
        {
            { LLM_TENSOR_TOKEN_EMBD,      "token_embd" },
            { LLM_TENSOR_OUTPUT_NORM,     "output_norm" },
            { LLM_TENSOR_OUTPUT,          "output" },
            { LLM_TENSOR_ATTN_NORM,       "blk.%d.attn_norm" },
            { LLM_TENSOR_ATTN_Q,          "blk.%d.attn_q" },
            { LLM_TENSOR_ATTN_K,          "blk.%d.attn_k" },
            { LLM_TENSOR_ATTN_V,          "blk.%d.attn_v" },
            { LLM_TENSOR_ATTN_OUT,        "blk.%d.attn_output" },
            { LLM_TENSOR_FFN_NORM,        "blk.%d.ffn_norm" },
            { LLM_TENSOR_FFN_GATE,        "blk.%d.ffn_gate" },
            { LLM_TENSOR_FFN_DOWN,        "blk.%d.ffn_down" },
            { LLM_TENSOR_FFN_UP,          "blk.%d.ffn_up" },
        },
    },
    {
        LLM_ARCH_BERT,
        {
            { LLM_TENSOR_TOKEN_EMBD,      "token_embd" },
            { LLM_TENSOR_TOKEN_EMBD_NORM, "token_embd_norm" },
            { LLM_TENSOR_TOKEN_TYPES,     "token_types" },
            { LLM_TENSOR_POS_EMBD,        "position_embd" },
            { LLM_TENSOR_ATTN_OUT_NORM,   "blk.%d.attn_output_norm" },
            { LLM_TENSOR_ATTN_Q,          "blk.%d.attn_q" },
            { LLM_TENSOR_ATTN_K,          "blk.%d.attn_k" },
            { LLM_TENSOR_ATTN_V,          "blk.%d.attn_v" },
            { LLM_TENSOR_ATTN_OUT,        "blk.%d.attn_output" },
            { LLM_TENSOR_LAYER_OUT_NORM,  "blk.%d.layer_output_norm" },
            { LLM_TENSOR_FFN_DOWN,        "blk.%d.ffn_down" },
            { LLM_TENSOR_FFN_UP,          "blk.%d.ffn_up" },
            { LLM_TENSOR_CLS,             "cls" },
            { LLM_TENSOR_CLS_OUT,         "cls.output" },
        },
    },
    {
        LLM_ARCH_NOMIC_BERT,
        {
            { LLM_TENSOR_TOKEN_EMBD,      "token_embd" },
            { LLM_TENSOR_TOKEN_EMBD_NORM, "token_embd_norm" },
            { LLM_TENSOR_TOKEN_TYPES,     "token_types" },
            { LLM_TENSOR_ATTN_OUT_NORM,   "blk.%d.attn_output_norm" },
            { LLM_TENSOR_ATTN_QKV,        "blk.%d.attn_qkv" },
            { LLM_TENSOR_ATTN_OUT,        "blk.%d.attn_output" },
            { LLM_TENSOR_LAYER_OUT_NORM,  "blk.%d.layer_output_norm" },
            { LLM_TENSOR_FFN_GATE,        "blk.%d.ffn_gate" },
            { LLM_TENSOR_FFN_DOWN,        "blk.%d.ffn_down" },
            { LLM_TENSOR_FFN_UP,          "blk.%d.ffn_up" },
        },
    },
    {
        LLM_ARCH_JINA_BERT_V2,
        {
            { LLM_TENSOR_TOKEN_EMBD,      "token_embd" },
            { LLM_TENSOR_TOKEN_EMBD_NORM, "token_embd_norm" },
            { LLM_TENSOR_TOKEN_TYPES,     "token_types" },
            { LLM_TENSOR_ATTN_NORM_2,     "blk.%d.attn_norm_2" },
            { LLM_TENSOR_ATTN_OUT_NORM,   "blk.%d.attn_output_norm" },
            { LLM_TENSOR_ATTN_Q,          "blk.%d.attn_q" },
            { LLM_TENSOR_ATTN_Q_NORM,     "blk.%d.attn_q_norm" },
            { LLM_TENSOR_ATTN_K,          "blk.%d.attn_k" },
            { LLM_TENSOR_ATTN_K_NORM,     "blk.%d.attn_k_norm" },
            { LLM_TENSOR_ATTN_V,          "blk.%d.attn_v" },
            { LLM_TENSOR_ATTN_OUT,        "blk.%d.attn_output" },
            { LLM_TENSOR_LAYER_OUT_NORM,  "blk.%d.layer_output_norm" },
            { LLM_TENSOR_FFN_DOWN,        "blk.%d.ffn_down" },
            { LLM_TENSOR_FFN_GATE,        "blk.%d.ffn_gate" },
            { LLM_TENSOR_FFN_UP,          "blk.%d.ffn_up" },
            { LLM_TENSOR_CLS,             "cls" },
        },
    },
    {
        LLM_ARCH_BLOOM,
        {
            { LLM_TENSOR_TOKEN_EMBD,      "token_embd" },
            { LLM_TENSOR_TOKEN_EMBD_NORM, "token_embd_norm" },
            { LLM_TENSOR_OUTPUT_NORM,     "output_norm" },
            { LLM_TENSOR_OUTPUT,          "output" },
            { LLM_TENSOR_ATTN_NORM,       "blk.%d.attn_norm" },
            { LLM_TENSOR_ATTN_QKV,        "blk.%d.attn_qkv" },
            { LLM_TENSOR_ATTN_OUT,        "blk.%d.attn_output" },
            { LLM_TENSOR_FFN_NORM,        "blk.%d.ffn_norm" },
            { LLM_TENSOR_FFN_UP,          "blk.%d.ffn_up" },
            { LLM_TENSOR_FFN_DOWN,        "blk.%d.ffn_down" },
        },
    },
    {
        LLM_ARCH_STABLELM,
        {
            { LLM_TENSOR_TOKEN_EMBD,      "token_embd" },
            { LLM_TENSOR_OUTPUT_NORM,     "output_norm" },
            { LLM_TENSOR_OUTPUT,          "output" },
            { LLM_TENSOR_ROPE_FREQS,      "rope_freqs" },
            { LLM_TENSOR_ATTN_NORM,       "blk.%d.attn_norm" },
            { LLM_TENSOR_ATTN_Q,          "blk.%d.attn_q" },
            { LLM_TENSOR_ATTN_K,          "blk.%d.attn_k" },
            { LLM_TENSOR_ATTN_V,          "blk.%d.attn_v" },
            { LLM_TENSOR_ATTN_OUT,        "blk.%d.attn_output" },
            { LLM_TENSOR_FFN_NORM,        "blk.%d.ffn_norm" },
            { LLM_TENSOR_FFN_GATE,        "blk.%d.ffn_gate" },
            { LLM_TENSOR_FFN_DOWN,        "blk.%d.ffn_down" },
            { LLM_TENSOR_FFN_UP,          "blk.%d.ffn_up" },
            { LLM_TENSOR_ATTN_Q_NORM,     "blk.%d.attn_q_norm" },
            { LLM_TENSOR_ATTN_K_NORM,     "blk.%d.attn_k_norm" },
        },
    },
    {
        LLM_ARCH_QWEN,
        {
            { LLM_TENSOR_TOKEN_EMBD,      "token_embd" },
            { LLM_TENSOR_OUTPUT_NORM,     "output_norm" },
            { LLM_TENSOR_OUTPUT,          "output" },
            { LLM_TENSOR_ROPE_FREQS,      "rope_freqs" },
            { LLM_TENSOR_ATTN_NORM,       "blk.%d.attn_norm" },
            { LLM_TENSOR_ATTN_QKV,        "blk.%d.attn_qkv" },
            { LLM_TENSOR_ATTN_OUT,        "blk.%d.attn_output" },
            { LLM_TENSOR_FFN_NORM,        "blk.%d.ffn_norm" },
            { LLM_TENSOR_FFN_GATE,        "blk.%d.ffn_gate" },
            { LLM_TENSOR_FFN_DOWN,        "blk.%d.ffn_down" },
            { LLM_TENSOR_FFN_UP,          "blk.%d.ffn_up" },
        },
    },
    {
        LLM_ARCH_QWEN2,
        {
            { LLM_TENSOR_TOKEN_EMBD,      "token_embd" },
            { LLM_TENSOR_OUTPUT_NORM,     "output_norm" },
            { LLM_TENSOR_OUTPUT,          "output" },
            { LLM_TENSOR_ATTN_NORM,       "blk.%d.attn_norm" },
            { LLM_TENSOR_ATTN_Q,          "blk.%d.attn_q" },
            { LLM_TENSOR_ATTN_K,          "blk.%d.attn_k" },
            { LLM_TENSOR_ATTN_V,          "blk.%d.attn_v" },
            { LLM_TENSOR_ATTN_OUT,        "blk.%d.attn_output" },
            { LLM_TENSOR_FFN_NORM,        "blk.%d.ffn_norm" },
            { LLM_TENSOR_FFN_GATE,        "blk.%d.ffn_gate" },
            { LLM_TENSOR_FFN_DOWN,        "blk.%d.ffn_down" },
            { LLM_TENSOR_FFN_UP,          "blk.%d.ffn_up" },
        },
    },
    {
        LLM_ARCH_QWEN2VL,
        {
            { LLM_TENSOR_TOKEN_EMBD,      "token_embd" },
            { LLM_TENSOR_OUTPUT_NORM,     "output_norm" },
            { LLM_TENSOR_OUTPUT,          "output" },
            { LLM_TENSOR_ATTN_NORM,       "blk.%d.attn_norm" },
            { LLM_TENSOR_ATTN_Q,          "blk.%d.attn_q" },
            { LLM_TENSOR_ATTN_K,          "blk.%d.attn_k" },
            { LLM_TENSOR_ATTN_V,          "blk.%d.attn_v" },
            { LLM_TENSOR_ATTN_OUT,        "blk.%d.attn_output" },
            { LLM_TENSOR_FFN_NORM,        "blk.%d.ffn_norm" },
            { LLM_TENSOR_FFN_GATE,        "blk.%d.ffn_gate" },
            { LLM_TENSOR_FFN_DOWN,        "blk.%d.ffn_down" },
            { LLM_TENSOR_FFN_UP,          "blk.%d.ffn_up" },
        },
    },
    {
        LLM_ARCH_QWEN2MOE,
        {
            { LLM_TENSOR_TOKEN_EMBD,         "token_embd" },
            { LLM_TENSOR_OUTPUT_NORM,        "output_norm" },
            { LLM_TENSOR_OUTPUT,             "output" },
            { LLM_TENSOR_ATTN_NORM,          "blk.%d.attn_norm" },
            { LLM_TENSOR_ATTN_Q,             "blk.%d.attn_q" },
            { LLM_TENSOR_ATTN_K,             "blk.%d.attn_k" },
            { LLM_TENSOR_ATTN_V,             "blk.%d.attn_v" },
            { LLM_TENSOR_ATTN_OUT,           "blk.%d.attn_output" },
            { LLM_TENSOR_FFN_NORM,           "blk.%d.ffn_norm" },
            { LLM_TENSOR_FFN_GATE_INP,       "blk.%d.ffn_gate_inp" },
            { LLM_TENSOR_FFN_GATE_EXPS,      "blk.%d.ffn_gate_exps" },
            { LLM_TENSOR_FFN_DOWN_EXPS,      "blk.%d.ffn_down_exps" },
            { LLM_TENSOR_FFN_UP_EXPS,        "blk.%d.ffn_up_exps" },
            { LLM_TENSOR_FFN_GATE_INP_SHEXP, "blk.%d.ffn_gate_inp_shexp" },
            { LLM_TENSOR_FFN_GATE_SHEXP,     "blk.%d.ffn_gate_shexp" },
            { LLM_TENSOR_FFN_DOWN_SHEXP,     "blk.%d.ffn_down_shexp" },
            { LLM_TENSOR_FFN_UP_SHEXP,       "blk.%d.ffn_up_shexp" },
        },
    },
    {
        LLM_ARCH_PHI2,
        {
            { LLM_TENSOR_TOKEN_EMBD,      "token_embd" },
            { LLM_TENSOR_OUTPUT_NORM,     "output_norm" },
            { LLM_TENSOR_OUTPUT,          "output" },
            { LLM_TENSOR_ATTN_NORM,       "blk.%d.attn_norm" },
            { LLM_TENSOR_ATTN_QKV,        "blk.%d.attn_qkv" },
            { LLM_TENSOR_ATTN_Q,          "blk.%d.attn_q" },
            { LLM_TENSOR_ATTN_K,          "blk.%d.attn_k" },
            { LLM_TENSOR_ATTN_V,          "blk.%d.attn_v" },
            { LLM_TENSOR_ATTN_OUT,        "blk.%d.attn_output" },
            { LLM_TENSOR_FFN_DOWN,        "blk.%d.ffn_down" },
            { LLM_TENSOR_FFN_UP,          "blk.%d.ffn_up" },
        },
    },
    {
        LLM_ARCH_PHI3,
        {
            { LLM_TENSOR_TOKEN_EMBD,         "token_embd" },
            { LLM_TENSOR_OUTPUT_NORM,        "output_norm" },
            { LLM_TENSOR_OUTPUT,             "output" },
            { LLM_TENSOR_ROPE_FACTORS_LONG,  "rope_factors_long" },
            { LLM_TENSOR_ROPE_FACTORS_SHORT, "rope_factors_short" },
            { LLM_TENSOR_ATTN_NORM,          "blk.%d.attn_norm" },
            { LLM_TENSOR_ATTN_QKV,           "blk.%d.attn_qkv" },
            { LLM_TENSOR_ATTN_Q,             "blk.%d.attn_q" },
            { LLM_TENSOR_ATTN_K,             "blk.%d.attn_k" },
            { LLM_TENSOR_ATTN_V,             "blk.%d.attn_v" },
            { LLM_TENSOR_ATTN_OUT,           "blk.%d.attn_output" },
            { LLM_TENSOR_FFN_NORM,           "blk.%d.ffn_norm" },
            { LLM_TENSOR_FFN_DOWN,           "blk.%d.ffn_down" },
            { LLM_TENSOR_FFN_UP,             "blk.%d.ffn_up" },
        },
    },
    {
        LLM_ARCH_PHIMOE,
        {
            { LLM_TENSOR_TOKEN_EMBD,         "token_embd" },
            { LLM_TENSOR_OUTPUT_NORM,        "output_norm" },
            { LLM_TENSOR_OUTPUT,             "output" },
            { LLM_TENSOR_ROPE_FACTORS_LONG,  "rope_factors_long" },
            { LLM_TENSOR_ROPE_FACTORS_SHORT, "rope_factors_short" },
            { LLM_TENSOR_ATTN_NORM,          "blk.%d.attn_norm" },
            { LLM_TENSOR_ATTN_QKV,           "blk.%d.attn_qkv" },
            { LLM_TENSOR_ATTN_Q,             "blk.%d.attn_q" },
            { LLM_TENSOR_ATTN_K,             "blk.%d.attn_k" },
            { LLM_TENSOR_ATTN_V,             "blk.%d.attn_v" },
            { LLM_TENSOR_ATTN_OUT,           "blk.%d.attn_output" },
            { LLM_TENSOR_FFN_NORM,           "blk.%d.ffn_norm" },
            { LLM_TENSOR_FFN_GATE_INP,       "blk.%d.ffn_gate_inp" },
            { LLM_TENSOR_FFN_GATE_EXPS,      "blk.%d.ffn_gate_exps" },
            { LLM_TENSOR_FFN_DOWN_EXPS,      "blk.%d.ffn_down_exps" },
            { LLM_TENSOR_FFN_UP_EXPS,        "blk.%d.ffn_up_exps" },
        },
    },
    {
        LLM_ARCH_PLAMO,
        {
            { LLM_TENSOR_TOKEN_EMBD,      "token_embd" },
            { LLM_TENSOR_OUTPUT_NORM,     "output_norm" },
            { LLM_TENSOR_OUTPUT,          "output" },
            { LLM_TENSOR_ROPE_FREQS,      "rope_freqs" },
            { LLM_TENSOR_ATTN_NORM,       "blk.%d.attn_norm" },
            { LLM_TENSOR_ATTN_Q,          "blk.%d.attn_q" },
            { LLM_TENSOR_ATTN_K,          "blk.%d.attn_k" },
            { LLM_TENSOR_ATTN_V,          "blk.%d.attn_v" },
            { LLM_TENSOR_ATTN_OUT,        "blk.%d.attn_output" },
            { LLM_TENSOR_ATTN_ROT_EMBD,   "blk.%d.attn_rot_embd" },
            { LLM_TENSOR_FFN_GATE,        "blk.%d.ffn_gate" },
            { LLM_TENSOR_FFN_DOWN,        "blk.%d.ffn_down" },
            { LLM_TENSOR_FFN_UP,          "blk.%d.ffn_up" },
        },
    },
    {
        LLM_ARCH_CODESHELL,
        {
            { LLM_TENSOR_TOKEN_EMBD,      "token_embd" },
            { LLM_TENSOR_OUTPUT_NORM,     "output_norm" },
            { LLM_TENSOR_OUTPUT,          "output" },
            { LLM_TENSOR_ROPE_FREQS,      "rope_freqs" },
            { LLM_TENSOR_ATTN_NORM,       "blk.%d.attn_norm" },
            { LLM_TENSOR_ATTN_Q,          "blk.%d.attn_q" },
            { LLM_TENSOR_ATTN_K,          "blk.%d.attn_k" },
            { LLM_TENSOR_ATTN_V,          "blk.%d.attn_v" },
            { LLM_TENSOR_ATTN_QKV,        "blk.%d.attn_qkv" },
            { LLM_TENSOR_ATTN_OUT,        "blk.%d.attn_output" },
            { LLM_TENSOR_ATTN_ROT_EMBD,   "blk.%d.attn_rot_embd" },
            { LLM_TENSOR_FFN_NORM,        "blk.%d.ffn_norm" },
            { LLM_TENSOR_FFN_GATE,        "blk.%d.ffn_gate" },
            { LLM_TENSOR_FFN_DOWN,        "blk.%d.ffn_down" },
            { LLM_TENSOR_FFN_UP,          "blk.%d.ffn_up" },
        },
    },
    {
        LLM_ARCH_ORION,
        {
            { LLM_TENSOR_TOKEN_EMBD,      "token_embd" },
            { LLM_TENSOR_OUTPUT_NORM,     "output_norm" },
            { LLM_TENSOR_OUTPUT,          "output" },
            { LLM_TENSOR_ROPE_FREQS,      "rope_freqs" },
            { LLM_TENSOR_ATTN_NORM,       "blk.%d.attn_norm" },
            { LLM_TENSOR_ATTN_Q,          "blk.%d.attn_q" },
            { LLM_TENSOR_ATTN_K,          "blk.%d.attn_k" },
            { LLM_TENSOR_ATTN_V,          "blk.%d.attn_v" },
            { LLM_TENSOR_ATTN_OUT,        "blk.%d.attn_output" },
            { LLM_TENSOR_ATTN_ROT_EMBD,   "blk.%d.attn_rot_embd" },
            { LLM_TENSOR_FFN_NORM,        "blk.%d.ffn_norm" },
            { LLM_TENSOR_FFN_GATE,        "blk.%d.ffn_gate" },
            { LLM_TENSOR_FFN_DOWN,        "blk.%d.ffn_down" },
            { LLM_TENSOR_FFN_UP,          "blk.%d.ffn_up" },
        },
    },
    {
        LLM_ARCH_INTERNLM2,
        {
            { LLM_TENSOR_TOKEN_EMBD,      "token_embd" },
            { LLM_TENSOR_OUTPUT_NORM,     "output_norm" },
            { LLM_TENSOR_OUTPUT,          "output" },
            { LLM_TENSOR_ATTN_NORM,       "blk.%d.attn_norm" },
            { LLM_TENSOR_ATTN_Q,          "blk.%d.attn_q" },
            { LLM_TENSOR_ATTN_K,          "blk.%d.attn_k" },
            { LLM_TENSOR_ATTN_V,          "blk.%d.attn_v" },
            { LLM_TENSOR_ATTN_OUT,        "blk.%d.attn_output" },
            { LLM_TENSOR_FFN_NORM,        "blk.%d.ffn_norm" },
            { LLM_TENSOR_FFN_GATE,        "blk.%d.ffn_gate" },
            { LLM_TENSOR_FFN_DOWN,        "blk.%d.ffn_down" },
            { LLM_TENSOR_FFN_UP,          "blk.%d.ffn_up" },
        },
    },
    {
        LLM_ARCH_MINICPM,
        {
            { LLM_TENSOR_TOKEN_EMBD,      "token_embd" },
            { LLM_TENSOR_OUTPUT_NORM,     "output_norm" },
            { LLM_TENSOR_OUTPUT,          "output" },
            { LLM_TENSOR_ROPE_FREQS,      "rope_freqs" },
            { LLM_TENSOR_ROPE_FACTORS_LONG,  "rope_factors_long" },
            { LLM_TENSOR_ROPE_FACTORS_SHORT, "rope_factors_short" },
            { LLM_TENSOR_ATTN_NORM,       "blk.%d.attn_norm" },
            { LLM_TENSOR_ATTN_Q,          "blk.%d.attn_q" },
            { LLM_TENSOR_ATTN_K,          "blk.%d.attn_k" },
            { LLM_TENSOR_ATTN_V,          "blk.%d.attn_v" },
            { LLM_TENSOR_ATTN_OUT,        "blk.%d.attn_output" },
            { LLM_TENSOR_ATTN_ROT_EMBD,   "blk.%d.attn_rot_embd" },
            { LLM_TENSOR_FFN_GATE_INP,    "blk.%d.ffn_gate_inp" },
            { LLM_TENSOR_FFN_NORM,        "blk.%d.ffn_norm" },
            { LLM_TENSOR_FFN_GATE,        "blk.%d.ffn_gate" },
            { LLM_TENSOR_FFN_DOWN,        "blk.%d.ffn_down" },
            { LLM_TENSOR_FFN_UP,          "blk.%d.ffn_up" },
            { LLM_TENSOR_FFN_GATE_EXP,    "blk.%d.ffn_gate.%d" },
            { LLM_TENSOR_FFN_DOWN_EXP,    "blk.%d.ffn_down.%d" },
            { LLM_TENSOR_FFN_UP_EXP,      "blk.%d.ffn_up.%d" },
        },
    },
    {
        LLM_ARCH_MINICPM3,
        {
            { LLM_TENSOR_TOKEN_EMBD,         "token_embd" },
            { LLM_TENSOR_OUTPUT_NORM,        "output_norm" },
            { LLM_TENSOR_OUTPUT,             "output" },
            { LLM_TENSOR_ROPE_FACTORS_LONG,  "rope_factors_long" },
            { LLM_TENSOR_ROPE_FACTORS_SHORT, "rope_factors_short" },
            { LLM_TENSOR_ATTN_NORM,          "blk.%d.attn_norm" },
            { LLM_TENSOR_ATTN_Q_A_NORM,      "blk.%d.attn_q_a_norm" },
            { LLM_TENSOR_ATTN_KV_A_NORM,     "blk.%d.attn_kv_a_norm" },
            { LLM_TENSOR_ATTN_Q,             "blk.%d.attn_q" },
            { LLM_TENSOR_ATTN_Q_A,           "blk.%d.attn_q_a" },
            { LLM_TENSOR_ATTN_Q_B,           "blk.%d.attn_q_b" },
            { LLM_TENSOR_ATTN_KV_A_MQA,      "blk.%d.attn_kv_a_mqa" },
            { LLM_TENSOR_ATTN_KV_B,          "blk.%d.attn_kv_b" },
            { LLM_TENSOR_ATTN_OUT,           "blk.%d.attn_output" },
            { LLM_TENSOR_FFN_NORM,           "blk.%d.ffn_norm" },
            { LLM_TENSOR_FFN_GATE,           "blk.%d.ffn_gate" },
            { LLM_TENSOR_FFN_UP,             "blk.%d.ffn_up" },
            { LLM_TENSOR_FFN_DOWN,           "blk.%d.ffn_down" },
        },
    },
    {
        LLM_ARCH_GEMMA,
        {
            { LLM_TENSOR_TOKEN_EMBD,      "token_embd" },
            { LLM_TENSOR_OUTPUT_NORM,     "output_norm" },
            { LLM_TENSOR_ATTN_NORM,       "blk.%d.attn_norm" },
            { LLM_TENSOR_ATTN_Q,          "blk.%d.attn_q" },
            { LLM_TENSOR_ATTN_K,          "blk.%d.attn_k" },
            { LLM_TENSOR_ATTN_V,          "blk.%d.attn_v" },
            { LLM_TENSOR_ATTN_OUT,        "blk.%d.attn_output" },
            { LLM_TENSOR_FFN_NORM,        "blk.%d.ffn_norm" },
            { LLM_TENSOR_FFN_GATE,        "blk.%d.ffn_gate" },
            { LLM_TENSOR_FFN_DOWN,        "blk.%d.ffn_down" },
            { LLM_TENSOR_FFN_UP,          "blk.%d.ffn_up" },
        },
    },
    {
        LLM_ARCH_GEMMA2,
        {
            { LLM_TENSOR_TOKEN_EMBD,      "token_embd" },
            { LLM_TENSOR_OUTPUT_NORM,     "output_norm" },
            { LLM_TENSOR_ATTN_NORM,       "blk.%d.attn_norm" },
            { LLM_TENSOR_ATTN_Q,          "blk.%d.attn_q" },
            { LLM_TENSOR_ATTN_K,          "blk.%d.attn_k" },
            { LLM_TENSOR_ATTN_V,          "blk.%d.attn_v" },
            { LLM_TENSOR_ATTN_OUT,        "blk.%d.attn_output" },
            { LLM_TENSOR_ATTN_POST_NORM,  "blk.%d.post_attention_norm" },
            { LLM_TENSOR_FFN_NORM,        "blk.%d.ffn_norm" },
            { LLM_TENSOR_FFN_GATE,        "blk.%d.ffn_gate" },
            { LLM_TENSOR_FFN_DOWN,        "blk.%d.ffn_down" },
            { LLM_TENSOR_FFN_UP,          "blk.%d.ffn_up" },
            { LLM_TENSOR_FFN_POST_NORM,   "blk.%d.post_ffw_norm" },
        },
    },
    {
        LLM_ARCH_STARCODER2,
        {
            { LLM_TENSOR_TOKEN_EMBD,      "token_embd" },
            { LLM_TENSOR_OUTPUT_NORM,     "output_norm" },
            { LLM_TENSOR_OUTPUT,          "output" },
            { LLM_TENSOR_ROPE_FREQS,      "rope_freqs" },
            { LLM_TENSOR_ATTN_NORM,       "blk.%d.attn_norm" },
            { LLM_TENSOR_ATTN_Q,          "blk.%d.attn_q" },
            { LLM_TENSOR_ATTN_K,          "blk.%d.attn_k" },
            { LLM_TENSOR_ATTN_V,          "blk.%d.attn_v" },
            { LLM_TENSOR_ATTN_OUT,        "blk.%d.attn_output" },
            { LLM_TENSOR_ATTN_ROT_EMBD,   "blk.%d.attn_rot_embd" },
            { LLM_TENSOR_FFN_NORM,        "blk.%d.ffn_norm" },
            { LLM_TENSOR_FFN_DOWN,        "blk.%d.ffn_down" },
            { LLM_TENSOR_FFN_UP,          "blk.%d.ffn_up" },
        },
    },
    {
        LLM_ARCH_MAMBA,
        {
            { LLM_TENSOR_TOKEN_EMBD,      "token_embd" },
            { LLM_TENSOR_OUTPUT_NORM,     "output_norm" },
            { LLM_TENSOR_OUTPUT,          "output" },
            { LLM_TENSOR_ATTN_NORM,       "blk.%d.attn_norm" },
            { LLM_TENSOR_SSM_IN,          "blk.%d.ssm_in" },
            { LLM_TENSOR_SSM_CONV1D,      "blk.%d.ssm_conv1d" },
            { LLM_TENSOR_SSM_X,           "blk.%d.ssm_x" },
            { LLM_TENSOR_SSM_DT,          "blk.%d.ssm_dt" },
            { LLM_TENSOR_SSM_A,           "blk.%d.ssm_a" },
            { LLM_TENSOR_SSM_D,           "blk.%d.ssm_d" },
            { LLM_TENSOR_SSM_OUT,         "blk.%d.ssm_out" },
        },
    },
    {
        LLM_ARCH_XVERSE,
        {
            { LLM_TENSOR_TOKEN_EMBD,      "token_embd" },
            { LLM_TENSOR_OUTPUT_NORM,     "output_norm" },
            { LLM_TENSOR_OUTPUT,          "output" },
            { LLM_TENSOR_ROPE_FREQS,      "rope_freqs" },
            { LLM_TENSOR_ATTN_NORM,       "blk.%d.attn_norm" },
            { LLM_TENSOR_ATTN_Q,          "blk.%d.attn_q" },
            { LLM_TENSOR_ATTN_K,          "blk.%d.attn_k" },
            { LLM_TENSOR_ATTN_V,          "blk.%d.attn_v" },
            { LLM_TENSOR_ATTN_OUT,        "blk.%d.attn_output" },
            { LLM_TENSOR_ATTN_ROT_EMBD,   "blk.%d.attn_rot_embd" },
            { LLM_TENSOR_FFN_NORM,        "blk.%d.ffn_norm" },
            { LLM_TENSOR_FFN_GATE,        "blk.%d.ffn_gate" },
            { LLM_TENSOR_FFN_DOWN,        "blk.%d.ffn_down" },
            { LLM_TENSOR_FFN_UP,          "blk.%d.ffn_up" },
        },
    },
    {
        LLM_ARCH_COMMAND_R,
        {
            { LLM_TENSOR_TOKEN_EMBD,      "token_embd" },
            { LLM_TENSOR_OUTPUT_NORM,     "output_norm" },
            { LLM_TENSOR_ATTN_NORM,       "blk.%d.attn_norm" },
            { LLM_TENSOR_ATTN_Q,          "blk.%d.attn_q" },
            { LLM_TENSOR_ATTN_K,          "blk.%d.attn_k" },
            { LLM_TENSOR_ATTN_V,          "blk.%d.attn_v" },
            { LLM_TENSOR_ATTN_OUT,        "blk.%d.attn_output" },
            { LLM_TENSOR_FFN_GATE,        "blk.%d.ffn_gate" },
            { LLM_TENSOR_FFN_DOWN,        "blk.%d.ffn_down" },
            { LLM_TENSOR_FFN_UP,          "blk.%d.ffn_up" },
            { LLM_TENSOR_ATTN_Q_NORM,     "blk.%d.attn_q_norm" },
            { LLM_TENSOR_ATTN_K_NORM,     "blk.%d.attn_k_norm" },
        },
    },
    {
        LLM_ARCH_COHERE2,
        {
            { LLM_TENSOR_TOKEN_EMBD,      "token_embd" },
            { LLM_TENSOR_OUTPUT_NORM,     "output_norm" },
            { LLM_TENSOR_ATTN_NORM,       "blk.%d.attn_norm" },
            { LLM_TENSOR_ATTN_Q,          "blk.%d.attn_q" },
            { LLM_TENSOR_ATTN_K,          "blk.%d.attn_k" },
            { LLM_TENSOR_ATTN_V,          "blk.%d.attn_v" },
            { LLM_TENSOR_ATTN_OUT,        "blk.%d.attn_output" },
            { LLM_TENSOR_FFN_GATE,        "blk.%d.ffn_gate" },
            { LLM_TENSOR_FFN_DOWN,        "blk.%d.ffn_down" },
            { LLM_TENSOR_FFN_UP,          "blk.%d.ffn_up" },
        },
    },
    {
        LLM_ARCH_DBRX,
        {
            { LLM_TENSOR_TOKEN_EMBD,      "token_embd" },
            { LLM_TENSOR_OUTPUT_NORM,     "output_norm" },
            { LLM_TENSOR_OUTPUT,          "output" },
            { LLM_TENSOR_ATTN_QKV,        "blk.%d.attn_qkv" },
            { LLM_TENSOR_ATTN_NORM,       "blk.%d.attn_norm" },
            { LLM_TENSOR_ATTN_OUT,        "blk.%d.attn_output" },
            { LLM_TENSOR_ATTN_OUT_NORM,   "blk.%d.attn_output_norm" },
            { LLM_TENSOR_FFN_GATE_INP,    "blk.%d.ffn_gate_inp" },
            { LLM_TENSOR_FFN_GATE_EXPS,   "blk.%d.ffn_gate_exps" },
            { LLM_TENSOR_FFN_DOWN_EXPS,   "blk.%d.ffn_down_exps" },
            { LLM_TENSOR_FFN_UP_EXPS,     "blk.%d.ffn_up_exps" },
        },
    },
    {
        LLM_ARCH_OLMO,
        {
            { LLM_TENSOR_TOKEN_EMBD,      "token_embd" },
            { LLM_TENSOR_OUTPUT,          "output" },
            { LLM_TENSOR_ATTN_Q,          "blk.%d.attn_q" },
            { LLM_TENSOR_ATTN_K,          "blk.%d.attn_k" },
            { LLM_TENSOR_ATTN_V,          "blk.%d.attn_v" },
            { LLM_TENSOR_ATTN_OUT,        "blk.%d.attn_output" },
            { LLM_TENSOR_FFN_GATE,        "blk.%d.ffn_gate" },
            { LLM_TENSOR_FFN_DOWN,        "blk.%d.ffn_down" },
            { LLM_TENSOR_FFN_UP,          "blk.%d.ffn_up" },
        },
    },
    {
        LLM_ARCH_OLMO2,
        {
            { LLM_TENSOR_TOKEN_EMBD,      "token_embd" },
            { LLM_TENSOR_OUTPUT_NORM,     "output_norm" },
            { LLM_TENSOR_OUTPUT,          "output" },
            { LLM_TENSOR_ATTN_Q,          "blk.%d.attn_q" },
            { LLM_TENSOR_ATTN_K,          "blk.%d.attn_k" },
            { LLM_TENSOR_ATTN_V,          "blk.%d.attn_v" },
            { LLM_TENSOR_ATTN_OUT,        "blk.%d.attn_output" },
            { LLM_TENSOR_ATTN_POST_NORM,  "blk.%d.post_attention_norm" },
            { LLM_TENSOR_ATTN_Q_NORM,     "blk.%d.attn_q_norm" },
            { LLM_TENSOR_ATTN_K_NORM,     "blk.%d.attn_k_norm" },
            { LLM_TENSOR_FFN_POST_NORM,   "blk.%d.post_ffw_norm" },
            { LLM_TENSOR_FFN_GATE,        "blk.%d.ffn_gate" },
            { LLM_TENSOR_FFN_DOWN,        "blk.%d.ffn_down" },
            { LLM_TENSOR_FFN_UP,          "blk.%d.ffn_up" },
        },
    },
    {
        LLM_ARCH_OLMOE,
        {
            { LLM_TENSOR_TOKEN_EMBD,         "token_embd" },
            { LLM_TENSOR_OUTPUT_NORM,        "output_norm" },
            { LLM_TENSOR_OUTPUT,             "output" },
            { LLM_TENSOR_ATTN_NORM,          "blk.%d.attn_norm" },
            { LLM_TENSOR_ATTN_Q,             "blk.%d.attn_q" },
            { LLM_TENSOR_ATTN_K,             "blk.%d.attn_k" },
            { LLM_TENSOR_ATTN_V,             "blk.%d.attn_v" },
            { LLM_TENSOR_ATTN_OUT,           "blk.%d.attn_output" },
            { LLM_TENSOR_ATTN_Q_NORM,        "blk.%d.attn_q_norm" },
            { LLM_TENSOR_ATTN_K_NORM,        "blk.%d.attn_k_norm" },
            { LLM_TENSOR_FFN_NORM,           "blk.%d.ffn_norm" },
            { LLM_TENSOR_FFN_GATE_INP,       "blk.%d.ffn_gate_inp" },
            { LLM_TENSOR_FFN_GATE_EXPS,      "blk.%d.ffn_gate_exps" },
            { LLM_TENSOR_FFN_DOWN_EXPS,      "blk.%d.ffn_down_exps" },
            { LLM_TENSOR_FFN_UP_EXPS,        "blk.%d.ffn_up_exps" },
        },
    },
    {
        LLM_ARCH_OPENELM,
        {
            { LLM_TENSOR_TOKEN_EMBD,      "token_embd" },
            { LLM_TENSOR_OUTPUT_NORM,     "output_norm" },
            { LLM_TENSOR_ATTN_NORM,       "blk.%d.attn_norm" },
            { LLM_TENSOR_ATTN_QKV,        "blk.%d.attn_qkv" },
            { LLM_TENSOR_ATTN_Q_NORM,     "blk.%d.attn_q_norm" },
            { LLM_TENSOR_ATTN_K_NORM,     "blk.%d.attn_k_norm" },
            { LLM_TENSOR_ATTN_OUT,        "blk.%d.attn_output" },
            { LLM_TENSOR_FFN_NORM,        "blk.%d.ffn_norm" },
            { LLM_TENSOR_FFN_GATE,        "blk.%d.ffn_gate" },
            { LLM_TENSOR_FFN_DOWN,        "blk.%d.ffn_down" },
            { LLM_TENSOR_FFN_UP,          "blk.%d.ffn_up" },
        },
    },
    {
        LLM_ARCH_ARCTIC,
        {
            { LLM_TENSOR_TOKEN_EMBD,      "token_embd" },
            { LLM_TENSOR_OUTPUT_NORM,     "output_norm" },
            { LLM_TENSOR_OUTPUT,          "output" },
            { LLM_TENSOR_ATTN_NORM,       "blk.%d.attn_norm" },
            { LLM_TENSOR_ATTN_Q,          "blk.%d.attn_q" },
            { LLM_TENSOR_ATTN_K,          "blk.%d.attn_k" },
            { LLM_TENSOR_ATTN_V,          "blk.%d.attn_v" },
            { LLM_TENSOR_ATTN_OUT,        "blk.%d.attn_output" },
            { LLM_TENSOR_FFN_GATE_INP,    "blk.%d.ffn_gate_inp" },
            { LLM_TENSOR_FFN_NORM,        "blk.%d.ffn_norm" },
            { LLM_TENSOR_FFN_GATE,        "blk.%d.ffn_gate" },
            { LLM_TENSOR_FFN_DOWN,        "blk.%d.ffn_down" },
            { LLM_TENSOR_FFN_UP,          "blk.%d.ffn_up" },
            { LLM_TENSOR_FFN_NORM_EXPS,   "blk.%d.ffn_norm_exps" },
            { LLM_TENSOR_FFN_GATE_EXPS,   "blk.%d.ffn_gate_exps" },
            { LLM_TENSOR_FFN_DOWN_EXPS,   "blk.%d.ffn_down_exps" },
            { LLM_TENSOR_FFN_UP_EXPS,     "blk.%d.ffn_up_exps" },
        },
    },
    {
        LLM_ARCH_DEEPSEEK,
        {
            { LLM_TENSOR_TOKEN_EMBD,         "token_embd" },
            { LLM_TENSOR_OUTPUT_NORM,        "output_norm" },
            { LLM_TENSOR_OUTPUT,             "output" },
            { LLM_TENSOR_ROPE_FREQS,         "rope_freqs" },
            { LLM_TENSOR_ATTN_NORM,          "blk.%d.attn_norm" },
            { LLM_TENSOR_ATTN_Q,             "blk.%d.attn_q" },
            { LLM_TENSOR_ATTN_K,             "blk.%d.attn_k" },
            { LLM_TENSOR_ATTN_V,             "blk.%d.attn_v" },
            { LLM_TENSOR_ATTN_OUT,           "blk.%d.attn_output" },
            { LLM_TENSOR_ATTN_ROT_EMBD,      "blk.%d.attn_rot_embd" },
            { LLM_TENSOR_FFN_GATE_INP,       "blk.%d.ffn_gate_inp" },
            { LLM_TENSOR_FFN_NORM,           "blk.%d.ffn_norm" },
            { LLM_TENSOR_FFN_GATE,           "blk.%d.ffn_gate" },
            { LLM_TENSOR_FFN_DOWN,           "blk.%d.ffn_down" },
            { LLM_TENSOR_FFN_UP,             "blk.%d.ffn_up" },
            { LLM_TENSOR_FFN_GATE_EXPS,      "blk.%d.ffn_gate_exps" },
            { LLM_TENSOR_FFN_DOWN_EXPS,      "blk.%d.ffn_down_exps" },
            { LLM_TENSOR_FFN_UP_EXPS,        "blk.%d.ffn_up_exps" },
            { LLM_TENSOR_FFN_GATE_INP_SHEXP, "blk.%d.ffn_gate_inp_shexp" },
            { LLM_TENSOR_FFN_GATE_SHEXP,     "blk.%d.ffn_gate_shexp" },
            { LLM_TENSOR_FFN_DOWN_SHEXP,     "blk.%d.ffn_down_shexp" },
            { LLM_TENSOR_FFN_UP_SHEXP,       "blk.%d.ffn_up_shexp" },
        },
    },
    {
        LLM_ARCH_DEEPSEEK2,
        {
            { LLM_TENSOR_TOKEN_EMBD,         "token_embd" },
            { LLM_TENSOR_OUTPUT_NORM,        "output_norm" },
            { LLM_TENSOR_OUTPUT,             "output" },
            { LLM_TENSOR_ATTN_NORM,          "blk.%d.attn_norm" },
            { LLM_TENSOR_ATTN_Q_A_NORM,      "blk.%d.attn_q_a_norm" },
            { LLM_TENSOR_ATTN_KV_A_NORM,     "blk.%d.attn_kv_a_norm" },
            { LLM_TENSOR_ATTN_Q,             "blk.%d.attn_q" },
            { LLM_TENSOR_ATTN_Q_A,           "blk.%d.attn_q_a" },
            { LLM_TENSOR_ATTN_Q_B,           "blk.%d.attn_q_b" },
            { LLM_TENSOR_ATTN_KV_A_MQA,      "blk.%d.attn_kv_a_mqa" },
            { LLM_TENSOR_ATTN_KV_B,          "blk.%d.attn_kv_b" },
            { LLM_TENSOR_ATTN_OUT,           "blk.%d.attn_output" },
            { LLM_TENSOR_FFN_NORM,           "blk.%d.ffn_norm" },
            { LLM_TENSOR_FFN_GATE,           "blk.%d.ffn_gate" },
            { LLM_TENSOR_FFN_UP,             "blk.%d.ffn_up" },
            { LLM_TENSOR_FFN_DOWN,           "blk.%d.ffn_down" },
            { LLM_TENSOR_FFN_GATE_INP,       "blk.%d.ffn_gate_inp" },
            { LLM_TENSOR_FFN_GATE_EXPS,      "blk.%d.ffn_gate_exps" },
            { LLM_TENSOR_FFN_DOWN_EXPS,      "blk.%d.ffn_down_exps" },
            { LLM_TENSOR_FFN_UP_EXPS,        "blk.%d.ffn_up_exps" },
            { LLM_TENSOR_FFN_GATE_INP_SHEXP, "blk.%d.ffn_gate_inp_shexp" },
            { LLM_TENSOR_FFN_GATE_SHEXP,     "blk.%d.ffn_gate_shexp" },
            { LLM_TENSOR_FFN_DOWN_SHEXP,     "blk.%d.ffn_down_shexp" },
            { LLM_TENSOR_FFN_UP_SHEXP,       "blk.%d.ffn_up_shexp" },
            { LLM_TENSOR_FFN_EXP_PROBS_B,    "blk.%d.exp_probs_b" },
        },
    },
    {
        LLM_ARCH_CHATGLM,
        {
            { LLM_TENSOR_TOKEN_EMBD,      "token_embd" },
            { LLM_TENSOR_ROPE_FREQS,      "rope_freqs" },
            { LLM_TENSOR_OUTPUT_NORM,     "output_norm" },
            { LLM_TENSOR_OUTPUT,          "output" },
            { LLM_TENSOR_ATTN_NORM,       "blk.%d.attn_norm" },
            { LLM_TENSOR_ATTN_QKV,        "blk.%d.attn_qkv" },
            { LLM_TENSOR_ATTN_OUT,        "blk.%d.attn_output" },
            { LLM_TENSOR_FFN_NORM,        "blk.%d.ffn_norm" },
            { LLM_TENSOR_FFN_UP,          "blk.%d.ffn_up" },
            { LLM_TENSOR_FFN_DOWN,        "blk.%d.ffn_down" },
        },
    },
    {
        LLM_ARCH_BITNET,
        {
            { LLM_TENSOR_TOKEN_EMBD,         "token_embd" },
            { LLM_TENSOR_OUTPUT_NORM,        "output_norm" },
            { LLM_TENSOR_ATTN_Q,             "blk.%d.attn_q" },
            { LLM_TENSOR_ATTN_K,             "blk.%d.attn_k" },
            { LLM_TENSOR_ATTN_V,             "blk.%d.attn_v" },
            { LLM_TENSOR_ATTN_OUT,           "blk.%d.attn_output" },
            { LLM_TENSOR_ATTN_NORM,          "blk.%d.attn_norm" },
            { LLM_TENSOR_ATTN_SUB_NORM,      "blk.%d.attn_sub_norm" },
            { LLM_TENSOR_FFN_GATE,           "blk.%d.ffn_gate" },
            { LLM_TENSOR_FFN_DOWN,           "blk.%d.ffn_down" },
            { LLM_TENSOR_FFN_UP,             "blk.%d.ffn_up" },
            { LLM_TENSOR_FFN_NORM,           "blk.%d.ffn_norm" },
            { LLM_TENSOR_FFN_SUB_NORM,       "blk.%d.ffn_sub_norm" },
        },
    },
    {
        LLM_ARCH_T5,
        {
            { LLM_TENSOR_TOKEN_EMBD,           "token_embd" },
            { LLM_TENSOR_OUTPUT,               "output" },
            { LLM_TENSOR_DEC_OUTPUT_NORM,      "dec.output_norm" },
            { LLM_TENSOR_DEC_ATTN_NORM,        "dec.blk.%d.attn_norm" },
            { LLM_TENSOR_DEC_ATTN_Q,           "dec.blk.%d.attn_q" },
            { LLM_TENSOR_DEC_ATTN_K,           "dec.blk.%d.attn_k" },
            { LLM_TENSOR_DEC_ATTN_V,           "dec.blk.%d.attn_v" },
            { LLM_TENSOR_DEC_ATTN_OUT,         "dec.blk.%d.attn_o" },
            { LLM_TENSOR_DEC_ATTN_REL_B,       "dec.blk.%d.attn_rel_b" },
            { LLM_TENSOR_DEC_CROSS_ATTN_NORM,  "dec.blk.%d.cross_attn_norm" },
            { LLM_TENSOR_DEC_CROSS_ATTN_Q,     "dec.blk.%d.cross_attn_q" },
            { LLM_TENSOR_DEC_CROSS_ATTN_K,     "dec.blk.%d.cross_attn_k" },
            { LLM_TENSOR_DEC_CROSS_ATTN_V,     "dec.blk.%d.cross_attn_v" },
            { LLM_TENSOR_DEC_CROSS_ATTN_OUT,   "dec.blk.%d.cross_attn_o" },
            { LLM_TENSOR_DEC_CROSS_ATTN_REL_B, "dec.blk.%d.cross_attn_rel_b" },
            { LLM_TENSOR_DEC_FFN_NORM,         "dec.blk.%d.ffn_norm" },
            { LLM_TENSOR_DEC_FFN_GATE,         "dec.blk.%d.ffn_gate" },
            { LLM_TENSOR_DEC_FFN_DOWN,         "dec.blk.%d.ffn_down" },
            { LLM_TENSOR_DEC_FFN_UP,           "dec.blk.%d.ffn_up" },
            { LLM_TENSOR_ENC_OUTPUT_NORM,      "enc.output_norm" },
            { LLM_TENSOR_ENC_ATTN_NORM,        "enc.blk.%d.attn_norm" },
            { LLM_TENSOR_ENC_ATTN_Q,           "enc.blk.%d.attn_q" },
            { LLM_TENSOR_ENC_ATTN_K,           "enc.blk.%d.attn_k" },
            { LLM_TENSOR_ENC_ATTN_V,           "enc.blk.%d.attn_v" },
            { LLM_TENSOR_ENC_ATTN_OUT,         "enc.blk.%d.attn_o" },
            { LLM_TENSOR_ENC_ATTN_REL_B,       "enc.blk.%d.attn_rel_b" },
            { LLM_TENSOR_ENC_FFN_NORM,         "enc.blk.%d.ffn_norm" },
            { LLM_TENSOR_ENC_FFN_GATE,         "enc.blk.%d.ffn_gate" },
            { LLM_TENSOR_ENC_FFN_DOWN,         "enc.blk.%d.ffn_down" },
            { LLM_TENSOR_ENC_FFN_UP,           "enc.blk.%d.ffn_up" },
        },
    },
    {
        LLM_ARCH_T5ENCODER,
        {
            { LLM_TENSOR_TOKEN_EMBD,           "token_embd" },
            { LLM_TENSOR_OUTPUT,               "output" },
            { LLM_TENSOR_ENC_OUTPUT_NORM,      "enc.output_norm" },
            { LLM_TENSOR_ENC_ATTN_NORM,        "enc.blk.%d.attn_norm" },
            { LLM_TENSOR_ENC_ATTN_Q,           "enc.blk.%d.attn_q" },
            { LLM_TENSOR_ENC_ATTN_K,           "enc.blk.%d.attn_k" },
            { LLM_TENSOR_ENC_ATTN_V,           "enc.blk.%d.attn_v" },
            { LLM_TENSOR_ENC_ATTN_OUT,         "enc.blk.%d.attn_o" },
            { LLM_TENSOR_ENC_ATTN_REL_B,       "enc.blk.%d.attn_rel_b" },
            { LLM_TENSOR_ENC_FFN_NORM,         "enc.blk.%d.ffn_norm" },
            { LLM_TENSOR_ENC_FFN_GATE,         "enc.blk.%d.ffn_gate" },
            { LLM_TENSOR_ENC_FFN_DOWN,         "enc.blk.%d.ffn_down" },
            { LLM_TENSOR_ENC_FFN_UP,           "enc.blk.%d.ffn_up" },
        },
    },
    {
        LLM_ARCH_JAIS,
        {
            { LLM_TENSOR_TOKEN_EMBD,      "token_embd" },
            { LLM_TENSOR_OUTPUT_NORM,     "output_norm" },
            { LLM_TENSOR_OUTPUT,          "output" },
            { LLM_TENSOR_ATTN_NORM,       "blk.%d.attn_norm" },
            { LLM_TENSOR_ATTN_QKV,        "blk.%d.attn_qkv" },
            { LLM_TENSOR_ATTN_OUT,        "blk.%d.attn_output" },
            { LLM_TENSOR_FFN_NORM,        "blk.%d.ffn_norm" },
            { LLM_TENSOR_FFN_UP,          "blk.%d.ffn_up" },
            { LLM_TENSOR_FFN_GATE,        "blk.%d.ffn_gate" },
            { LLM_TENSOR_FFN_DOWN,        "blk.%d.ffn_down" },
        },
    },
    {
        LLM_ARCH_NEMOTRON,
        {
            { LLM_TENSOR_TOKEN_EMBD,      "token_embd" },
            { LLM_TENSOR_OUTPUT_NORM,     "output_norm" },
            { LLM_TENSOR_OUTPUT,          "output" },
            { LLM_TENSOR_ROPE_FREQS,      "rope_freqs" },
            { LLM_TENSOR_ATTN_NORM,       "blk.%d.attn_norm" },
            { LLM_TENSOR_ATTN_Q,          "blk.%d.attn_q" },
            { LLM_TENSOR_ATTN_K,          "blk.%d.attn_k" },
            { LLM_TENSOR_ATTN_V,          "blk.%d.attn_v" },
            { LLM_TENSOR_ATTN_OUT,        "blk.%d.attn_output" },
            { LLM_TENSOR_ATTN_ROT_EMBD,   "blk.%d.attn_rot_embd" },
            { LLM_TENSOR_FFN_NORM,        "blk.%d.ffn_norm" },
            { LLM_TENSOR_FFN_DOWN,        "blk.%d.ffn_down" },
            { LLM_TENSOR_FFN_UP,          "blk.%d.ffn_up" },
        },
    },
    {
        LLM_ARCH_EXAONE,
        {
            { LLM_TENSOR_TOKEN_EMBD,      "token_embd" },
            { LLM_TENSOR_OUTPUT_NORM,     "output_norm" },
            { LLM_TENSOR_OUTPUT,          "output" },
            { LLM_TENSOR_ROPE_FREQS,      "rope_freqs" },
            { LLM_TENSOR_ATTN_NORM,       "blk.%d.attn_norm" },
            { LLM_TENSOR_ATTN_Q,          "blk.%d.attn_q" },
            { LLM_TENSOR_ATTN_K,          "blk.%d.attn_k" },
            { LLM_TENSOR_ATTN_V,          "blk.%d.attn_v" },
            { LLM_TENSOR_ATTN_OUT,        "blk.%d.attn_output" },
            { LLM_TENSOR_ATTN_ROT_EMBD,   "blk.%d.attn_rot_embd" },
            { LLM_TENSOR_FFN_NORM,        "blk.%d.ffn_norm" },
            { LLM_TENSOR_FFN_GATE,        "blk.%d.ffn_gate" },
            { LLM_TENSOR_FFN_DOWN,        "blk.%d.ffn_down" },
            { LLM_TENSOR_FFN_UP,          "blk.%d.ffn_up" },
        },
    },
    {
        LLM_ARCH_RWKV6,
        {
            { LLM_TENSOR_TOKEN_EMBD,                "token_embd" },
            { LLM_TENSOR_TOKEN_EMBD_NORM,           "token_embd_norm" },
            { LLM_TENSOR_OUTPUT_NORM,               "output_norm" },
            { LLM_TENSOR_OUTPUT,                    "output" },
            { LLM_TENSOR_ATTN_NORM,                 "blk.%d.attn_norm" },
            { LLM_TENSOR_ATTN_NORM_2,               "blk.%d.attn_norm_2" },
            { LLM_TENSOR_TIME_MIX_W1,               "blk.%d.time_mix_w1" },
            { LLM_TENSOR_TIME_MIX_W2,               "blk.%d.time_mix_w2" },
            { LLM_TENSOR_TIME_MIX_LERP_X,           "blk.%d.time_mix_lerp_x" },
            { LLM_TENSOR_TIME_MIX_LERP_W,           "blk.%d.time_mix_lerp_w" },
            { LLM_TENSOR_TIME_MIX_LERP_K,           "blk.%d.time_mix_lerp_k" },
            { LLM_TENSOR_TIME_MIX_LERP_V,           "blk.%d.time_mix_lerp_v" },
            { LLM_TENSOR_TIME_MIX_LERP_R,           "blk.%d.time_mix_lerp_r" },
            { LLM_TENSOR_TIME_MIX_LERP_G,           "blk.%d.time_mix_lerp_g" },
            { LLM_TENSOR_TIME_MIX_LERP_FUSED,       "blk.%d.time_mix_lerp_fused" },
            { LLM_TENSOR_TIME_MIX_FIRST,            "blk.%d.time_mix_first" },
            { LLM_TENSOR_TIME_MIX_DECAY,            "blk.%d.time_mix_decay" },
            { LLM_TENSOR_TIME_MIX_DECAY_W1,         "blk.%d.time_mix_decay_w1" },
            { LLM_TENSOR_TIME_MIX_DECAY_W2,         "blk.%d.time_mix_decay_w2" },
            { LLM_TENSOR_TIME_MIX_KEY,              "blk.%d.time_mix_key" },
            { LLM_TENSOR_TIME_MIX_VALUE,            "blk.%d.time_mix_value" },
            { LLM_TENSOR_TIME_MIX_RECEPTANCE,       "blk.%d.time_mix_receptance" },
            { LLM_TENSOR_TIME_MIX_GATE,             "blk.%d.time_mix_gate" },
            { LLM_TENSOR_TIME_MIX_LN,               "blk.%d.time_mix_ln" },
            { LLM_TENSOR_TIME_MIX_OUTPUT,           "blk.%d.time_mix_output" },
            { LLM_TENSOR_CHANNEL_MIX_LERP_K,        "blk.%d.channel_mix_lerp_k" },
            { LLM_TENSOR_CHANNEL_MIX_LERP_R,        "blk.%d.channel_mix_lerp_r" },
            { LLM_TENSOR_CHANNEL_MIX_KEY,           "blk.%d.channel_mix_key" },
            { LLM_TENSOR_CHANNEL_MIX_VALUE,         "blk.%d.channel_mix_value" },
            { LLM_TENSOR_CHANNEL_MIX_RECEPTANCE,    "blk.%d.channel_mix_receptance" },
        },
    },
    {
        LLM_ARCH_RWKV6QWEN2,
        {
            { LLM_TENSOR_TOKEN_EMBD,                "token_embd" },
            { LLM_TENSOR_OUTPUT_NORM,               "output_norm" },
            { LLM_TENSOR_OUTPUT,                    "output" },
            { LLM_TENSOR_ATTN_NORM,                 "blk.%d.attn_norm" },
            { LLM_TENSOR_TIME_MIX_W1,               "blk.%d.time_mix_w1" },
            { LLM_TENSOR_TIME_MIX_W2,               "blk.%d.time_mix_w2" },
            { LLM_TENSOR_TIME_MIX_LERP_X,           "blk.%d.time_mix_lerp_x" },
            { LLM_TENSOR_TIME_MIX_LERP_FUSED,       "blk.%d.time_mix_lerp_fused" },
            { LLM_TENSOR_TIME_MIX_FIRST,            "blk.%d.time_mix_first" },
            { LLM_TENSOR_TIME_MIX_DECAY,            "blk.%d.time_mix_decay" },
            { LLM_TENSOR_TIME_MIX_DECAY_W1,         "blk.%d.time_mix_decay_w1" },
            { LLM_TENSOR_TIME_MIX_DECAY_W2,         "blk.%d.time_mix_decay_w2" },
            { LLM_TENSOR_TIME_MIX_KEY,              "blk.%d.time_mix_key" },
            { LLM_TENSOR_TIME_MIX_VALUE,            "blk.%d.time_mix_value" },
            { LLM_TENSOR_TIME_MIX_RECEPTANCE,       "blk.%d.time_mix_receptance" },
            { LLM_TENSOR_TIME_MIX_GATE,             "blk.%d.time_mix_gate" },
            { LLM_TENSOR_TIME_MIX_OUTPUT,           "blk.%d.time_mix_output" },
            { LLM_TENSOR_FFN_NORM,                  "blk.%d.ffn_norm" },
            { LLM_TENSOR_FFN_GATE,                  "blk.%d.ffn_gate" },
            { LLM_TENSOR_FFN_DOWN,                  "blk.%d.ffn_down" },
            { LLM_TENSOR_FFN_UP,                    "blk.%d.ffn_up" },
        },
    },
    {
        LLM_ARCH_GRANITE,
        {
            { LLM_TENSOR_TOKEN_EMBD,      "token_embd" },
            { LLM_TENSOR_OUTPUT_NORM,     "output_norm" },
            { LLM_TENSOR_OUTPUT,          "output" },
            { LLM_TENSOR_ATTN_NORM,       "blk.%d.attn_norm" },
            { LLM_TENSOR_ATTN_Q,          "blk.%d.attn_q" },
            { LLM_TENSOR_ATTN_K,          "blk.%d.attn_k" },
            { LLM_TENSOR_ATTN_V,          "blk.%d.attn_v" },
            { LLM_TENSOR_ATTN_OUT,        "blk.%d.attn_output" },
            { LLM_TENSOR_FFN_NORM,        "blk.%d.ffn_norm" },
            { LLM_TENSOR_FFN_GATE,        "blk.%d.ffn_gate" },
            { LLM_TENSOR_FFN_DOWN,        "blk.%d.ffn_down" },
            { LLM_TENSOR_FFN_UP,          "blk.%d.ffn_up" },
        },
    },
    {
        LLM_ARCH_GRANITE_MOE,
        {
            { LLM_TENSOR_TOKEN_EMBD,      "token_embd" },
            { LLM_TENSOR_OUTPUT_NORM,     "output_norm" },
            { LLM_TENSOR_OUTPUT,          "output" },
            { LLM_TENSOR_ATTN_NORM,       "blk.%d.attn_norm" },
            { LLM_TENSOR_ATTN_Q,          "blk.%d.attn_q" },
            { LLM_TENSOR_ATTN_K,          "blk.%d.attn_k" },
            { LLM_TENSOR_ATTN_V,          "blk.%d.attn_v" },
            { LLM_TENSOR_ATTN_OUT,        "blk.%d.attn_output" },
            { LLM_TENSOR_FFN_NORM,        "blk.%d.ffn_norm" },
            { LLM_TENSOR_FFN_GATE_INP,    "blk.%d.ffn_gate_inp" },
            { LLM_TENSOR_FFN_GATE_EXPS,   "blk.%d.ffn_gate_exps" },
            { LLM_TENSOR_FFN_DOWN_EXPS,   "blk.%d.ffn_down_exps" },
            { LLM_TENSOR_FFN_UP_EXPS,     "blk.%d.ffn_up_exps" },
        },
    },
    {
        LLM_ARCH_CHAMELEON,
        {
            { LLM_TENSOR_TOKEN_EMBD,      "token_embd" },
            { LLM_TENSOR_OUTPUT_NORM,     "output_norm" },
            { LLM_TENSOR_OUTPUT,          "output" },
            { LLM_TENSOR_ATTN_NORM,       "blk.%d.attn_norm" },
            { LLM_TENSOR_ATTN_Q,          "blk.%d.attn_q" },
            { LLM_TENSOR_ATTN_K,          "blk.%d.attn_k" },
            { LLM_TENSOR_ATTN_V,          "blk.%d.attn_v" },
            { LLM_TENSOR_ATTN_OUT,        "blk.%d.attn_output" },
            { LLM_TENSOR_FFN_NORM,        "blk.%d.ffn_norm" },
            { LLM_TENSOR_FFN_GATE,        "blk.%d.ffn_gate" },
            { LLM_TENSOR_FFN_DOWN,        "blk.%d.ffn_down" },
            { LLM_TENSOR_FFN_UP,          "blk.%d.ffn_up" },
            { LLM_TENSOR_ATTN_Q_NORM,     "blk.%d.attn_q_norm" },
            { LLM_TENSOR_ATTN_K_NORM,     "blk.%d.attn_k_norm" },
        },
    },
    {
        LLM_ARCH_WAVTOKENIZER_DEC,
        {
            { LLM_TENSOR_TOKEN_EMBD,        "token_embd" },
            { LLM_TENSOR_TOKEN_EMBD_NORM,   "token_embd_norm" },
            { LLM_TENSOR_CONV1D,            "conv1d" },
            { LLM_TENSOR_CONVNEXT_DW,       "convnext.%d.dw" },
            { LLM_TENSOR_CONVNEXT_NORM,     "convnext.%d.norm" },
            { LLM_TENSOR_CONVNEXT_PW1,      "convnext.%d.pw1" },
            { LLM_TENSOR_CONVNEXT_PW2,      "convnext.%d.pw2" },
            { LLM_TENSOR_CONVNEXT_GAMMA,    "convnext.%d.gamma" },
            { LLM_TENSOR_OUTPUT_NORM,       "output_norm" },
            { LLM_TENSOR_OUTPUT,            "output" },
            { LLM_TENSOR_POS_NET_CONV1,     "posnet.%d.conv1" },
            { LLM_TENSOR_POS_NET_CONV2,     "posnet.%d.conv2" },
            { LLM_TENSOR_POS_NET_NORM,      "posnet.%d.norm" },
            { LLM_TENSOR_POS_NET_NORM1,     "posnet.%d.norm1" },
            { LLM_TENSOR_POS_NET_NORM2,     "posnet.%d.norm2" },
            { LLM_TENSOR_POS_NET_ATTN_NORM, "posnet.%d.attn_norm" },
            { LLM_TENSOR_POS_NET_ATTN_Q,    "posnet.%d.attn_q" },
            { LLM_TENSOR_POS_NET_ATTN_K,    "posnet.%d.attn_k" },
            { LLM_TENSOR_POS_NET_ATTN_V,    "posnet.%d.attn_v" },
            { LLM_TENSOR_POS_NET_ATTN_OUT,  "posnet.%d.attn_output" },
        },
    },
    {
        LLM_ARCH_UNKNOWN,
        {
            { LLM_TENSOR_TOKEN_EMBD,      "token_embd" },
        },
    },
};

static const std::map<llm_tensor, llm_tensor_info> LLM_TENSOR_INFOS = {
    {LLM_TENSOR_TOKEN_EMBD,                 {LLM_TENSOR_LAYER_INPUT, GGML_OP_GET_ROWS}},
    {LLM_TENSOR_POS_EMBD,                   {LLM_TENSOR_LAYER_INPUT, GGML_OP_GET_ROWS}},
    {LLM_TENSOR_TOKEN_EMBD_NORM,            {LLM_TENSOR_LAYER_INPUT, GGML_OP_GET_ROWS}},
    {LLM_TENSOR_TOKEN_TYPES,                {LLM_TENSOR_LAYER_INPUT, GGML_OP_GET_ROWS}},
    {LLM_TENSOR_OUTPUT,                     {LLM_TENSOR_LAYER_OUTPUT, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_CLS,                        {LLM_TENSOR_LAYER_OUTPUT, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_CLS_OUT,                    {LLM_TENSOR_LAYER_OUTPUT, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_OUTPUT_NORM,                {LLM_TENSOR_LAYER_OUTPUT, GGML_OP_MUL}},
    {LLM_TENSOR_DEC_OUTPUT_NORM,            {LLM_TENSOR_LAYER_OUTPUT, GGML_OP_MUL}},
    {LLM_TENSOR_ENC_OUTPUT_NORM,            {LLM_TENSOR_LAYER_OUTPUT, GGML_OP_MUL}},
    {LLM_TENSOR_ROPE_FREQS,                 {LLM_TENSOR_LAYER_REPEATING, GGML_OP_ROPE}},
    {LLM_TENSOR_ROPE_FACTORS_LONG,          {LLM_TENSOR_LAYER_REPEATING, GGML_OP_ROPE}},
    {LLM_TENSOR_ROPE_FACTORS_SHORT,         {LLM_TENSOR_LAYER_REPEATING, GGML_OP_ROPE}},
    {LLM_TENSOR_ATTN_Q,                     {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_ATTN_K,                     {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_ATTN_V,                     {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_ATTN_QKV,                   {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_ATTN_OUT,                   {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_FFN_GATE,                   {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_FFN_DOWN,                   {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_FFN_UP,                     {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_FFN_DOWN_SHEXP,             {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_FFN_GATE_SHEXP,             {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_FFN_UP_SHEXP,               {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_ATTN_Q_A,                   {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_ATTN_Q_B,                   {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_ATTN_KV_A_MQA,              {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_ATTN_KV_B,                  {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_DEC_ATTN_Q,                 {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_DEC_ATTN_K,                 {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_ATTN_Q,                     {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_ATTN_K,                     {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_ATTN_V,                     {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_ATTN_QKV,                   {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_ATTN_OUT,                   {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_FFN_GATE,                   {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_FFN_DOWN,                   {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_FFN_UP,                     {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_FFN_DOWN_SHEXP,             {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_FFN_GATE_SHEXP,             {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_FFN_UP_SHEXP,               {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_ATTN_Q_A,                   {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_ATTN_Q_B,                   {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_ATTN_KV_A_MQA,              {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_ATTN_KV_B,                  {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_DEC_ATTN_Q,                 {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_DEC_ATTN_K,                 {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_DEC_ATTN_V,                 {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_DEC_ATTN_OUT,               {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_DEC_CROSS_ATTN_Q,           {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_DEC_CROSS_ATTN_K,           {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_DEC_CROSS_ATTN_V,           {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_DEC_CROSS_ATTN_OUT,         {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_DEC_FFN_GATE,               {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_DEC_FFN_DOWN,               {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_DEC_FFN_UP,                 {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_ENC_ATTN_Q,                 {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_ENC_ATTN_K,                 {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_ENC_ATTN_V,                 {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_ENC_ATTN_OUT,               {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_ENC_FFN_GATE,               {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_ENC_FFN_DOWN,               {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_ENC_FFN_UP,                 {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_FFN_GATE_INP_SHEXP,         {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_FFN_GATE_INP,               {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_SSM_IN,                     {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_SSM_X,                      {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_SSM_DT,                     {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_SSM_OUT,                    {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_TIME_MIX_W1,                {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_TIME_MIX_W2,                {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_TIME_MIX_DECAY_W1,          {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_TIME_MIX_DECAY_W2,          {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_TIME_MIX_KEY,               {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_TIME_MIX_VALUE,             {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_TIME_MIX_RECEPTANCE,        {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_TIME_MIX_GATE,              {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_TIME_MIX_OUTPUT,            {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_CHANNEL_MIX_KEY,            {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_CHANNEL_MIX_RECEPTANCE,     {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_CHANNEL_MIX_VALUE,          {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_FFN_ACT,                    {LLM_TENSOR_LAYER_REPEATING, GGML_OP_DIV}},
    {LLM_TENSOR_SSM_CONV1D,                 {LLM_TENSOR_LAYER_REPEATING, GGML_OP_SSM_CONV}},
    {LLM_TENSOR_SSM_A,                      {LLM_TENSOR_LAYER_REPEATING, GGML_OP_SSM_SCAN}},
    {LLM_TENSOR_SSM_D,                      {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL}},
    {LLM_TENSOR_TIME_MIX_LERP_X,            {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL}},
    {LLM_TENSOR_TIME_MIX_LN,                {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL}},
    {LLM_TENSOR_CHANNEL_MIX_LERP_K,         {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL}},
    {LLM_TENSOR_CHANNEL_MIX_LERP_R,         {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL}},
    {LLM_TENSOR_TIME_MIX_LERP_W,            {LLM_TENSOR_LAYER_REPEATING, GGML_OP_ADD}},
    {LLM_TENSOR_TIME_MIX_LERP_K,            {LLM_TENSOR_LAYER_REPEATING, GGML_OP_ADD}},
    {LLM_TENSOR_TIME_MIX_LERP_V,            {LLM_TENSOR_LAYER_REPEATING, GGML_OP_ADD}},
    {LLM_TENSOR_TIME_MIX_LERP_R,            {LLM_TENSOR_LAYER_REPEATING, GGML_OP_ADD}},
    {LLM_TENSOR_TIME_MIX_LERP_G,            {LLM_TENSOR_LAYER_REPEATING, GGML_OP_ADD}},
    {LLM_TENSOR_TIME_MIX_LERP_FUSED,        {LLM_TENSOR_LAYER_REPEATING, GGML_OP_ADD}},
    {LLM_TENSOR_TIME_MIX_DECAY,             {LLM_TENSOR_LAYER_REPEATING, GGML_OP_ADD}},
    {LLM_TENSOR_TIME_MIX_FIRST,             {LLM_TENSOR_LAYER_REPEATING, GGML_OP_RWKV_WKV6}},
    {LLM_TENSOR_ATTN_NORM,                  {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL}},
    {LLM_TENSOR_ATTN_NORM_2,                {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL}},
    {LLM_TENSOR_ATTN_OUT_NORM,              {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL}},
    {LLM_TENSOR_ATTN_POST_NORM,             {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL}},
    {LLM_TENSOR_FFN_NORM,                   {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL}},
    {LLM_TENSOR_FFN_POST_NORM,              {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL}},
    {LLM_TENSOR_FFN_NORM_EXPS,              {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL}},
    {LLM_TENSOR_ATTN_Q_NORM,                {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL}},
    {LLM_TENSOR_ATTN_K_NORM,                {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL}},
    {LLM_TENSOR_LAYER_OUT_NORM,             {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL}},
    {LLM_TENSOR_ATTN_Q_A_NORM,              {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL}},
    {LLM_TENSOR_ATTN_KV_A_NORM,             {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL}},
    {LLM_TENSOR_ATTN_SUB_NORM,              {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL}},
    {LLM_TENSOR_FFN_SUB_NORM,               {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL}},
    {LLM_TENSOR_DEC_ATTN_NORM,              {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL}},
    {LLM_TENSOR_DEC_CROSS_ATTN_NORM,        {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL}},
    {LLM_TENSOR_DEC_FFN_NORM,               {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL}},
    {LLM_TENSOR_ENC_ATTN_NORM,              {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL}},
    {LLM_TENSOR_ENC_FFN_NORM,               {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL}},
    {LLM_TENSOR_DEC_ATTN_REL_B,             {LLM_TENSOR_LAYER_REPEATING, GGML_OP_GET_ROWS}},
    {LLM_TENSOR_ENC_ATTN_REL_B,             {LLM_TENSOR_LAYER_REPEATING, GGML_OP_GET_ROWS}},
    {LLM_TENSOR_FFN_DOWN_EXPS,              {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT_ID}},
    {LLM_TENSOR_FFN_GATE_EXPS,              {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT_ID}},
    {LLM_TENSOR_FFN_UP_EXPS,                {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT_ID}},
    {LLM_TENSOR_FFN_EXP_PROBS_B,            {LLM_TENSOR_LAYER_REPEATING, GGML_OP_ADD}},
    // this tensor is loaded for T5, but never used
    {LLM_TENSOR_DEC_CROSS_ATTN_REL_B,       {LLM_TENSOR_LAYER_REPEATING, GGML_OP_NONE}},
    {LLM_TENSOR_CONV1D,                     {LLM_TENSOR_LAYER_INPUT,     GGML_OP_IM2COL}},
    {LLM_TENSOR_POS_NET_NORM,               {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL}},
    {LLM_TENSOR_POS_NET_NORM1,              {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL}},
    {LLM_TENSOR_POS_NET_NORM2,              {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL}},
    {LLM_TENSOR_POS_NET_CONV1,              {LLM_TENSOR_LAYER_REPEATING, GGML_OP_IM2COL}},
    {LLM_TENSOR_POS_NET_CONV2,              {LLM_TENSOR_LAYER_REPEATING, GGML_OP_IM2COL}},
    {LLM_TENSOR_POS_NET_ATTN_NORM,          {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL}},
    {LLM_TENSOR_POS_NET_ATTN_Q,             {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_POS_NET_ATTN_K,             {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_POS_NET_ATTN_V,             {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_POS_NET_ATTN_OUT,           {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_CONVNEXT_DW,                {LLM_TENSOR_LAYER_REPEATING, GGML_OP_IM2COL}},
    {LLM_TENSOR_CONVNEXT_NORM,              {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL}},
    {LLM_TENSOR_CONVNEXT_PW1,               {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_CONVNEXT_PW2,               {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
    {LLM_TENSOR_CONVNEXT_GAMMA,             {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL}},
};

LLM_KV::LLM_KV(llm_arch arch) : arch(arch) {}

std::string LLM_KV::operator()(llm_kv kv) const {
    return ::format(LLM_KV_NAMES.at(kv), LLM_ARCH_NAMES.at(arch));
}

std::string LLM_TN_IMPL::str() const {
    if (LLM_TENSOR_NAMES.at(arch).find(tensor) == LLM_TENSOR_NAMES.at(arch).end()) {
        return "__missing__";
    }

    std::string name = ::format(LLM_TENSOR_NAMES.at(arch).at(tensor), bid, xid);

    if (suffix != nullptr) {
        name += ".";
        name += suffix;
    }

    return name;
}

const char * llm_arch_name(llm_arch arch) {
    auto it = LLM_ARCH_NAMES.find(arch);
    if (it == LLM_ARCH_NAMES.end()) {
        return "unknown";
    }
    return it->second;
}

llm_arch llm_arch_from_string(const std::string & name) {
    for (const auto & kv : LLM_ARCH_NAMES) { // NOLINT
        if (kv.second == name) {
            return kv.first;
        }
    }

    return LLM_ARCH_UNKNOWN;
}

const llm_tensor_info & llm_tensor_info_for(llm_tensor tensor) {
    return LLM_TENSOR_INFOS.at(tensor);
}