llama.cpp LLM_ARCH_DEEPSEEK and LLM_ARCH_DEEPSEEK2
llama.cpp LLM_ARCH_DEEPSEEK and LLM_ARCH_DEEPSEEK2
- 1. `LLM_ARCH_DEEPSEEK` and `LLM_ARCH_DEEPSEEK2`
- 2. `LLM_ARCH_DEEPSEEK` and `LLM_ARCH_DEEPSEEK2`
- 3. `struct ggml_cgraph * build_deepseek()` and `struct ggml_cgraph * build_deepseek2()`
- References
不宜吹捧中国大语言模型的同时，又去贬低美国大语言模型。
水是人体的主要化学成分，约占体重的 50% 至 70%。大语言模型的含水量也不会太少。
llama.cpp
https://github.com/ggerganov/llama.cpp
1. LLM_ARCH_DEEPSEEK and LLM_ARCH_DEEPSEEK2
/home/yongqiang/llm_work/llama_cpp_25_01_05/llama.cpp/src/llama-arch.h
/home/yongqiang/llm_work/llama_cpp_25_01_05/llama.cpp/src/llama-arch.cpp
LLM_ARCH_DEEPSEEKandLLM_ARCH_DEEPSEEK2
//
// gguf constants (sync with gguf.py)
//enum llm_arch {LLM_ARCH_LLAMA,LLM_ARCH_DECI,LLM_ARCH_FALCON,LLM_ARCH_BAICHUAN,LLM_ARCH_GROK,LLM_ARCH_GPT2,LLM_ARCH_GPTJ,LLM_ARCH_GPTNEOX,LLM_ARCH_MPT,LLM_ARCH_STARCODER,LLM_ARCH_REFACT,LLM_ARCH_BERT,LLM_ARCH_NOMIC_BERT,LLM_ARCH_JINA_BERT_V2,LLM_ARCH_BLOOM,LLM_ARCH_STABLELM,LLM_ARCH_QWEN,LLM_ARCH_QWEN2,LLM_ARCH_QWEN2MOE,LLM_ARCH_QWEN2VL,LLM_ARCH_PHI2,LLM_ARCH_PHI3,LLM_ARCH_PHIMOE,LLM_ARCH_PLAMO,LLM_ARCH_CODESHELL,LLM_ARCH_ORION,LLM_ARCH_INTERNLM2,LLM_ARCH_MINICPM,LLM_ARCH_MINICPM3,LLM_ARCH_GEMMA,LLM_ARCH_GEMMA2,LLM_ARCH_STARCODER2,LLM_ARCH_MAMBA,LLM_ARCH_XVERSE,LLM_ARCH_COMMAND_R,LLM_ARCH_COHERE2,LLM_ARCH_DBRX,LLM_ARCH_OLMO,LLM_ARCH_OLMO2,LLM_ARCH_OLMOE,LLM_ARCH_OPENELM,LLM_ARCH_ARCTIC,LLM_ARCH_DEEPSEEK,LLM_ARCH_DEEPSEEK2,LLM_ARCH_CHATGLM,LLM_ARCH_BITNET,LLM_ARCH_T5,LLM_ARCH_T5ENCODER,LLM_ARCH_JAIS,LLM_ARCH_NEMOTRON,LLM_ARCH_EXAONE,LLM_ARCH_RWKV6,LLM_ARCH_RWKV6QWEN2,LLM_ARCH_GRANITE,LLM_ARCH_GRANITE_MOE,LLM_ARCH_CHAMELEON,LLM_ARCH_WAVTOKENIZER_DEC,LLM_ARCH_UNKNOWN,
};
{ LLM_ARCH_DEEPSEEK, "deepseek" }and{ LLM_ARCH_DEEPSEEK2, "deepseek2" }
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)" },
};
2. LLM_ARCH_DEEPSEEK and LLM_ARCH_DEEPSEEK2
/home/yongqiang/llm_work/llama_cpp_25_01_05/llama.cpp/src/llama-arch.cpp
LLM_ARCH_DEEPSEEKandLLM_ARCH_DEEPSEEK2
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" },},},
};
3. struct ggml_cgraph * build_deepseek() and struct ggml_cgraph * build_deepseek2()
/home/yongqiang/llm_work/llama_cpp_25_01_05/llama.cpp/src/llama.cpp
struct ggml_cgraph * build_deepseek()
struct ggml_cgraph * build_deepseek() {struct ggml_cgraph * gf = ggml_new_graph_custom(ctx0, model.max_nodes(), false);// mutable variable, needed during the last layer of the computation to skip unused tokensint32_t n_tokens = this->n_tokens;const int64_t n_embd_head = hparams.n_embd_head_v;GGML_ASSERT(n_embd_head == hparams.n_embd_head_k);GGML_ASSERT(n_embd_head == hparams.n_rot);struct ggml_tensor * cur;struct ggml_tensor * inpL;inpL = llm_build_inp_embd(ctx0, lctx, hparams, ubatch, model.tok_embd, cb);// inp_pos - contains the positionsstruct ggml_tensor * inp_pos = build_inp_pos();// KQ_mask (mask for 1 head, it will be broadcasted to all heads)struct ggml_tensor * KQ_mask = build_inp_KQ_mask();const float kq_scale = hparams.f_attention_scale == 0.0f ? 1.0f/sqrtf(float(n_embd_head)) : hparams.f_attention_scale;for (int il = 0; il < n_layer; ++il) {struct ggml_tensor * inpSA = inpL;// normcur = llm_build_norm(ctx0, inpL, hparams,model.layers[il].attn_norm, NULL,LLM_NORM_RMS, cb, il);cb(cur, "attn_norm", il);// self-attention{// rope freq factors for llama3; may return nullptr for llama2 and other modelsstruct ggml_tensor * rope_factors = build_rope_factors(il);// compute Q and K and RoPE themstruct ggml_tensor * Qcur = llm_build_lora_mm(lctx, ctx0, model.layers[il].wq, cur);cb(Qcur, "Qcur", il);if (model.layers[il].bq) {Qcur = ggml_add(ctx0, Qcur, model.layers[il].bq);cb(Qcur, "Qcur", il);}struct ggml_tensor * Kcur = llm_build_lora_mm(lctx, ctx0, model.layers[il].wk, cur);cb(Kcur, "Kcur", il);if (model.layers[il].bk) {Kcur = ggml_add(ctx0, Kcur, model.layers[il].bk);cb(Kcur, "Kcur", il);}struct ggml_tensor * Vcur = llm_build_lora_mm(lctx, ctx0, model.layers[il].wv, cur);cb(Vcur, "Vcur", il);if (model.layers[il].bv) {Vcur = ggml_add(ctx0, Vcur, model.layers[il].bv);cb(Vcur, "Vcur", il);}Qcur = ggml_rope_ext(ctx0, ggml_reshape_3d(ctx0, Qcur, n_embd_head, n_head, n_tokens), inp_pos, rope_factors,n_rot, rope_type, n_ctx_orig, freq_base, freq_scale,ext_factor, attn_factor, beta_fast, beta_slow);cb(Qcur, "Qcur", il);Kcur = ggml_rope_ext(ctx0, ggml_reshape_3d(ctx0, Kcur, n_embd_head, n_head_kv, n_tokens), inp_pos, rope_factors,n_rot, rope_type, n_ctx_orig, freq_base, freq_scale,ext_factor, attn_factor, beta_fast, beta_slow);cb(Kcur, "Kcur", il);cur = llm_build_kv(ctx0, lctx, kv_self, gf,model.layers[il].wo, model.layers[il].bo,Kcur, Vcur, Qcur, KQ_mask, n_tokens, kv_head, n_kv, kq_scale, cb, il);}if (il == n_layer - 1) {// skip computing output for unused tokensstruct ggml_tensor * inp_out_ids = build_inp_out_ids();n_tokens = n_outputs;cur = ggml_get_rows(ctx0, cur, inp_out_ids);inpSA = ggml_get_rows(ctx0, inpSA, inp_out_ids);}struct ggml_tensor * ffn_inp = ggml_add(ctx0, cur, inpSA);cb(ffn_inp, "ffn_inp", il);cur = llm_build_norm(ctx0, ffn_inp, hparams,model.layers[il].ffn_norm, NULL,LLM_NORM_RMS, cb, il);cb(cur, "ffn_norm", il);if ((uint32_t) il < hparams.n_layer_dense_lead) {cur = llm_build_ffn(ctx0, lctx, cur,model.layers[il].ffn_up, NULL, NULL,model.layers[il].ffn_gate, NULL, NULL,model.layers[il].ffn_down, NULL, NULL,NULL,LLM_FFN_SILU, LLM_FFN_PAR, cb, il);cb(cur, "ffn_out", il);} else {// MoE branchggml_tensor * moe_out =llm_build_moe_ffn(ctx0, lctx, cur,model.layers[il].ffn_gate_inp,model.layers[il].ffn_up_exps,model.layers[il].ffn_gate_exps,model.layers[il].ffn_down_exps,nullptr,n_expert, n_expert_used,LLM_FFN_SILU, false,false, hparams.expert_weights_scale,LLAMA_EXPERT_GATING_FUNC_TYPE_SOFTMAX,cb, il);cb(moe_out, "ffn_moe_out", il);// FFN shared expert{ggml_tensor * ffn_shexp = llm_build_ffn(ctx0, lctx, cur,model.layers[il].ffn_up_shexp, NULL, NULL,model.layers[il].ffn_gate_shexp, NULL, NULL,model.layers[il].ffn_down_shexp, NULL, NULL,NULL,LLM_FFN_SILU, LLM_FFN_PAR, cb, il);cb(ffn_shexp, "ffn_shexp", il);cur = ggml_add(ctx0, moe_out, ffn_shexp);cb(cur, "ffn_out", il);}}cur = ggml_add(ctx0, cur, ffn_inp);cur = lctx.cvec.apply_to(ctx0, cur, il);cb(cur, "l_out", il);// input for next layerinpL = cur;}cur = inpL;cur = llm_build_norm(ctx0, cur, hparams,model.output_norm, NULL,LLM_NORM_RMS, cb, -1);cb(cur, "result_norm", -1);// lm_headcur = llm_build_lora_mm(lctx, ctx0, model.output, cur);cb(cur, "result_output", -1);ggml_build_forward_expand(gf, cur);return gf;}
struct ggml_cgraph * build_deepseek2()
struct ggml_cgraph * build_deepseek2() {struct ggml_cgraph * gf = ggml_new_graph_custom(ctx0, model.max_nodes(), false);// mutable variable, needed during the last layer of the computation to skip unused tokensint32_t n_tokens = this->n_tokens;bool is_lite = (hparams.n_layer == 27);// We have to pre-scale kq_scale and attn_factor to make the YaRN RoPE work correctly.// See https://github.com/ggerganov/llama.cpp/discussions/7416 for detailed explanation.const float mscale = attn_factor * (1.0f + hparams.rope_yarn_log_mul * logf(1.0f / freq_scale));const float kq_scale = 1.0f*mscale*mscale/sqrtf(float(hparams.n_embd_head_k));const float attn_factor_scaled = 1.0f / (1.0f + 0.1f * logf(1.0f / freq_scale));const uint32_t n_embd_head_qk_rope = hparams.n_rot;const uint32_t n_embd_head_qk_nope = hparams.n_embd_head_k - hparams.n_rot;const uint32_t kv_lora_rank = hparams.n_lora_kv;struct ggml_tensor * cur;struct ggml_tensor * inpL;// {n_embd, n_tokens}inpL = llm_build_inp_embd(ctx0, lctx, hparams, ubatch, model.tok_embd, cb);// inp_pos - contains the positionsstruct ggml_tensor * inp_pos = build_inp_pos();// KQ_mask (mask for 1 head, it will be broadcasted to all heads)struct ggml_tensor * KQ_mask = build_inp_KQ_mask();for (int il = 0; il < n_layer; ++il) {struct ggml_tensor * inpSA = inpL;// normcur = llm_build_norm(ctx0, inpL, hparams,model.layers[il].attn_norm, NULL,LLM_NORM_RMS, cb, il);cb(cur, "attn_norm", il);// self_attention{struct ggml_tensor * q = NULL;if (!is_lite) {// {n_embd, q_lora_rank} * {n_embd, n_tokens} -> {q_lora_rank, n_tokens}q = ggml_mul_mat(ctx0, model.layers[il].wq_a, cur);cb(q, "q", il);q = llm_build_norm(ctx0, q, hparams,model.layers[il].attn_q_a_norm, NULL,LLM_NORM_RMS, cb, il);cb(q, "q", il);// {q_lora_rank, n_head * hparams.n_embd_head_k} * {q_lora_rank, n_tokens} -> {n_head * hparams.n_embd_head_k, n_tokens}q = ggml_mul_mat(ctx0, model.layers[il].wq_b, q);cb(q, "q", il);} else {q = ggml_mul_mat(ctx0, model.layers[il].wq, cur);cb(q, "q", il);}// split into {n_head * n_embd_head_qk_nope, n_tokens}struct ggml_tensor * q_nope = ggml_view_3d(ctx0, q, n_embd_head_qk_nope, n_head, n_tokens,ggml_row_size(q->type, hparams.n_embd_head_k),ggml_row_size(q->type, hparams.n_embd_head_k * n_head),0);cb(q_nope, "q_nope", il);// and {n_head * n_embd_head_qk_rope, n_tokens}struct ggml_tensor * q_pe = ggml_view_3d(ctx0, q, n_embd_head_qk_rope, n_head, n_tokens,ggml_row_size(q->type, hparams.n_embd_head_k),ggml_row_size(q->type, hparams.n_embd_head_k * n_head),ggml_row_size(q->type, n_embd_head_qk_nope));cb(q_pe, "q_pe", il);// {n_embd, kv_lora_rank + n_embd_head_qk_rope} * {n_embd, n_tokens} -> {kv_lora_rank + n_embd_head_qk_rope, n_tokens}struct ggml_tensor * kv_pe_compresseed = ggml_mul_mat(ctx0, model.layers[il].wkv_a_mqa, cur);cb(kv_pe_compresseed, "kv_pe_compresseed", il);// split into {kv_lora_rank, n_tokens}struct ggml_tensor * kv_compressed = ggml_view_2d(ctx0, kv_pe_compresseed, kv_lora_rank, n_tokens,kv_pe_compresseed->nb[1],0);cb(kv_compressed, "kv_compressed", il);// and {n_embd_head_qk_rope, n_tokens}struct ggml_tensor * k_pe = ggml_view_3d(ctx0, kv_pe_compresseed, n_embd_head_qk_rope, 1, n_tokens,kv_pe_compresseed->nb[1],kv_pe_compresseed->nb[1],ggml_row_size(kv_pe_compresseed->type, kv_lora_rank));cb(k_pe, "k_pe", il);kv_compressed = ggml_cont(ctx0, kv_compressed); // TODO: the CUDA backend does not support non-contiguous normkv_compressed = llm_build_norm(ctx0, kv_compressed, hparams,model.layers[il].attn_kv_a_norm, NULL,LLM_NORM_RMS, cb, il);cb(kv_compressed, "kv_compressed", il);// {kv_lora_rank, n_head * (n_embd_head_qk_nope + n_embd_head_v)} * {kv_lora_rank, n_tokens} -> {n_head * (n_embd_head_qk_nope + n_embd_head_v), n_tokens}struct ggml_tensor * kv = ggml_mul_mat(ctx0, model.layers[il].wkv_b, kv_compressed);cb(kv, "kv", il);// split into {n_head * n_embd_head_qk_nope, n_tokens}struct ggml_tensor * k_nope = ggml_view_3d(ctx0, kv, n_embd_head_qk_nope, n_head, n_tokens,ggml_row_size(kv->type, n_embd_head_qk_nope + hparams.n_embd_head_v),ggml_row_size(kv->type, n_head * (n_embd_head_qk_nope + hparams.n_embd_head_v)),0);cb(k_nope, "k_nope", il);// and {n_head * n_embd_head_v, n_tokens}struct ggml_tensor * v_states = ggml_view_3d(ctx0, kv, hparams.n_embd_head_v, n_head, n_tokens,ggml_row_size(kv->type, (n_embd_head_qk_nope + hparams.n_embd_head_v)),ggml_row_size(kv->type, (n_embd_head_qk_nope + hparams.n_embd_head_v)*n_head),ggml_row_size(kv->type, (n_embd_head_qk_nope)));cb(v_states, "v_states", il);v_states = ggml_cont(ctx0, v_states);cb(v_states, "v_states", il);v_states = ggml_view_2d(ctx0, v_states, hparams.n_embd_head_v * n_head, n_tokens,ggml_row_size(kv->type, hparams.n_embd_head_v * n_head),0);cb(v_states, "v_states", il);q_pe = ggml_cont(ctx0, q_pe); // TODO: the CUDA backend used to not support non-cont. RoPE, investigate removing thisq_pe = ggml_rope_ext(ctx0, q_pe, inp_pos, nullptr,n_rot, rope_type, n_ctx_orig, freq_base, freq_scale,ext_factor, attn_factor_scaled, beta_fast, beta_slow);cb(q_pe, "q_pe", il);// shared RoPE keyk_pe = ggml_cont(ctx0, k_pe); // TODO: the CUDA backend used to not support non-cont. RoPE, investigate removing thisk_pe = ggml_rope_ext(ctx0, k_pe, inp_pos, nullptr,n_rot, rope_type, n_ctx_orig, freq_base, freq_scale,ext_factor, attn_factor_scaled, beta_fast, beta_slow);cb(k_pe, "k_pe", il);struct ggml_tensor * q_states = ggml_concat(ctx0, q_nope, q_pe, 0);cb(q_states, "q_states", il);struct ggml_tensor * k_states = ggml_concat(ctx0, k_nope, ggml_repeat(ctx0, k_pe, q_pe), 0);cb(k_states, "k_states", il);cur = llm_build_kv(ctx0, lctx, kv_self, gf,model.layers[il].wo, NULL,k_states, v_states, q_states, KQ_mask, n_tokens, kv_head, n_kv, kq_scale, cb, il);}if (il == n_layer - 1) {// skip computing output for unused tokensstruct ggml_tensor * inp_out_ids = build_inp_out_ids();n_tokens = n_outputs;cur = ggml_get_rows(ctx0, cur, inp_out_ids);inpSA = ggml_get_rows(ctx0, inpSA, inp_out_ids);}struct ggml_tensor * ffn_inp = ggml_add(ctx0, cur, inpSA);cb(ffn_inp, "ffn_inp", il);cur = llm_build_norm(ctx0, ffn_inp, hparams,model.layers[il].ffn_norm, NULL,LLM_NORM_RMS, cb, il);cb(cur, "ffn_norm", il);if ((uint32_t) il < hparams.n_layer_dense_lead) {cur = llm_build_ffn(ctx0, lctx, cur,model.layers[il].ffn_up, NULL, NULL,model.layers[il].ffn_gate, NULL, NULL,model.layers[il].ffn_down, NULL, NULL,NULL,LLM_FFN_SILU, LLM_FFN_PAR, cb, il);cb(cur, "ffn_out", il);} else {// MoE branchggml_tensor * moe_out =llm_build_moe_ffn(ctx0, lctx, cur,model.layers[il].ffn_gate_inp,model.layers[il].ffn_up_exps,model.layers[il].ffn_gate_exps,model.layers[il].ffn_down_exps,model.layers[il].ffn_exp_probs_b,n_expert, n_expert_used,LLM_FFN_SILU, hparams.expert_weights_norm,true, hparams.expert_weights_scale,(enum llama_expert_gating_func_type) hparams.expert_gating_func,cb, il);cb(moe_out, "ffn_moe_out", il);// FFN shared expert{ggml_tensor * ffn_shexp = llm_build_ffn(ctx0, lctx, cur,model.layers[il].ffn_up_shexp, NULL, NULL,model.layers[il].ffn_gate_shexp, NULL, NULL,model.layers[il].ffn_down_shexp, NULL, NULL,NULL,LLM_FFN_SILU, LLM_FFN_PAR, cb, il);cb(ffn_shexp, "ffn_shexp", il);cur = ggml_add(ctx0, moe_out, ffn_shexp);cb(cur, "ffn_out", il);}}cur = ggml_add(ctx0, cur, ffn_inp);cur = lctx.cvec.apply_to(ctx0, cur, il);cb(cur, "l_out", il);// input for next layerinpL = cur;}cur = inpL;cur = llm_build_norm(ctx0, cur, hparams,model.output_norm, NULL,LLM_NORM_RMS, cb, -1);cb(cur, "result_norm", -1);// lm_headcur = ggml_mul_mat(ctx0, model.output, cur);cb(cur, "result_output", -1);ggml_build_forward_expand(gf, cur);return gf;}
case LLM_ARCH_DEEPSEEK:andcase LLM_ARCH_DEEPSEEK2:
switch (model.arch) {case LLM_ARCH_LLAMA:case LLM_ARCH_MINICPM:case LLM_ARCH_GRANITE:case LLM_ARCH_GRANITE_MOE:{result = llm.build_llama();} break;case LLM_ARCH_DECI:{result = llm.build_deci();} break;case LLM_ARCH_BAICHUAN:{result = llm.build_baichuan();} break;case LLM_ARCH_FALCON:{result = llm.build_falcon();} break;case LLM_ARCH_GROK:{result = llm.build_grok();} break;case LLM_ARCH_STARCODER:{result = llm.build_starcoder();} break;case LLM_ARCH_REFACT:{result = llm.build_refact();} break;case LLM_ARCH_BERT:case LLM_ARCH_JINA_BERT_V2:case LLM_ARCH_NOMIC_BERT:{result = llm.build_bert();} break;case LLM_ARCH_BLOOM:{result = llm.build_bloom();} break;case LLM_ARCH_MPT:{result = llm.build_mpt();} break;case LLM_ARCH_STABLELM:{result = llm.build_stablelm();} break;case LLM_ARCH_QWEN:{result = llm.build_qwen();} break;case LLM_ARCH_QWEN2:{result = llm.build_qwen2();} break;case LLM_ARCH_QWEN2VL:{lctx.n_pos_per_token = 4;result = llm.build_qwen2vl();} break;case LLM_ARCH_QWEN2MOE:{result = llm.build_qwen2moe();} break;case LLM_ARCH_PHI2:{result = llm.build_phi2();} break;case LLM_ARCH_PHI3:case LLM_ARCH_PHIMOE:{result = llm.build_phi3();} break;case LLM_ARCH_PLAMO:{result = llm.build_plamo();} break;case LLM_ARCH_GPT2:{result = llm.build_gpt2();} break;case LLM_ARCH_CODESHELL:{result = llm.build_codeshell();} break;case LLM_ARCH_ORION:{result = llm.build_orion();} break;case LLM_ARCH_INTERNLM2:{result = llm.build_internlm2();} break;case LLM_ARCH_MINICPM3:{result = llm.build_minicpm3();} break;case LLM_ARCH_GEMMA:{result = llm.build_gemma();} break;case LLM_ARCH_GEMMA2:{result = llm.build_gemma2();} break;case LLM_ARCH_STARCODER2:{result = llm.build_starcoder2();} break;case LLM_ARCH_MAMBA:{result = llm.build_mamba();} break;case LLM_ARCH_XVERSE:{result = llm.build_xverse();} break;case LLM_ARCH_COMMAND_R:{result = llm.build_command_r();} break;case LLM_ARCH_COHERE2:{result = llm.build_cohere2();} break;case LLM_ARCH_DBRX:{result = llm.build_dbrx();} break;case LLM_ARCH_OLMO:{result = llm.build_olmo();} break;case LLM_ARCH_OLMO2:{result = llm.build_olmo2();} break;case LLM_ARCH_OLMOE:{result = llm.build_olmoe();} break;case LLM_ARCH_OPENELM:{result = llm.build_openelm();} break;case LLM_ARCH_GPTNEOX:{result = llm.build_gptneox();} break;case LLM_ARCH_ARCTIC:{result = llm.build_arctic();} break;case LLM_ARCH_DEEPSEEK:{result = llm.build_deepseek();} break;case LLM_ARCH_DEEPSEEK2:{result = llm.build_deepseek2();} break;case LLM_ARCH_CHATGLM:{result = llm.build_chatglm();} break;case LLM_ARCH_BITNET:{result = llm.build_bitnet();} break;case LLM_ARCH_T5:{if (lctx.is_encoding) {result = llm.build_t5_enc();} else {result = llm.build_t5_dec();}} break;case LLM_ARCH_T5ENCODER:{result = llm.build_t5_enc();} break;case LLM_ARCH_JAIS:{result = llm.build_jais();} break;case LLM_ARCH_NEMOTRON:{result = llm.build_nemotron();} break;case LLM_ARCH_EXAONE:{result = llm.build_exaone();} break;case LLM_ARCH_RWKV6:{result = llm.build_rwkv6();} break;case LLM_ARCH_RWKV6QWEN2:{result = llm.build_rwkv6qwen2();} break;case LLM_ARCH_CHAMELEON:{result = llm.build_chameleon();} break;case LLM_ARCH_WAVTOKENIZER_DEC:{result = llm.build_wavtokenizer_dec();} break;default:GGML_ABORT("fatal error");}
References
[1] Yongqiang Cheng, https://yongqiang.blog.csdn.net/
[2] huggingface/gguf, https://github.com/huggingface/huggingface.js/tree/main/packages/gguf
相关文章：
llama.cpp LLM_ARCH_DEEPSEEK and LLM_ARCH_DEEPSEEK2
llama.cpp LLM_ARCH_DEEPSEEK and LLM_ARCH_DEEPSEEK2 1. LLM_ARCH_DEEPSEEK and LLM_ARCH_DEEPSEEK22. LLM_ARCH_DEEPSEEK and LLM_ARCH_DEEPSEEK23. struct ggml_cgraph * build_deepseek() and struct ggml_cgraph * build_deepseek2()References 不宜吹捧中国大语言模型的同…...
C语言自定义数据类型详解（二）——结构体类型（下）
书接上回，前面我们已经给大家介绍了如何去声明和创建一个结构体，如何初始化结构体变量等这些关于结构体的基础知识。下面我们将继续给大家介绍和结构体有关的知识： 今天的主题是：结构体大小的计算并简单了解一下位段的相关知识。…...
DeepSeek学术写作测评第二弹：数据分析、图表解读，效果怎么样？
我是娜姐 迪娜学姐 ，一个SCI医学期刊编辑，探索用AI工具提效论文写作和发表。 针对最近全球热议的DeepSeek开源大模型，娜姐昨天分析了关于论文润色、中译英的详细效果测评： DeepSeek学术写作测评第一弹：论文润色&#…...
深入理解 Python 中的 `__all__`：控制模块的公共接口
在 Python 编程中，模块化设计是构建可维护和可扩展代码的关键。模块不仅帮助我们组织代码，还能通过隐藏实现细节来提高代码的可读性和安全性。Python 提供了多种机制来控制模块的可见性，其中 __all__ 是一个非常重要但常被忽视的特性。本文将…...
虚幻基础07：蓝图接口
能帮到你的话，就给个赞吧 😘 文章目录 作用原理事件函数 作用 实现对象间的通知。 A 通知 B 做什么。 原理 将接口抽象为蓝图，使得任意蓝图都能直接访问。 只需要再传入对象地址，就能执行对象的功能。 事件 黄色：…...
数据结构---哈希表
基本概念 哈希函数（Hash Function）是一种将输入的数据（通常是任意大小的）映射到固定大小的输出（通常是一个固定长度的值）的函数。这个输出值通常称为“哈希值”（Hash Value）或“哈希…...
DataWhale组队学习 leetCode task4
1. 滑动窗口算法介绍 想象你正在用一台望远镜观察一片星空。望远镜的镜头大小是固定的，你可以通过滑动镜头来观察不同的星区。滑动窗口算法就像这台望远镜，它通过一个固定或可变大小的“窗口”来观察数组或字符串中的连续区间。 滑动操作：就像…...
【ESP32】ESP-IDF开发 | WiFi开发 | UDP用户数据报协议 + UDP客户端和服务器例程
1. 简介 UDP协议（User Datagram Protocol），全称用户数据报协议，它是一种面向非连接的协议，面向非连接指的是在正式通信前不必与对方先建立连接， 不管对方状态就直接发送。至于对方是否可以接收到这些数据内…...
【PyQt5】数据库连接失败: Driver not loaded Driver not loaded
报错内容如下： 可以看到目前所支持的数据库驱动仅有[‘QSQLITE’, ‘QMARIADB’, ‘QODBC’, ‘QODBC3’, ‘QPSQL’, ‘QPSQL7’] 我在网上查找半天解决方法未果，其中有一篇看评论反馈是可以使用的，但是PyQt5的版本有点低，5.12…...
Unity游戏(Assault空对地打击)开发(1) 创建项目和选择插件
目录 前言 创建项目 插件导入 地形插件 前言 这是游戏开发第一篇，进行开发准备。 创作不易，欢迎支持。 我的编辑器布局是【Tall】，建议调整为该布局，如下。 创建项目 首先创建一个项目，过程略，名字请勿…...
Rust：如何动态调用字符串定义的 Rhai 函数？
在 Rust 中使用 Rhai 脚本引擎时，你可以动态地调用传入的字符串表示的 Rhai 函数。Rhai 是一个嵌入式脚本语言，专为嵌入到 Rust 应用中而设计。以下是一个基本示例，展示了如何在 Rust 中调用用字符串传入的 Rhai 函数。 首先，确保…...
A星算法两元障碍物矩阵转化为rrt算法四元障碍物矩阵
对于a星算法obstacle所表示的障碍物障碍物信息，每行表示一个障碍物的坐标，例如2 , 3; % 第一个障碍物在第二行第三列，也就是边长为1的正方形障碍物右上角横坐标是2，纵坐标为3，障碍物的宽度和高度始终为1.在rrt路径规划…...
【C++】设计模式详解：单例模式
文章目录 Ⅰ. 设计一个类，不允许被拷贝Ⅱ. 请设计一个类，只能在堆上创建对象Ⅲ. 请设计一个类，只能在栈上创建对象Ⅳ. 请设计一个类，不能被继承Ⅴ. 请设计一个类，只能创建一个对象（单例模式）&am…...
单细胞分析基础-第一节 数据质控、降维聚类
scRNA_pipeline\1.Seurat 生物技能树 可进官网查询 添加链接描述 分析流程 准备：R包安装 options("repos"="https://mirrors.ustc.edu.cn/CRAN/") if(!require("BiocManager")) install.packages("BiocManager",update = F,ask =…...
多项日常使用测试，带你了解如何选择AI工具 Deepseek VS ChatGpt VS Claude
多项日常使用测试，带你了解如何选择AI工具 Deepseek VS ChatGpt VS Claude 注：因为考虑到绝大部分人的使用，我这里所用的模型均为免费模型。官方可访问的。ChatGPT这里用的是4o Ai对话，编程一直以来都是人们所讨论的话题。Ai的出现…...
每日一题-判断是否是平衡二叉树
判断是否是平衡二叉树 题目描述数据范围题解解题思路递归算法代码实现代码解析时间和空间复杂度分析示例示例 1示例 2 总结 ) 题目描述 输入一棵节点数为 n 的二叉树，判断该二叉树是否是平衡二叉树。平衡二叉树定义为： 它是一棵空树。或者它的左右子树…...
FLTK - FLTK1.4.1 - 搭建模板，将FLTK自带的实现搬过来做实验
文章目录 FLTK - FLTK1.4.1 - 搭建模板，将FLTK自带的实现搬过来做实验概述笔记my_fltk_test.cppfltk_test.hfltk_test.cxx用adjuster工程试了一下，好使。END FLTK - FLTK1.4.1 - 搭建模板，将FLTK自带的实现搬过来做实验 概述 用fluid搭建UI…...
《多阶段渐进式图像修复》学习笔记
paper：2102.02808 GitHub：swz30/MPRNet: [CVPR 2021] Multi-Stage Progressive Image Restoration. SOTA results for Image deblurring, deraining, and denoising. 目录 摘要 1、介绍 2、相关工作 2.1 单阶段方法 2.2 多阶段方法 2.3 注意力机…...
AWScurl笔记
摘要 AWScurl是一款专为与AWS服务交互设计的命令行工具，它模拟了curl的功能并添加了AWS签名版本4的支持。这一特性使得用户能够安全有效地执行带有AWS签名的请求，极大地提升了与AWS服务交互时的安全性和有效性。 GitHub - okigan/awscurl: curl-like acc…...
QT使用eigen
QT使用eigen 1. 下载eigen https://eigen.tuxfamily.org/index.php?titleMain_Page#Download 下载后解压 2. QT引入eigen eigen源码好像只有头文件，因此只需要引入头文件就好了 qt新建项目后。修改pro文件. INCLUDEPATH E:\222078\qt\eigen-3.4.0\eigen-3.…...
揭示Baklib企业内容管理系统CMS的核心功能与应用价值
内容概要 企业内容管理系统（CMS）是指通过一系列工具和技术，帮助企业高效地创建、存储、管理和分发数字内容的系统。这些系统在现代企业运作中发挥着至关重要的作用，尤其是在信息量大、业务流程复杂的环境中。Baklib作为一个突出的…...
如何跨互联网adb连接到远程手机-蓝牙电话集中维护
如何跨互联网adb连接到远程手机-蓝牙电话集中维护 --ADB连接专题 一、前言 随便找一个手机，安装一个App并简单设置一下，就可以跨互联网的ADB连接到这个手机，从而远程操控这个手机做各种操作。你敢相信吗？而这正是本篇想要描述的…...
flume和kafka整合 flume和kafka为什么一起用？
Flume和Kafka一起使用的主要原因是为了实现高效、可靠的数据采集和实时处理。12 实时流式日志处理的需求 Flume和Kafka结合使用的主要目的是为了完成实时流式的日志处理。Flume负责数据的采集和传输，而Kafka则作为消息缓存队列，能够有效地缓冲数据，防止数据堆积或丢…...
java.util.Random类（详细案例拆解）（已完结）
前言： 小编打算近期更俩三期类的专栏，一些常用的专集类，给大家分好类别总结和详细的代码举例解释。 今天是除夕，小编先祝贺大家除夕快乐啦！！ 今天是第六个 java.lang.Math 包中的 java.util.Random类 我…...
Java后端之AOP
AOP：面向切面编程，本质是面向特定方法编程 引入依赖： <dependency><groupId>org.springframework.boot</groupId><artifactId>spring-boot-starter-aop</artifactId></dependency>示例：记录…...
【信息系统项目管理师-选择真题】2008上半年综合知识答案和详解
更多内容请见： 备考信息系统项目管理师-专栏介绍和目录 文章目录 【第1题】【第2题】【第3题】【第4题】【第5题】【第6题】【第7~8题】【第9题】【第10题】【第11题】【第12题】【第13题】【第14题】【第15题】【第16~20题】【第21题】【第22题】【第23题】【第24题】【第25题…...
go到底是什么意思：对go的猜测或断言
go这个单词，简单地讲，表示“走或去”的意思： go v.去；走 认真想想，go是一个非常神秘的单词，g-和o-这两个字母，为什么就会表达“去；走”的意思呢？它的字面义或本质&…...
零刻SER7接口及配置跑分
今天入手了一台迷你机-零刻SER7 ，不得不说这机身是真的小啊，相比于传统台式机，它几乎不占空间，可以轻松放置在桌面、电视柜甚至背包中，非常适合需要频繁移动或空间有限的用户。尽管体积小巧，但零刻SER7在性…...
【Java基础-41.5】深入解析Java异常链：构建清晰的错误追踪体系
在Java编程中，异常处理是保证程序健壮性和可维护性的重要部分。然而，在实际开发中，异常往往不是孤立发生的，而是由一系列相关的异常引发的。为了更好地理解和处理这种复杂的异常场景，Java引入了 异常链（Exc…...
【Python实现机器遗忘算法】复现2023年TNNLS期刊算法UNSIR
【Python实现机器遗忘算法】复现2023年TNNLS期刊算法UNSIR 1 算法原理 Tarun A K, Chundawat V S, Mandal M, et al. Fast yet effective machine unlearning[J]. IEEE Transactions on Neural Networks and Learning Systems, 2023. 本文提出了一种名为 UNSIR（Un…...