mirror of
				https://github.com/ggml-org/llama.cpp.git
				synced 2025-10-31 08:51:55 +00:00 
			
		
		
		
	model : add hunyuan moe (#14425)
* model : add hunyuan moe * tokenizer ok * fix tensor name * cgraph init * chat template * wip * almost working * skip embed, fix bos * cleanup * yarn scaling * cleanup * correct rope type * failed token fix * ntk alpha freq_base * tokenization working * cleanup and pr changes * vocab_size sanity check * ntk alpha generic * Update convert_hf_to_gguf.py * Apply suggestions from code review * fix regression * fix style --------- Co-authored-by: kooshi <1934337+kooshi@users.noreply.github.com>
This commit is contained in:
		| @@ -78,6 +78,7 @@ static const std::map<llm_arch, const char *> LLM_ARCH_NAMES = { | ||||
|     { LLM_ARCH_DOTS1,            "dots1"            }, | ||||
|     { LLM_ARCH_ARCEE,            "arcee"            }, | ||||
|     { LLM_ARCH_ERNIE4_5,         "ernie4_5"         }, | ||||
|     { LLM_ARCH_HUNYUAN_MOE,      "hunyuan-moe"      }, | ||||
|     { LLM_ARCH_UNKNOWN,          "(unknown)"        }, | ||||
| }; | ||||
|  | ||||
| @@ -1694,6 +1695,29 @@ static const std::map<llm_arch, std::map<llm_tensor, const char *>> LLM_TENSOR_N | ||||
|             { LLM_TENSOR_FFN_UP,             "blk.%d.ffn_up" }, | ||||
|         }, | ||||
|     }, | ||||
|     { | ||||
|         LLM_ARCH_HUNYUAN_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_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_FFN_GATE_INP,    "blk.%d.ffn_gate_inp" }, | ||||
|             { LLM_TENSOR_FFN_NORM,        "blk.%d.ffn_norm" }, | ||||
|             { 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_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_UNKNOWN, | ||||
|         { | ||||
|   | ||||
		Reference in New Issue
	
	Block a user
	 Xuan-Son Nguyen
					Xuan-Son Nguyen