|
|
@@ -1777,26 +1777,26 @@ static const std::map<llm_arch, std::map<llm_tensor, const char *>> LLM_TENSOR_N
|
|
|
},
|
|
|
},
|
|
|
{
|
|
|
- LLM_ARCH_UNKNOWN,
|
|
|
+ LLM_ARCH_SMOLLM3,
|
|
|
{
|
|
|
- { LLM_TENSOR_TOKEN_EMBD, "token_embd" },
|
|
|
+ { 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_SMOLLM3,
|
|
|
+ LLM_ARCH_UNKNOWN,
|
|
|
{
|
|
|
- { 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_TOKEN_EMBD, "token_embd" },
|
|
|
},
|
|
|
},
|
|
|
};
|