ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-03-02 01:50:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

model : Port Minimax M2 from mainline (#907)

Browse Source 
Co-authored-by: firecoperana <firecoperana>
This commit is contained in:
firecoperana
2025-11-06 16:09:24 +00:00
committed by GitHub
parent 66ef68bc14
commit e15a215e6b
15 changed files with 292 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
src/llama-model.cpp
View File

@@ -1228,6 +1228,27 @@ static const std::map<llm_arch, std::map<llm_tensor, std::string>> LLM_TENSOR_NA
{ LLM_TENSOR_LAYER_OUT_NORM, "blk.%d.layer_output_norm" },
},
},
{
LLM_ARCH_MINIMAX_M2,
{
{ 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_TENSOR_FFN_EXP_PROBS_B, "blk.%d.exp_probs_b" },
},
},
{
LLM_ARCH_UNKNOWN,
{
@@ -1470,6 +1491,7 @@ const char * llama_model_type_name(e_model type) {
case MODEL_80B_A13B: return "80B.A13B";
case MODEL_100B_A6B: return "100B.A6B";
case MODEL_106B_A12B: return "106B.A12B";
case MODEL_230B_A10B: return "230B.A10B";
case MODEL_235B_A22B: return "235B.A22B";
case MODEL_300B_A47B: return "300B.A47B";
case MODEL_355B_A32B: return "355B.A32B";