mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-10-30 08:42:00 +00:00
model: support GLM 4.5 family of models (#14939)
* model: Add GLM 4.5 (#14921) Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Merge in PR suggestions Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * model: Add GLM 4.5 family of models (#14921) 1. Updated tensor_mapping.py with NextN tensor mappings - Added proper tensor mappings for all NextN/MTP tensors in /Users/samm/git/llama.cpp/gguf-py/gguf/tensor_mapping.py - Added mappings for: eh_proj, embed_tokens, enorm, hnorm, shared_head.head, shared_head.norm 2. Added num_nextn_predict_layers configuration - Added LLM_KV_NUM_NEXTN_PREDICT_LAYERS constant to llama-arch.h and llama-arch.cpp - Added num_nextn_predict_layers field to llama_hparams struct - Updated GLM4_MOE parameter loading in llama-model.cpp to read this parameter - Modified tensor loading logic to conditionally load NextN tensors based on num_nextn_predict_layers - Added GGUF writer support in gguf_writer.py with add_num_nextn_predict_layers() method - Updated conversion script to extract and write this parameter from HuggingFace config 3. Added FIM tokens for GLM4_MOE - Added GLM-4.5's FIM tokens to llama-vocab.cpp: - <|code_prefix|> for FIM_PRE - <|code_suffix|> for FIM_SUF - <|code_middle|> for FIM_MID 4. Removed manual NextN tensor handling - Removed the special-case handling in convert_hf_to_gguf.py that manually mapped NextN tensors - NextN tensors are now handled automatically through the proper tensor mapping system * glm 4.5 update tensors names * model: glm 4.5 apply suggestions from code review Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update src/llama-model.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * model: glm 4.5 apply suggestions from code review Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * model: glm 4.5 apply suggestions from code review * Apply suggestions from code review * patch broken chat template * typings fix * add TENSOR_SKIP flag Co-authored-by: Diego Devesa <slarengh@gmail.com> * Update src/llama-model-loader.h Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> --------- Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> Co-authored-by: Diego Devesa <slarengh@gmail.com>
This commit is contained in:
Sam
@@ -62,6 +62,7 @@ static const std::map<llm_arch, const char *> LLM_ARCH_NAMES = {
|
||||
{ LLM_ARCH_DEEPSEEK2, "deepseek2" },
|
||||
{ LLM_ARCH_CHATGLM, "chatglm" },
|
||||
{ LLM_ARCH_GLM4, "glm4" },
|
||||
{ LLM_ARCH_GLM4_MOE, "glm4moe" },
|
||||
{ LLM_ARCH_BITNET, "bitnet" },
|
||||
{ LLM_ARCH_T5, "t5" },
|
||||
{ LLM_ARCH_T5ENCODER, "t5encoder" },
|
||||
@@ -127,6 +128,7 @@ static const std::map<llm_kv, const char *> LLM_KV_NAMES = {
|
||||
{ LLM_KV_EXPERT_WEIGHTS_NORM, "%s.expert_weights_norm" },
|
||||
{ LLM_KV_EXPERT_GATING_FUNC, "%s.expert_gating_func" },
|
||||
{ LLM_KV_MOE_EVERY_N_LAYERS, "%s.moe_every_n_layers" },
|
||||
{ LLM_KV_NEXTN_PREDICT_LAYERS, "%s.nextn_predict_layers" },
|
||||
{ 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" },
|
||||
@@ -1391,6 +1393,40 @@ static const std::map<llm_arch, std::map<llm_tensor, const char *>> LLM_TENSOR_N
|
||||
{ LLM_TENSOR_FFN_POST_NORM, "blk.%d.post_ffw_norm" },
|
||||
},
|
||||
},
|
||||
{
|
||||
LLM_ARCH_GLM4_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_POST_NORM, "blk.%d.post_attention_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_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_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_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" },
|
||||
// NextN/MTP tensors - preserved but unused (in final layer, dynamic layer number)
|
||||
{ LLM_TENSOR_NEXTN_EH_PROJ, "blk.%d.nextn.eh_proj" },
|
||||
{ LLM_TENSOR_NEXTN_EMBED_TOKENS, "blk.%d.nextn.embed_tokens" },
|
||||
{ LLM_TENSOR_NEXTN_ENORM, "blk.%d.nextn.enorm" },
|
||||
{ LLM_TENSOR_NEXTN_HNORM, "blk.%d.nextn.hnorm" },
|
||||
{ LLM_TENSOR_NEXTN_SHARED_HEAD_HEAD, "blk.%d.nextn.shared_head_head" },
|
||||
{ LLM_TENSOR_NEXTN_SHARED_HEAD_NORM, "blk.%d.nextn.shared_head_norm" },
|
||||
},
|
||||
},
|
||||
{
|
||||
LLM_ARCH_BITNET,
|
||||
{
|
||||
@@ -2181,6 +2217,14 @@ static const std::map<llm_tensor, llm_tensor_info> LLM_TENSOR_INFOS = {
|
||||
{LLM_TENSOR_SHORTCONV_CONV, {LLM_TENSOR_LAYER_REPEATING, GGML_OP_SSM_CONV}},
|
||||
{LLM_TENSOR_SHORTCONV_INPROJ, {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
|
||||
{LLM_TENSOR_SHORTCONV_OUTPROJ, {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
|
||||
// NextN/MTP tensors are currently ignored (reserved for future MTP support)
|
||||
// These tensors only exist in the last layer(s) and are treated as output tensors
|
||||
{LLM_TENSOR_NEXTN_EH_PROJ, {LLM_TENSOR_LAYER_OUTPUT, GGML_OP_MUL_MAT}},
|
||||
{LLM_TENSOR_NEXTN_EMBED_TOKENS, {LLM_TENSOR_LAYER_OUTPUT, GGML_OP_GET_ROWS}},
|
||||
{LLM_TENSOR_NEXTN_ENORM, {LLM_TENSOR_LAYER_OUTPUT, GGML_OP_GET_ROWS}},
|
||||
{LLM_TENSOR_NEXTN_HNORM, {LLM_TENSOR_LAYER_OUTPUT, GGML_OP_MUL}},
|
||||
{LLM_TENSOR_NEXTN_SHARED_HEAD_HEAD, {LLM_TENSOR_LAYER_OUTPUT, GGML_OP_MUL_MAT}},
|
||||
{LLM_TENSOR_NEXTN_SHARED_HEAD_NORM, {LLM_TENSOR_LAYER_OUTPUT, GGML_OP_MUL}},
|
||||
};
|
||||
|
||||
LLM_KV::LLM_KV(llm_arch arch, const char * suffix) : arch(arch), suffix(suffix) {}
|
||||
|
||||
Reference in New Issue
Block a user