diff --git a/src/llama-arch.cpp b/src/llama-arch.cpp index 799d16167b..f79bc828f3 100644 --- a/src/llama-arch.cpp +++ b/src/llama-arch.cpp @@ -543,6 +543,10 @@ static std::set llm_get_tensor_names(llm_arch arch) { case LLM_ARCH_CLIP: return {}; case LLM_ARCH_LLAMA: + case LLM_ARCH_REFACT: + case LLM_ARCH_MINICPM: + case LLM_ARCH_GRANITE: + case LLM_ARCH_GRANITE_MOE: case LLM_ARCH_DECI: case LLM_ARCH_MISTRAL3: case LLM_ARCH_LLAMA_EMBED: @@ -743,11 +747,9 @@ static std::set llm_get_tensor_names(llm_arch arch) { LLM_TENSOR_ATTN_Q_NORM, LLM_TENSOR_ATTN_K_NORM, }; - case LLM_ARCH_REFACT: case LLM_ARCH_QWEN2: case LLM_ARCH_QWEN2VL: case LLM_ARCH_INTERNLM2: - case LLM_ARCH_GRANITE: case LLM_ARCH_ERNIE4_5: case LLM_ARCH_PADDLEOCR: case LLM_ARCH_SMOLLM3: @@ -758,6 +760,7 @@ static std::set llm_get_tensor_names(llm_arch arch) { LLM_TENSOR_TOKEN_EMBD, LLM_TENSOR_OUTPUT_NORM, LLM_TENSOR_OUTPUT, + LLM_TENSOR_ROPE_FREQS, LLM_TENSOR_ATTN_NORM, LLM_TENSOR_ATTN_Q, LLM_TENSOR_ATTN_K, @@ -1231,29 +1234,6 @@ static std::set llm_get_tensor_names(llm_arch arch) { LLM_TENSOR_FFN_DOWN, LLM_TENSOR_FFN_UP, }; - case LLM_ARCH_MINICPM: - return { - LLM_TENSOR_TOKEN_EMBD, - LLM_TENSOR_OUTPUT_NORM, - LLM_TENSOR_OUTPUT, - LLM_TENSOR_ROPE_FREQS, - LLM_TENSOR_ROPE_FACTORS_LONG, - LLM_TENSOR_ROPE_FACTORS_SHORT, - LLM_TENSOR_ATTN_NORM, - LLM_TENSOR_ATTN_Q, - LLM_TENSOR_ATTN_K, - LLM_TENSOR_ATTN_V, - LLM_TENSOR_ATTN_OUT, - LLM_TENSOR_ATTN_ROT_EMBD, - LLM_TENSOR_FFN_GATE_INP, - LLM_TENSOR_FFN_NORM, - LLM_TENSOR_FFN_GATE, - LLM_TENSOR_FFN_DOWN, - LLM_TENSOR_FFN_UP, - LLM_TENSOR_FFN_GATE_EXP, - LLM_TENSOR_FFN_DOWN_EXP, - LLM_TENSOR_FFN_UP_EXP, - }; case LLM_ARCH_MINICPM3: return { LLM_TENSOR_TOKEN_EMBD, @@ -1441,6 +1421,7 @@ static std::set llm_get_tensor_names(llm_arch arch) { LLM_TENSOR_TOKEN_EMBD, LLM_TENSOR_OUTPUT, LLM_TENSOR_OUTPUT_NORM, + LLM_TENSOR_ROPE_FREQS, LLM_TENSOR_ATTN_NORM, LLM_TENSOR_ATTN_Q, LLM_TENSOR_ATTN_K, @@ -1655,7 +1636,9 @@ static std::set llm_get_tensor_names(llm_arch arch) { LLM_TENSOR_ROPE_FREQS, LLM_TENSOR_OUTPUT_NORM, LLM_TENSOR_OUTPUT, + LLM_TENSOR_TOKEN_EMBD, LLM_TENSOR_ATTN_NORM, + LLM_TENSOR_ATTN_QKV, LLM_TENSOR_ATTN_Q, LLM_TENSOR_ATTN_K, LLM_TENSOR_ATTN_V, @@ -2059,30 +2042,12 @@ static std::set llm_get_tensor_names(llm_arch arch) { LLM_TENSOR_FFN_DOWN, LLM_TENSOR_FFN_UP, }; - case LLM_ARCH_GRANITE_MOE: - return { - LLM_TENSOR_TOKEN_EMBD, - LLM_TENSOR_OUTPUT_NORM, - LLM_TENSOR_OUTPUT, - LLM_TENSOR_ATTN_NORM, - LLM_TENSOR_ATTN_Q, - LLM_TENSOR_ATTN_K, - LLM_TENSOR_ATTN_V, - LLM_TENSOR_ATTN_OUT, - LLM_TENSOR_FFN_NORM, - LLM_TENSOR_FFN_GATE_INP, - LLM_TENSOR_FFN_GATE_EXPS, - LLM_TENSOR_FFN_DOWN_EXPS, - LLM_TENSOR_FFN_UP_EXPS, - LLM_TENSOR_FFN_GATE_SHEXP, - LLM_TENSOR_FFN_DOWN_SHEXP, - LLM_TENSOR_FFN_UP_SHEXP, - }; case LLM_ARCH_GRANITE_HYBRID: return { LLM_TENSOR_TOKEN_EMBD, LLM_TENSOR_OUTPUT_NORM, LLM_TENSOR_OUTPUT, + LLM_TENSOR_ROPE_FREQS, LLM_TENSOR_ATTN_NORM, LLM_TENSOR_SSM_IN, LLM_TENSOR_SSM_CONV1D, @@ -2410,6 +2375,7 @@ static std::set llm_get_tensor_names(llm_arch arch) { LLM_TENSOR_TOKEN_EMBD, LLM_TENSOR_OUTPUT_NORM, LLM_TENSOR_OUTPUT, + LLM_TENSOR_ROPE_FREQS, LLM_TENSOR_ATTN_NORM, LLM_TENSOR_ATTN_QKV, LLM_TENSOR_ATTN_OUT, @@ -2787,7 +2753,12 @@ std::string LLM_TN_IMPL::str() const { } if (model_tensors.find(tensor) == model_tensors.end()) { - return LLM_TENSOR_NAMES.at(tensor); + const char * name = LLM_TENSOR_NAMES.at(tensor); + if (suffix != nullptr || bid != -1 || xid != -1) { + LLAMA_LOG_ERROR("%s: cannot properly format tensor name %s with suffix=%s bid=%d xid=%d\n", + __func__, name, suffix, bid, xid); + } + return name; } std::string name = ::format(LLM_TENSOR_NAMES.at(tensor), bid, xid); diff --git a/src/llama-model-saver.cpp b/src/llama-model-saver.cpp index 6f6538aecc..637be9b7ce 100644 --- a/src/llama-model-saver.cpp +++ b/src/llama-model-saver.cpp @@ -2,6 +2,7 @@ #include "gguf.h" +#include "llama-arch.h" #include "llama.h" #include "llama-hparams.h" #include "llama-model.h" @@ -105,7 +106,10 @@ void llama_model_saver::add_tensor(const struct ggml_tensor * tensor) { return; } if (gguf_find_tensor(gguf_ctx, tensor->name) >= 0) { - GGML_ASSERT(std::string(tensor->name) == "rope_freqs.weight"); // FIXME + const std::string tensor_name = tensor->name; + GGML_ASSERT( + tensor_name == "rope_freqs.weight" || tensor_name == "rope_factors_long.weight" || + tensor_name == "rope_factors_short.weight"); // FIXME return; } gguf_add_tensor(gguf_ctx, tensor); @@ -127,6 +131,7 @@ void llama_model_saver::add_kv_from_model() { tokens[id] = token_data.text; scores[id] = token_data.score; + // FIXME should this be treated as flags? switch(token_data.attr) { case LLAMA_TOKEN_ATTR_UNKNOWN: token_types[id] = LLAMA_TOKEN_TYPE_UNKNOWN; break; case LLAMA_TOKEN_ATTR_UNUSED: token_types[id] = LLAMA_TOKEN_TYPE_UNUSED; break; @@ -134,6 +139,9 @@ void llama_model_saver::add_kv_from_model() { case LLAMA_TOKEN_ATTR_CONTROL: token_types[id] = LLAMA_TOKEN_TYPE_CONTROL; break; case LLAMA_TOKEN_ATTR_USER_DEFINED: token_types[id] = LLAMA_TOKEN_TYPE_USER_DEFINED; break; case LLAMA_TOKEN_ATTR_BYTE: token_types[id] = LLAMA_TOKEN_TYPE_BYTE; break; + // case LLAMA_TOKEN_ATTR_NORMALIZED: ??? + // case LLAMA_TOKEN_ATTR_LSTRIP: ??? + // case LLAMA_TOKEN_ATTR_RSTRIP: ??? case LLAMA_TOKEN_ATTR_UNDEFINED: default: token_types[id] = LLAMA_TOKEN_TYPE_UNDEFINED; break; } @@ -144,6 +152,19 @@ void llama_model_saver::add_kv_from_model() { add_kv(LLM_KV_GENERAL_ARCHITECTURE, model->arch_name()); // add_kv(LLM_KV_GENERAL_QUANTIZATION_VERSION, ???); // add_kv(LLM_KV_GENERAL_ALIGNMENT, ???); + // add_kv(LLM_KV_GENERAL_FILE_TYPE, ???); + // add_kv(LLM_KV_GENERAL_SAMPLING_SEQUENCE, ???); + // add_kv(LLM_KV_GENERAL_SAMPLING_TOP_K, ???); + // add_kv(LLM_KV_GENERAL_SAMPLING_TOP_P, ???); + // add_kv(LLM_KV_GENERAL_SAMPLING_MIN_P, ???); + // add_kv(LLM_KV_GENERAL_SAMPLING_XTC_PROBABILITY, ???); + // add_kv(LLM_KV_GENERAL_SAMPLING_XTC_THRESHOLD, ???); + // add_kv(LLM_KV_GENERAL_SAMPLING_TEMP, ???); + // add_kv(LLM_KV_GENERAL_SAMPLING_PENALTY_LAST_N, ???); + // add_kv(LLM_KV_GENERAL_SAMPLING_PENALTY_REPEAT, ???); + // add_kv(LLM_KV_GENERAL_SAMPLING_MIROSTAT, ???); + // add_kv(LLM_KV_GENERAL_SAMPLING_MIROSTAT_TAU, ???); + // add_kv(LLM_KV_GENERAL_SAMPLING_MIROSTAT_ETA, ???); add_kv(LLM_KV_GENERAL_NAME, model->name); // add_kv(LLM_KV_GENERAL_AUTHOR, ???); // add_kv(LLM_KV_GENERAL_VERSION, ???); @@ -163,17 +184,31 @@ void llama_model_saver::add_kv_from_model() { add_kv(LLM_KV_LEADING_DENSE_BLOCK_COUNT, hparams.n_layer_dense_lead); add_kv(LLM_KV_FEED_FORWARD_LENGTH, hparams.n_ff_arr, true); add_kv(LLM_KV_EXPERT_FEED_FORWARD_LENGTH, hparams.n_ff_exp); - add_kv(LLM_KV_EXPERT_SHARED_FEED_FORWARD_LENGTH, hparams.n_ff_exp); + add_kv(LLM_KV_EXPERT_SHARED_FEED_FORWARD_LENGTH, hparams.n_ff_shexp); + add_kv(LLM_KV_EXPERT_SHARED_FEED_FORWARD_LENGTH, hparams.n_ff_chexp); + add_kv(LLM_KV_SWIGLU_CLAMP_EXP, hparams.swiglu_clamp_exp); + add_kv(LLM_KV_SWIGLU_CLAMP_SHEXP, hparams.swiglu_clamp_shexp); add_kv(LLM_KV_USE_PARALLEL_RESIDUAL, hparams.use_par_res); // add_kv(LLM_KV_TENSOR_DATA_LAYOUT, ???); add_kv(LLM_KV_EXPERT_COUNT, hparams.n_expert); add_kv(LLM_KV_EXPERT_USED_COUNT, hparams.n_expert_used); add_kv(LLM_KV_EXPERT_SHARED_COUNT, hparams.n_expert_shared); + add_kv(LLM_KV_EXPERT_GROUP_COUNT, hparams.n_expert_groups); + add_kv(LLM_KV_EXPERT_GROUP_USED_COUNT, hparams.n_group_used); add_kv(LLM_KV_EXPERT_WEIGHTS_SCALE, hparams.expert_weights_scale); + add_kv(LLM_KV_EXPERT_WEIGHTS_NORM, hparams.expert_weights_norm); + add_kv(LLM_KV_EXPERT_GATING_FUNC, hparams.expert_gating_func); + add_kv(LLM_KV_EXPERT_GROUP_SCALE, hparams.expert_group_scale); + add_kv(LLM_KV_EXPERTS_PER_GROUP, hparams.n_group_experts); + add_kv(LLM_KV_MOE_EVERY_N_LAYERS, hparams.moe_every_n_layers); + add_kv(LLM_KV_NEXTN_PREDICT_LAYERS, hparams.nextn_predict_layers); + add_kv(LLM_KV_NUM_DEEPSTACK_LAYERS, hparams.n_deepstack_layers); add_kv(LLM_KV_POOLING_TYPE, uint32_t(hparams.pooling_type)); add_kv(LLM_KV_LOGIT_SCALE, hparams.f_logit_scale); add_kv(LLM_KV_DECODER_START_TOKEN_ID, hparams.dec_start_token_id); + add_kv(LLM_KV_DECODER_BLOCK_COUNT, hparams.dec_n_layer); add_kv(LLM_KV_ATTN_LOGIT_SOFTCAPPING, hparams.f_attn_logit_softcapping); + add_kv(LLM_KV_ROUTER_LOGIT_SOFTCAPPING, hparams.f_router_logit_softcapping); add_kv(LLM_KV_FINAL_LOGIT_SOFTCAPPING, hparams.f_final_logit_softcapping); add_kv(LLM_KV_SWIN_NORM, hparams.swin_norm); add_kv(LLM_KV_RESCALE_EVERY_N_LAYERS, hparams.rescale_every_n_layers); @@ -181,6 +216,9 @@ void llama_model_saver::add_kv_from_model() { add_kv(LLM_KV_TIME_DECAY_EXTRA_DIM, hparams.time_decay_extra_dim); add_kv(LLM_KV_RESIDUAL_SCALE, hparams.f_residual_scale); add_kv(LLM_KV_EMBEDDING_SCALE, hparams.f_embedding_scale); + add_kv(LLM_KV_TOKEN_SHIFT_COUNT, hparams.token_shift_count); + add_kv(LLM_KV_INTERLEAVE_MOE_LAYER_STEP, hparams.n_moe_layer_step); + // add_kv(LLM_KV_FULL_ATTENTION_INTERVAL, ???); add_kv(LLM_KV_ATTENTION_HEAD_COUNT, hparams.n_head_arr, true); add_kv(LLM_KV_ATTENTION_HEAD_COUNT_KV, hparams.n_head_kv_arr, true); @@ -188,22 +226,39 @@ void llama_model_saver::add_kv_from_model() { add_kv(LLM_KV_ATTENTION_CLAMP_KQV, hparams.f_clamp_kqv); add_kv(LLM_KV_ATTENTION_KEY_LENGTH, hparams.n_embd_head_k_full); add_kv(LLM_KV_ATTENTION_VALUE_LENGTH, hparams.n_embd_head_v_full); - add_kv(LLM_KV_ATTENTION_KEY_LENGTH_SWA, hparams.n_embd_head_k_swa); - add_kv(LLM_KV_ATTENTION_VALUE_LENGTH_SWA, hparams.n_embd_head_v_swa); add_kv(LLM_KV_ATTENTION_LAYERNORM_EPS, hparams.f_norm_eps); add_kv(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps); + add_kv(LLM_KV_ATTENTION_GROUPNORM_EPS, hparams.f_norm_group_eps); + add_kv(LLM_KV_ATTENTION_GROUPNORM_GROUPS, hparams.n_norm_groups); add_kv(LLM_KV_ATTENTION_CAUSAL, hparams.causal_attn); add_kv(LLM_KV_ATTENTION_Q_LORA_RANK, hparams.n_lora_q); add_kv(LLM_KV_ATTENTION_KV_LORA_RANK, hparams.n_lora_kv); + add_kv(LLM_KV_ATTENTION_DECAY_LORA_RANK, hparams.n_lora_decay); + add_kv(LLM_KV_ATTENTION_ICLR_LORA_RANK, hparams.n_lora_iclr); + add_kv(LLM_KV_ATTENTION_VALUE_RESIDUAL_MIX_LORA_RANK, hparams.n_lora_value_res_mix); + add_kv(LLM_KV_ATTENTION_GATE_LORA_RANK, hparams.n_lora_gate); add_kv(LLM_KV_ATTENTION_RELATIVE_BUCKETS_COUNT, hparams.n_rel_attn_bkts); add_kv(LLM_KV_ATTENTION_SLIDING_WINDOW, hparams.n_swa); + // add_kv(LLM_KV_ATTENTION_SLIDING_WINDOW_PATTERN, ???); add_kv(LLM_KV_ATTENTION_SCALE, hparams.f_attention_scale); + add_kv(LLM_KV_ATTENTION_OUTPUT_SCALE, hparams.f_attn_out_scale); + add_kv(LLM_KV_ATTENTION_TEMPERATURE_LENGTH, hparams.attn_temp_length); + add_kv(LLM_KV_ATTENTION_TEMPERATURE_SCALE, hparams.f_attn_temp_scale); + add_kv(LLM_KV_ATTENTION_KEY_LENGTH_MLA, hparams.n_embd_head_k_mla_impl); + add_kv(LLM_KV_ATTENTION_VALUE_LENGTH_MLA, hparams.n_embd_head_v_mla_impl); + add_kv(LLM_KV_ATTENTION_KEY_LENGTH_SWA, hparams.n_embd_head_k_swa); + add_kv(LLM_KV_ATTENTION_VALUE_LENGTH_SWA, hparams.n_embd_head_v_swa); + add_kv(LLM_KV_ATTENTION_INDEXER_HEAD_COUNT, hparams.indexer_n_head); + add_kv(LLM_KV_ATTENTION_INDEXER_KEY_LENGTH, hparams.indexer_head_size); + add_kv(LLM_KV_ATTENTION_INDEXER_TOP_K, hparams.indexer_top_k); const float rope_scaling_factor = hparams.rope_freq_scale_train == 1.0f ? 0.0f : 1.0f/hparams.rope_freq_scale_train; add_kv(LLM_KV_ROPE_DIMENSION_COUNT, hparams.n_rot_full); add_kv(LLM_KV_ROPE_DIMENSION_COUNT_SWA, hparams.n_rot_swa); + add_kv(LLM_KV_ROPE_DIMENSION_SECTIONS, hparams.rope_sections); add_kv(LLM_KV_ROPE_FREQ_BASE, hparams.rope_freq_base_train); + add_kv(LLM_KV_ROPE_FREQ_BASE_SWA, hparams.rope_freq_base_train_swa); // add_kv(LLM_KV_ROPE_SCALE_LINEAR, rope_scaling_factor); // old name add_kv(LLM_KV_ROPE_SCALING_TYPE, llama_rope_scaling_type_name(hparams.rope_scaling_type_train)); add_kv(LLM_KV_ROPE_SCALING_FACTOR, rope_scaling_factor); @@ -211,6 +266,10 @@ void llama_model_saver::add_kv_from_model() { add_kv(LLM_KV_ROPE_SCALING_ORIG_CTX_LEN, hparams.n_ctx_orig_yarn); add_kv(LLM_KV_ROPE_SCALING_FINETUNED, hparams.rope_finetuned); add_kv(LLM_KV_ROPE_SCALING_YARN_LOG_MUL, hparams.rope_yarn_log_mul); + add_kv(LLM_KV_ROPE_SCALING_YARN_EXT_FACTOR, hparams.yarn_ext_factor); + add_kv(LLM_KV_ROPE_SCALING_YARN_ATTN_FACTOR, hparams.yarn_attn_factor); + add_kv(LLM_KV_ROPE_SCALING_YARN_BETA_FAST, hparams.yarn_beta_fast); + add_kv(LLM_KV_ROPE_SCALING_YARN_BETA_SLOW, hparams.yarn_beta_slow); // TODO: implement split file support // add_kv(LLM_KV_SPLIT_NO, ???); @@ -221,8 +280,11 @@ void llama_model_saver::add_kv_from_model() { add_kv(LLM_KV_SSM_CONV_KERNEL, hparams.ssm_d_conv); add_kv(LLM_KV_SSM_STATE_SIZE, hparams.ssm_d_state); add_kv(LLM_KV_SSM_TIME_STEP_RANK, hparams.ssm_dt_rank); + add_kv(LLM_KV_SSM_GROUP_COUNT, hparams.ssm_n_group); add_kv(LLM_KV_SSM_DT_B_C_RMS, hparams.ssm_dt_b_c_rms); + add_kv(LLM_KV_KDA_HEAD_DIM, hparams.n_embd_head_kda); + add_kv(LLM_KV_WKV_HEAD_SIZE, hparams.wkv_head_size); add_kv(LLM_KV_TOKENIZER_MODEL, vocab.get_tokenizer_model()); @@ -260,15 +322,39 @@ void llama_model_saver::add_kv_from_model() { // TODO: implement LoRA support // add_kv(LLM_KV_ADAPTER_TYPE, ???); // add_kv(LLM_KV_ADAPTER_LORA_ALPHA, ???); + // add_kv(LLM_KV_ADAPTER_LORA_TASK_NAME, ???); + // add_kv(LLM_KV_ADAPTER_LORA_PROMPT_PREFIX, ???); + // add_kv(LLM_KV_ADAPTER_ALORA_INVOCATION_TOKENS, ???); + + add_kv(LLM_KV_POSNET_EMBEDDING_LENGTH, hparams.posnet.n_embd); + add_kv(LLM_KV_POSNET_BLOCK_COUNT, hparams.posnet.n_layer); + + add_kv(LLM_KV_CONVNEXT_EMBEDDING_LENGTH, hparams.convnext.n_embd); + add_kv(LLM_KV_CONVNEXT_BLOCK_COUNT, hparams.convnext.n_layer); + + add_kv(LLM_KV_CLASSIFIER_OUTPUT_LABELS, model->classifier_labels); + + add_kv(LLM_KV_SHORTCONV_L_CACHE, hparams.n_shortconv_l_cache); + + add_kv(LLM_KV_XIELU_ALPHA_N, hparams.xielu_alpha_n); + add_kv(LLM_KV_XIELU_ALPHA_P, hparams.xielu_alpha_p); + add_kv(LLM_KV_XIELU_BETA, hparams.xielu_beta); + add_kv(LLM_KV_XIELU_EPS, hparams.xielu_eps); // deprecated // add_kv(LLM_KV_TOKENIZER_PREFIX_ID, ???); // add_kv(LLM_KV_TOKENIZER_SUFFIX_ID, ???); // add_kv(LLM_KV_TOKENIZER_MIDDLE_ID, ???); + + add_kv(LLM_KV_DENSE_2_FEAT_IN, hparams.dense_2_feat_in); + add_kv(LLM_KV_DENSE_2_FEAT_OUT, hparams.dense_2_feat_out); + add_kv(LLM_KV_DENSE_3_FEAT_IN, hparams.dense_3_feat_in); + add_kv(LLM_KV_DENSE_3_FEAT_OUT, hparams.dense_3_feat_out); } void llama_model_saver::add_tensors_from_model() { - if (std::string(model->output->name) != std::string(model->tok_embd->name)) { + if (model->output != nullptr && + std::string(model->output->name) != std::string(model->tok_embd->name)) { add_tensor(model->tok_embd); // some models use the same tensor for tok_embd and output } add_tensor(model->type_embd); diff --git a/src/llama-model.cpp b/src/llama-model.cpp index e8e1bbf1cd..7ea698b0fd 100644 --- a/src/llama-model.cpp +++ b/src/llama-model.cpp @@ -1623,7 +1623,7 @@ void llama_model::load_hparams(llama_model_loader & ml) { // (optional) temperature tuning - used by mistral-large ml.get_key(LLM_KV_ATTENTION_TEMPERATURE_SCALE, hparams.f_attn_temp_scale, false); - ml.get_key(LLM_KV_ATTENTION_TEMPERATURE_LENGTH, hparams.n_attn_temp_floor_scale, false); + ml.get_key(LLM_KV_ATTENTION_TEMPERATURE_LENGTH, hparams.n_attn_temp_floor_scale, false); // FIXME why not use temperature_length? hparams.f_attn_temp_offset = 0.0f; @@ -7446,6 +7446,7 @@ bool llama_model::load_tensors(llama_model_loader & ml) { // generic pass: load optional per-tensor/per-expert ".scale" tensors (e.g. NVFP4 scale2) // this avoids having to add scale loading to every architecture + if (arch != LLM_ARCH_T5) { for (int i = 0; i < n_layer; ++i) { auto & layer = layers[i]; @@ -7512,6 +7513,7 @@ bool llama_model::load_tensors(llama_model_loader & ml) { } } } + } ml.done_getting_tensors(); diff --git a/tests/test-llama-archs.cpp b/tests/test-llama-archs.cpp index 014b3f2b14..0d490f8e7b 100644 --- a/tests/test-llama-archs.cpp +++ b/tests/test-llama-archs.cpp @@ -90,6 +90,7 @@ static gguf_context_ptr get_gguf_ctx(const llm_arch arch, const bool moe) { n_embd = 64; n_head = 1; n_ff = 96; + n_layer = 22; // hparams.n_layer_kv_from_start = 20 is hardcoded } else if (arch == LLM_ARCH_DEEPSEEK2 || arch == LLM_ARCH_GLM_DSA || arch == LLM_ARCH_KIMI_LINEAR) { n_embd = 128; n_head = 1; @@ -98,8 +99,6 @@ static gguf_context_ptr get_gguf_ctx(const llm_arch arch, const bool moe) { n_layer = 3; } else if (arch == LLM_ARCH_CHAMELEON) { n_vocab = 10240; - } else if (arch == LLM_ARCH_GEMMA3N) { - n_layer = 22; // hparams.n_layer_kv_from_start = 20 is hardcoded } const uint32_t n_embd_head = n_embd / n_head; @@ -344,7 +343,6 @@ static bool moe_implemented(const llm_arch arch) { } static int save_models(const llm_arch target_arch, const size_t seed, const ggml_log_level log_level, const std::string & dir) { - GGML_ABORT("llama_model_save_to_file is broken"); struct user_data_t { struct { ggml_log_callback callback; @@ -369,6 +367,16 @@ static int save_models(const llm_arch target_arch, const size_t seed, const ggml if (arch == LLM_ARCH_CLIP || arch == LLM_ARCH_GPTJ || arch == LLM_ARCH_UNKNOWN) { continue; // These models don't have usable implementations. } + if (arch == LLM_ARCH_RWKV6 || arch == LLM_ARCH_RWKV6QWEN2 || arch == LLM_ARCH_RWKV7 || arch == LLM_ARCH_ARWKV7) { + continue; // FIXME + } + if (arch == LLM_ARCH_BERT || arch == LLM_ARCH_MODERN_BERT || arch == LLM_ARCH_NOMIC_BERT || arch == LLM_ARCH_NOMIC_BERT_MOE || + arch == LLM_ARCH_NEO_BERT || arch == LLM_ARCH_JINA_BERT_V2 || arch == LLM_ARCH_JINA_BERT_V3 || arch == LLM_ARCH_EUROBERT) { + continue; // TODO vocab + } + if (arch == LLM_ARCH_PLM) { + continue; // TODO tensor shapes + } for (bool moe : {false, true}) { if (moe && !moe_implemented(arch)) { continue;