model : Granite Embedding support (#15641)
ModernBERT but without `head.norm` so will currently fail to convert and run any other ModernBERT models, PRs with `head.norm` support welcome! * constants and tensor mappings for modern bert support, model not supported yet but working on getting conversion to work for encoder only * conversion now working, hf -> gguf * working on support, now working on building graph * some cleanup * cleanup * continuing * correct tensor shape for qkv * fixed tensor mappings and working on buildin graph * tensor debugging now works -> (llama-eval-callback), instead of simulated gate split with views, GEGLU is now used which does exactly this * cleanup * cleanup * cleanup * more cleanup * ubatch issues, the assert for checking equal seqs in llama-graph.cpp when building attention keeps failing, setting ubatch size to 1 when running llama-embedding with --ubatch-size 1 makes it work, but needs to be looked into more * added cls token per previous modern bert attempt, still working on checking out the rest * fixed pre tokenizer and still working through previous pr * working through previous attemp, implimented more accurate conversion per previous attempt, added local sliding window attention that alternates every third layer * fixed pre tokenizer * working on swa with local and global alternating attention * some cleanup and now fails on build attn * starting to work, and some cleanup, currently failing on last layer construction in graph build * alternating rope implemented and modern bert graph build succeeds * fixed asser for equal ubatch seq * cleanup * added mask check in vocab * fixed alternating rope, the hparams.rope_freq_base_train and hparams.rope_freq_base_train_swa were the same and i set them to correct values * reuse variable * removed repeat * standard swa method can be used instead of a new enum being LLAMA_SWA_TYPE_LOCAL * correct swa layer indexing, is supposed to be 0, 3, 6 ... instead of 1, 4, 7 ... * more modular hparam setting * replaced attn out norm with ffn_norm and cosine similarity between hf embds and llama.cpp embds went way up, from 0.05 to 0.24, replaced the cacheless kv with swa todo per the previous conversion * Update gguf-py/gguf/tensor_mapping.py Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update convert_hf_to_gguf_update.py Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update src/llama-model.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update src/llama-vocab.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update src/llama-model.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update gguf-py/gguf/tensor_mapping.py Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update convert_hf_to_gguf.py Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update gguf-py/gguf/tensor_mapping.py Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update gguf-py/gguf/tensor_mapping.py Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update convert_hf_to_gguf.py Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update gguf-py/gguf/tensor_mapping.py Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update gguf-py/gguf/tensor_mapping.py Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update gguf-py/gguf/tensor_mapping.py Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update gguf-py/gguf/tensor_mapping.py Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update gguf-py/gguf/tensor_mapping.py Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update gguf-py/gguf/tensor_mapping.py Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update src/llama-graph.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update src/llama-arch.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update src/llama-model.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update src/llama-model.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update src/llama-model.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update src/llama-model.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update src/llama-model.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * removed redundant hparam set * enums for model sizes * conversion for modern-bert model supported rather than just granite-small * Update src/llama-model.cpp Co-authored-by: Gabe Goodhart <ghart@us.ibm.com> * Update src/llama-model.cpp Co-authored-by: Gabe Goodhart <ghart@us.ibm.com> * fixed ordering of enum for freq_base_swa * fixed where I added residual, now gives much much better embeddings~ * readded cacheless logic * removing whitespace * conversion now working for swa pattern - dense every n layers * modern bert put into seperate src file * removing whitespace * fixed whitespace and newline errors in editorconfig job * Update convert_hf_to_gguf.py Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * better naming convention, n_swa_pattern -> swa_period * reusing sliding_window_pattern key rather than making new dense_every_n_layers key, and adding writing and reading support * fixing pyright type-check fail * Update convert_hf_to_gguf.py Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update gguf-py/gguf/gguf_writer.py Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update src/llama-hparams.h Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update src/llama-model-saver.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update src/models/modern-bert.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update src/models/modern-bert.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update src/models/modern-bert.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update gguf-py/gguf/gguf_writer.py Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update src/models/modern-bert.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update src/models/modern-bert.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update src/llama-model.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update src/llama-model-loader.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update src/llama-model-loader.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update src/llama-model-loader.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * added descriptions in llama-model * fixed tensor mappings for conversion * Update src/llama-model.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update src/llama-model.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * mapping name for size * nits * unused --------- Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> Co-authored-by: Gabe Goodhart <ghart@us.ibm.com>
This commit is contained in:
Ryan Mangeno
@@ -31,12 +31,14 @@ const char * llm_type_name(llm_type type) {
|
||||
case LLM_TYPE_17M: return "17M";
|
||||
case LLM_TYPE_22M: return "22M";
|
||||
case LLM_TYPE_33M: return "33M";
|
||||
case LLM_TYPE_47M: return "47M";
|
||||
case LLM_TYPE_60M: return "60M";
|
||||
case LLM_TYPE_70M: return "70M";
|
||||
case LLM_TYPE_80M: return "80M";
|
||||
case LLM_TYPE_109M: return "109M";
|
||||
case LLM_TYPE_137M: return "137M";
|
||||
case LLM_TYPE_140M: return "140M";
|
||||
case LLM_TYPE_149M: return "149M";
|
||||
case LLM_TYPE_160M: return "160M";
|
||||
case LLM_TYPE_190M: return "190M";
|
||||
case LLM_TYPE_220M: return "220M";
|
||||
@@ -46,6 +48,7 @@ const char * llm_type_name(llm_type type) {
|
||||
case LLM_TYPE_335M: return "335M";
|
||||
case LLM_TYPE_350M: return "350M";
|
||||
case LLM_TYPE_360M: return "360M";
|
||||
case LLM_TYPE_395M: return "395M";
|
||||
case LLM_TYPE_410M: return "410M";
|
||||
case LLM_TYPE_450M: return "450M";
|
||||
case LLM_TYPE_475M: return "475M";
|
||||
@@ -875,6 +878,34 @@ void llama_model::load_hparams(llama_model_loader & ml) {
|
||||
default: type = LLM_TYPE_UNKNOWN;
|
||||
}
|
||||
} break;
|
||||
case LLM_ARCH_MODERN_BERT:
|
||||
{
|
||||
const bool found_swa = ml.get_key(LLM_KV_ATTENTION_SLIDING_WINDOW, hparams.n_swa, false);
|
||||
if (found_swa && hparams.n_swa > 0) {
|
||||
uint32_t swa_period = 3;
|
||||
hparams.swa_type = LLAMA_SWA_TYPE_SYMMETRIC;
|
||||
|
||||
ml.get_key(LLM_KV_ROPE_FREQ_BASE_SWA, hparams.rope_freq_base_train_swa);
|
||||
ml.get_key_or_arr(LLM_KV_ATTENTION_SLIDING_WINDOW_PATTERN, swa_period, false);
|
||||
hparams.set_swa_pattern(swa_period);
|
||||
} else {
|
||||
hparams.swa_type = LLAMA_SWA_TYPE_NONE;
|
||||
}
|
||||
|
||||
ml.get_key(LLM_KV_ATTENTION_LAYERNORM_EPS, hparams.f_norm_eps);
|
||||
ml.get_key(LLM_KV_ATTENTION_CAUSAL, hparams.causal_attn);
|
||||
ml.get_key(LLM_KV_POOLING_TYPE, hparams.pooling_type, false);
|
||||
|
||||
switch (hparams.n_layer) {
|
||||
case 12:
|
||||
type = LLM_TYPE_47M; break; // granite-embedding-small
|
||||
case 22:
|
||||
type = LLM_TYPE_149M; break; // modern-bert-base
|
||||
case 28:
|
||||
type = LLM_TYPE_395M; break; // modern-bert-large
|
||||
default: type = LLM_TYPE_UNKNOWN;
|
||||
}
|
||||
} break;
|
||||
case LLM_ARCH_JINA_BERT_V2:
|
||||
{
|
||||
ml.get_key(LLM_KV_ATTENTION_LAYERNORM_EPS, hparams.f_norm_eps);
|
||||
@@ -3155,6 +3186,37 @@ bool llama_model::load_tensors(llama_model_loader & ml) {
|
||||
layer.layer_out_norm_b = create_tensor(tn(LLM_TENSOR_LAYER_OUT_NORM, "bias", i), {n_embd}, 0);
|
||||
}
|
||||
} break;
|
||||
case LLM_ARCH_MODERN_BERT:
|
||||
{
|
||||
tok_embd = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, 0);
|
||||
tok_norm = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD_NORM, "weight"), {n_embd}, 0);
|
||||
|
||||
output_norm = create_tensor(tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}, 0);
|
||||
|
||||
for(int i = 0; i < n_layer; ++i) {
|
||||
auto& layer = layers[i];
|
||||
|
||||
if ( i != 0 ) {
|
||||
layer.attn_norm = create_tensor(tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}, 0);
|
||||
} else{
|
||||
// layer 0 uses identity
|
||||
layer.attn_norm = create_tensor(tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}, TENSOR_NOT_REQUIRED);
|
||||
}
|
||||
|
||||
|
||||
layer.wqkv = create_tensor(tn(LLM_TENSOR_ATTN_QKV, "weight", i), {n_embd, 3 * n_embd }, 0);
|
||||
layer.wo = create_tensor(tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}, 0);
|
||||
|
||||
layer.ffn_up = create_tensor(tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, 2 * n_ff}, 0);
|
||||
layer.ffn_down = create_tensor(tn(LLM_TENSOR_FFN_DOWN, "weight", i), {n_ff, n_embd}, 0);
|
||||
layer.ffn_norm = create_tensor(tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}, 0);
|
||||
}
|
||||
|
||||
cls = create_tensor(tn(LLM_TENSOR_CLS, "weight"), {n_embd, n_embd}, TENSOR_NOT_REQUIRED);
|
||||
cls_out = create_tensor(tn(LLM_TENSOR_CLS_OUT, "weight"), {n_embd, hparams.n_cls_out}, TENSOR_NOT_REQUIRED);
|
||||
cls_out_b = create_tensor(tn(LLM_TENSOR_CLS_OUT, "bias"), {hparams.n_cls_out}, TENSOR_NOT_REQUIRED);
|
||||
|
||||
} break;
|
||||
case LLM_ARCH_NEO_BERT:
|
||||
{
|
||||
tok_embd = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, 0);
|
||||
@@ -7089,6 +7151,7 @@ llama_memory_i * llama_model::create_memory(const llama_memory_params & params,
|
||||
case LLM_ARCH_NOMIC_BERT_MOE:
|
||||
case LLM_ARCH_NEO_BERT:
|
||||
case LLM_ARCH_WAVTOKENIZER_DEC:
|
||||
case LLM_ARCH_MODERN_BERT:
|
||||
case LLM_ARCH_GEMMA_EMBEDDING:
|
||||
case LLM_ARCH_DREAM:
|
||||
case LLM_ARCH_LLADA:
|
||||
@@ -7248,6 +7311,10 @@ ggml_cgraph * llama_model::build_graph(const llm_graph_params & params) const {
|
||||
{
|
||||
llm = std::make_unique<llm_build_bert>(*this, params);
|
||||
} break;
|
||||
case LLM_ARCH_MODERN_BERT:
|
||||
{
|
||||
llm = std::make_unique<llm_build_modern_bert<true>>(*this, params);
|
||||
} break;
|
||||
case LLM_ARCH_NEO_BERT:
|
||||
{
|
||||
llm = std::make_unique<llm_build_neo_bert>(*this, params);
|
||||
@@ -7816,6 +7883,7 @@ llama_rope_type llama_model_rope_type(const llama_model * model) {
|
||||
case LLM_ARCH_DBRX:
|
||||
case LLM_ARCH_BERT:
|
||||
case LLM_ARCH_JINA_BERT_V3:
|
||||
case LLM_ARCH_MODERN_BERT:
|
||||
case LLM_ARCH_NOMIC_BERT:
|
||||
case LLM_ARCH_NOMIC_BERT_MOE:
|
||||
case LLM_ARCH_STABLELM:
|
||||
|
||||
Reference in New Issue
Block a user