vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Inference support for T5 and FLAN-T5 model families (#5763)

Browse source 
* llama : add inference support and model types for T5 and FLAN-T5 model families

* llama : add new API functions to support encoder-decoder models: llama_encode(), llama_model_has_encoder(), llama_model_decoder_start_token()

* common, llama-cli, llama-batched : add support for encoder-decoder models

* convert-hf : handle shared token embeddings tensors in T5Model

* convert-hf : add support for SentencePiece BPE tokenizer in T5Model (for Pile-T5 models)

* convert-hf : add MT5ForConditionalGeneration and UMT5ForConditionalGeneration to architectures supported by T5Model

* convert : add t5 tokenizer tests, use "slow" HF tokenizer for t5

---------

Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
fairydreaming 2024-07-04 15:46:11 +02:00 • committed by GitHub
parent f8c4c0738d
commit 807b0c49ff
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
33 changed files with 946 additions and 31 deletions
Download patch file Download diff file Expand all files Collapse all files

34
examples/batched/batched.cpp
View file

@ -93,14 +93,34 @@ int main(int argc, char ** argv) {
// create a llama_batch
// we use this object to submit token data for decoding
llama_batch batch = llama_batch_init(std::max(tokens_list.size(), (size_t)n_parallel), 0, 1);
llama_batch batch = llama_batch_init(std::max(tokens_list.size(), (size_t) n_parallel), 0, n_parallel);
std::vector<llama_seq_id> seq_ids(n_parallel, 0);
for (int32_t i = 0; i < n_parallel; ++i) {
seq_ids[i] = i;
}
// evaluate the initial prompt
for (size_t i = 0; i < tokens_list.size(); ++i) {
llama_batch_add(batch, tokens_list[i], i, { 0 }, false);
llama_batch_add(batch, tokens_list[i], i, seq_ids, false);
}
GGML_ASSERT(batch.n_tokens == (int) tokens_list.size());
if (llama_model_has_encoder(model)) {
if (llama_encode(ctx, batch)) {
LOG_TEE("%s : failed to eval\n", __func__);
return 1;
}
llama_token decoder_start_token_id = llama_model_decoder_start_token(model);
if (decoder_start_token_id == -1) {
decoder_start_token_id = llama_token_bos(model);
}
llama_batch_clear(batch);
llama_batch_add(batch, decoder_start_token_id, 0, seq_ids, false);
}
// llama_decode will output logits only for the last token of the prompt
batch.logits[batch.n_tokens - 1] = true;
@ -109,11 +129,11 @@ int main(int argc, char ** argv) {
return 1;
}
// assign the system KV cache to all parallel sequences
// this way, the parallel sequences will "reuse" the prompt tokens without having to copy them
for (int32_t i = 1; i < n_parallel; ++i) {
llama_kv_cache_seq_cp(ctx, 0, i, -1, -1);
}
//// assign the system KV cache to all parallel sequences
//// this way, the parallel sequences will "reuse" the prompt tokens without having to copy them
//for (int32_t i = 1; i < n_parallel; ++i) {
// llama_kv_cache_seq_cp(ctx, 0, i, -1, -1);
//}
if (n_parallel > 1) {
LOG_TEE("\n\n%s: generating %d sequences ...\n", __func__, n_parallel);

22
examples/main/main.cpp
View file

@ -255,7 +255,9 @@ int main(int argc, char ** argv) {
}
const bool add_bos = llama_should_add_bos_token(model);
GGML_ASSERT(llama_add_eos_token(model) != 1);
if (!llama_model_has_encoder(model)) {
GGML_ASSERT(llama_add_eos_token(model) != 1);
}
LOG("add_bos: %d\n", add_bos);
std::vector<llama_token> embd_inp;
@ -517,6 +519,24 @@ int main(int argc, char ** argv) {
exit(1);
}
if (llama_model_has_encoder(model)) {
int enc_input_size = embd_inp.size();
llama_token * enc_input_buf = embd_inp.data();
if (llama_encode(ctx, llama_batch_get_one(enc_input_buf, enc_input_size, 0, 0))) {
LOG_TEE("%s : failed to eval\n", __func__);
return 1;
}
llama_token decoder_start_token_id = llama_model_decoder_start_token(model);
if (decoder_start_token_id == -1) {
decoder_start_token_id = llama_token_bos(model);
}
embd_inp.clear();
embd_inp.push_back(decoder_start_token_id);
}
while ((n_remain != 0 && !is_antiprompt) || params.interactive) {
// predict
if (!embd.empty()) {