llama.cpp/models
fairydreaming 807b0c49ff
Inference support for T5 and FLAN-T5 model families (#5763)
* 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>
2024-07-04 15:46:11 +02:00
..
.editorconfig
ggml-vocab-aquila.gguf
ggml-vocab-baichuan.gguf
ggml-vocab-bert-bge.gguf
ggml-vocab-bert-bge.gguf.inp Inference support for T5 and FLAN-T5 model families (#5763) 2024-07-04 15:46:11 +02:00
ggml-vocab-bert-bge.gguf.out Inference support for T5 and FLAN-T5 model families (#5763) 2024-07-04 15:46:11 +02:00
ggml-vocab-command-r.gguf
ggml-vocab-command-r.gguf.inp Inference support for T5 and FLAN-T5 model families (#5763) 2024-07-04 15:46:11 +02:00
ggml-vocab-command-r.gguf.out Inference support for T5 and FLAN-T5 model families (#5763) 2024-07-04 15:46:11 +02:00
ggml-vocab-deepseek-coder.gguf
ggml-vocab-deepseek-coder.gguf.inp Inference support for T5 and FLAN-T5 model families (#5763) 2024-07-04 15:46:11 +02:00
ggml-vocab-deepseek-coder.gguf.out Inference support for T5 and FLAN-T5 model families (#5763) 2024-07-04 15:46:11 +02:00
ggml-vocab-deepseek-llm.gguf
ggml-vocab-deepseek-llm.gguf.inp Inference support for T5 and FLAN-T5 model families (#5763) 2024-07-04 15:46:11 +02:00
ggml-vocab-deepseek-llm.gguf.out Inference support for T5 and FLAN-T5 model families (#5763) 2024-07-04 15:46:11 +02:00
ggml-vocab-falcon.gguf
ggml-vocab-falcon.gguf.inp Inference support for T5 and FLAN-T5 model families (#5763) 2024-07-04 15:46:11 +02:00
ggml-vocab-falcon.gguf.out Inference support for T5 and FLAN-T5 model families (#5763) 2024-07-04 15:46:11 +02:00
ggml-vocab-gpt2.gguf
ggml-vocab-gpt-2.gguf
ggml-vocab-gpt-2.gguf.inp Inference support for T5 and FLAN-T5 model families (#5763) 2024-07-04 15:46:11 +02:00
ggml-vocab-gpt-2.gguf.out Inference support for T5 and FLAN-T5 model families (#5763) 2024-07-04 15:46:11 +02:00
ggml-vocab-gpt-neox.gguf
ggml-vocab-llama-bpe.gguf
ggml-vocab-llama-bpe.gguf.inp Inference support for T5 and FLAN-T5 model families (#5763) 2024-07-04 15:46:11 +02:00
ggml-vocab-llama-bpe.gguf.out Inference support for T5 and FLAN-T5 model families (#5763) 2024-07-04 15:46:11 +02:00
ggml-vocab-llama-spm.gguf
ggml-vocab-llama-spm.gguf.inp Inference support for T5 and FLAN-T5 model families (#5763) 2024-07-04 15:46:11 +02:00
ggml-vocab-llama-spm.gguf.out Inference support for T5 and FLAN-T5 model families (#5763) 2024-07-04 15:46:11 +02:00
ggml-vocab-mpt.gguf
ggml-vocab-mpt.gguf.inp Inference support for T5 and FLAN-T5 model families (#5763) 2024-07-04 15:46:11 +02:00
ggml-vocab-mpt.gguf.out Inference support for T5 and FLAN-T5 model families (#5763) 2024-07-04 15:46:11 +02:00
ggml-vocab-phi-3.gguf
ggml-vocab-phi-3.gguf.inp Inference support for T5 and FLAN-T5 model families (#5763) 2024-07-04 15:46:11 +02:00
ggml-vocab-phi-3.gguf.out Inference support for T5 and FLAN-T5 model families (#5763) 2024-07-04 15:46:11 +02:00
ggml-vocab-qwen2.gguf
ggml-vocab-qwen2.gguf.inp Inference support for T5 and FLAN-T5 model families (#5763) 2024-07-04 15:46:11 +02:00
ggml-vocab-qwen2.gguf.out Inference support for T5 and FLAN-T5 model families (#5763) 2024-07-04 15:46:11 +02:00
ggml-vocab-refact.gguf
ggml-vocab-refact.gguf.inp Inference support for T5 and FLAN-T5 model families (#5763) 2024-07-04 15:46:11 +02:00
ggml-vocab-refact.gguf.out Inference support for T5 and FLAN-T5 model families (#5763) 2024-07-04 15:46:11 +02:00
ggml-vocab-stablelm.gguf llama : fix BPE pre-tokenization (#6920) 2024-04-29 16:58:41 +03:00
ggml-vocab-starcoder.gguf
ggml-vocab-starcoder.gguf.inp Inference support for T5 and FLAN-T5 model families (#5763) 2024-07-04 15:46:11 +02:00
ggml-vocab-starcoder.gguf.out Inference support for T5 and FLAN-T5 model families (#5763) 2024-07-04 15:46:11 +02:00