From 9a1d4cea760112290ba9b304c4ab95a156056bdf Mon Sep 17 00:00:00 2001 From: Baolin Peng Date: Tue, 18 Oct 2022 21:54:09 +0000 Subject: [PATCH] Upload T5ForConditionalGeneration --- config.json | 60 +++++++++++++++++++++++++++++++++++++++++++++++ pytorch_model.bin | 3 +++ 2 files changed, 63 insertions(+) create mode 100644 config.json create mode 100644 pytorch_model.bin diff --git a/config.json b/config.json new file mode 100644 index 0000000..8ca94a3 --- /dev/null +++ b/config.json @@ -0,0 +1,60 @@ +{ + "_name_or_path": "GODEL-v1_1-base-seq2seq", + "architectures": [ + "T5ForConditionalGeneration" + ], + "d_ff": 3072, + "d_kv": 64, + "d_model": 768, + "decoder_start_token_id": 0, + "dense_act_fn": "relu", + "dropout_rate": 0.1, + "eos_token_id": 1, + "feed_forward_proj": "relu", + "initializer_factor": 1.0, + "is_encoder_decoder": true, + "is_gated_act": false, + "layer_norm_epsilon": 1e-06, + "model_type": "t5", + "n_positions": 512, + "num_decoder_layers": 12, + "num_heads": 12, + "num_layers": 12, + "output_past": true, + "pad_token_id": 0, + "relative_attention_max_distance": 128, + "relative_attention_num_buckets": 32, + "task_specific_params": { + "summarization": { + "early_stopping": true, + "length_penalty": 2.0, + "max_length": 200, + "min_length": 30, + "no_repeat_ngram_size": 3, + "num_beams": 4, + "prefix": "summarize: " + }, + "translation_en_to_de": { + "early_stopping": true, + "max_length": 300, + "num_beams": 4, + "prefix": "translate English to German: " + }, + "translation_en_to_fr": { + "early_stopping": true, + "max_length": 300, + "num_beams": 4, + "prefix": "translate English to French: " + }, + "translation_en_to_ro": { + "early_stopping": true, + "max_length": 300, + "num_beams": 4, + "prefix": "translate English to Romanian: " + } + }, + "torch_dtype": "float32", + "transformers_version": "4.22.2", + "use_cache": true, + "vocab_size": 32102 +} diff --git a/pytorch_model.bin b/pytorch_model.bin new file mode 100644 index 0000000..af48e08 --- /dev/null +++ b/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a26c5f1db9a8399547cc2fcd4166db600a4ea945dd43c91a08745355d2d6b72c +size 891617279