Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+decoder/t5-base_float32_tp1_rank0.engine filter=lfs diff=lfs merge=lfs -text
+encoder/t5-base_float32_tp1_rank0.engine filter=lfs diff=lfs merge=lfs -text

.gitattributes copy

@@ -0,0 +1,37 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+encoder/t5-base_float32_tp1_rank0.engine filter=lfs diff=lfs merge=lfs -text
+decoder/t5-base_float32_tp1_rank0.engine filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "j5ng/et5-base",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 3072,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "T5Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.0",
+  "use_cache": true,
+  "vocab_size": 45100
+}

decoder/config.json

@@ -0,0 +1,65 @@
+{
+  "builder_config": {
+    "apply_query_key_layer_scaling": false,
+    "cross_attention": true,
+    "gather_context_logits": false,
+    "gather_generation_logits": false,
+    "gpus_per_node": 8,
+    "has_position_embedding": false,
+    "has_token_type_embedding": false,
+    "head_size": 64,
+    "hf_modules_to_trtllm_modules": null,
+    "hidden_act": "gelu_new",
+    "hidden_size": 768,
+    "int8": false,
+    "lora_target_modules": null,
+    "max_batch_size": 8,
+    "max_beam_width": 5,
+    "max_decoder_input_len": 1,
+    "max_encoder_input_len": 1024,
+    "max_output_len": 256,
+    "max_position_embeddings": 512,
+    "max_prompt_embedding_table_size": 0,
+    "name": "t5-base",
+    "num_heads": 12,
+    "num_layers": 12,
+    "parallel_build": false,
+    "pipeline_parallel": 1,
+    "precision": "float32",
+    "strongly_typed": false,
+    "tensor_parallel": 1,
+    "trtllm_modules_to_hf_modules": null,
+    "use_refit": false,
+    "vocab_size": 45100
+  },
+  "plugin_config": {
+    "attention_qk_half_accumulation": false,
+    "bert_attention_plugin": "float32",
+    "context_fmha": false,
+    "context_fmha_fp32_acc": false,
+    "dense_context_fmha": false,
+    "enable_xqa": false,
+    "gemm_plugin": "float32",
+    "gpt_attention_plugin": "float32",
+    "identity_plugin": null,
+    "layernorm_quantization_plugin": null,
+    "lookup_plugin": null,
+    "lora_plugin": null,
+    "moe_plugin": null,
+    "multi_block_mode": false,
+    "nccl_plugin": null,
+    "paged_kv_cache": false,
+    "pos_shift": false,
+    "quantize_per_token_plugin": false,
+    "quantize_tensor_plugin": false,
+    "remove_input_padding": true,
+    "rmsnorm_quantization_plugin": null,
+    "smooth_quant_gemm_plugin": null,
+    "tokens_per_block": 128,
+    "use_context_fmha_for_generation": false,
+    "use_custom_all_reduce": false,
+    "use_paged_context_fmha": false,
+    "weight_only_groupwise_quant_matmul_plugin": null,
+    "weight_only_quant_matmul_plugin": null
+  }
+}

decoder/t5-base_float32_tp1_rank0.engine

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1669f9928afee144e0affacc725859e021bad453f024babd86db821bbf14a5b
+size 845351052

encoder/config.json

@@ -0,0 +1,65 @@
+{
+  "builder_config": {
+    "apply_query_key_layer_scaling": false,
+    "cross_attention": false,
+    "gather_context_logits": false,
+    "gather_generation_logits": false,
+    "gpus_per_node": 8,
+    "has_position_embedding": false,
+    "has_token_type_embedding": false,
+    "head_size": 64,
+    "hf_modules_to_trtllm_modules": null,
+    "hidden_act": "gelu_new",
+    "hidden_size": 768,
+    "int8": false,
+    "lora_target_modules": null,
+    "max_batch_size": 8,
+    "max_beam_width": 5,
+    "max_decoder_input_len": 1,
+    "max_encoder_input_len": 1024,
+    "max_output_len": 256,
+    "max_position_embeddings": 512,
+    "max_prompt_embedding_table_size": 0,
+    "name": "t5-base",
+    "num_heads": 12,
+    "num_layers": 12,
+    "parallel_build": false,
+    "pipeline_parallel": 1,
+    "precision": "float32",
+    "strongly_typed": false,
+    "tensor_parallel": 1,
+    "trtllm_modules_to_hf_modules": null,
+    "use_refit": false,
+    "vocab_size": 45100
+  },
+  "plugin_config": {
+    "attention_qk_half_accumulation": false,
+    "bert_attention_plugin": "float32",
+    "context_fmha": false,
+    "context_fmha_fp32_acc": false,
+    "dense_context_fmha": false,
+    "enable_xqa": false,
+    "gemm_plugin": "float32",
+    "gpt_attention_plugin": "float32",
+    "identity_plugin": null,
+    "layernorm_quantization_plugin": null,
+    "lookup_plugin": null,
+    "lora_plugin": null,
+    "moe_plugin": null,
+    "multi_block_mode": false,
+    "nccl_plugin": null,
+    "paged_kv_cache": false,
+    "pos_shift": false,
+    "quantize_per_token_plugin": false,
+    "quantize_tensor_plugin": false,
+    "remove_input_padding": true,
+    "rmsnorm_quantization_plugin": null,
+    "smooth_quant_gemm_plugin": null,
+    "tokens_per_block": 128,
+    "use_context_fmha_for_generation": false,
+    "use_custom_all_reduce": false,
+    "use_paged_context_fmha": false,
+    "weight_only_groupwise_quant_matmul_plugin": null,
+    "weight_only_quant_matmul_plugin": null
+  }
+}

encoder/t5-base_float32_tp1_rank0.engine

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c39b63e64e9b3e0551f63266dbfd5ba4e4065d075b5d10018de96d675a5b02b9
+size 592835748

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.28.0"
+}

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ebba0a7b0fadda80677fe980264027fd8c51f822c486201b39dfdfe8804a570
+size 1196021

tokenizer_config.json

@@ -0,0 +1,11 @@
+{
+  "additional_special_tokens": null,
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}