Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,6 @@ 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
+trt_engines.b128/unimernet/1-gpu/bfloat16/decoder/rank0.engine filter=lfs diff=lfs merge=lfs -text
+trt_engines.b128/vision_encoder/model.engine filter=lfs diff=lfs merge=lfs -text
+trt_engines.b256/unimernet/1-gpu/bfloat16/decoder/rank0.engine filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,193 @@
+{
+  "architectures": [
+    "VisionEncoderDecoderModel"
+  ],
+  "decoder": {
+    "_name_or_path": "",
+    "activation_dropout": 0.0,
+    "activation_function": "gelu",
+    "add_cross_attention": true,
+    "add_final_layer_norm": true,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": 0.0,
+    "cross_attention_hidden_size": null,
+    "d_model": 1024,
+    "decoder_attention_heads": 16,
+    "decoder_ffn_dim": 4096,
+    "decoder_layerdrop": 0.0,
+    "decoder_layers": 8,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.1,
+    "early_stopping": false,
+    "encoder_attention_heads": 16,
+    "encoder_ffn_dim": 4096,
+    "encoder_layerdrop": 0.0,
+    "encoder_layers": 12,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": 2,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "init_std": 0.02,
+    "is_decoder": true,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 1536,
+    "min_length": 0,
+    "model_type": "mbart",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 1,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "scale_embedding": true,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": false,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 50000
+  },
+  "decoder_start_token_id": 0,
+  "encoder": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_probs_dropout_prob": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "depths": [
+      2,
+      2,
+      14,
+      2
+    ],
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "drop_path_rate": 0.1,
+    "early_stopping": false,
+    "embed_dim": 128,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.0,
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": [
+      420,
+      420
+    ],
+    "initializer_range": 0.02,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "mlp_ratio": 4.0,
+    "model_type": "donut-swin",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_heads": [
+      4,
+      8,
+      16,
+      32
+    ],
+    "num_layers": 4,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 4,
+    "path_norm": true,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "qkv_bias": true,
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_2d_embeddings": false,
+    "use_absolute_embeddings": false,
+    "use_bfloat16": false,
+    "window_size": 5
+  },
+  "eos_token_id": 2,
+  "is_encoder_decoder": true,
+  "model_type": "vision-encoder-decoder",
+  "pad_token_id": 1,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.0"
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.40.0"
+}

preprocessor_config.json

@@ -0,0 +1,36 @@
+{
+  "do_align_long_axis": false,
+  "do_normalize": false,
+  "do_pad": false,
+  "do_rescale": false,
+  "do_resize": false,
+  "do_thumbnail": false,
+  "feature_extractor_type": "DonutFeatureExtractor",
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "VariableDonutImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "max_size": {
+    "height": 192,
+    "width": 672
+  },
+  "patch_size": [
+    4,
+    4
+  ],
+  "processor_class": "VariableDonutProcessor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": [
+    192,
+    672
+  ],
+  "train": false
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:019ec971608d141cedb03934ac9849e8cd2e9be30dc481f0d63e41b7fcb1473c
+size 1250082554

tokenizer_config.json

@@ -0,0 +1,205 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[START_REF]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "[END_REF]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "[IMAGE]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<fragments>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "</fragments>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<work>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "</work>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "[START_SUP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "[END_SUP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "[START_SUB]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "[END_SUB]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "[START_DNA]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "[END_DNA]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "17": {
+      "content": "[START_AMINO]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "18": {
+      "content": "[END_AMINO]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "19": {
+      "content": "[START_SMILES]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "20": {
+      "content": "[END_SMILES]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "21": {
+      "content": "[START_I_SMILES]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "22": {
+      "content": "[END_I_SMILES]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "max_length": 4096,
+  "model_max_length": 768,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "processor_class": "VariableDonutProcessor",
+  "stride": 0,
+  "tokenizer_class": "NougatTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>",
+  "vocab_file": null
+}

trt_engines.b128/unimernet/1-gpu/bfloat16/decoder/config.json

@@ -0,0 +1,168 @@
+{
+    "version": "0.12.0",
+    "pretrained_config": {
+        "architecture": "DecoderModel",
+        "dtype": "bfloat16",
+        "vocab_size": 50000,
+        "hidden_size": 1024,
+        "num_hidden_layers": 8,
+        "num_attention_heads": 16,
+        "hidden_act": "gelu",
+        "logits_dtype": "float32",
+        "norm_epsilon": false,
+        "position_embedding_type": "learned_absolute",
+        "max_position_embeddings": 1536,
+        "num_key_value_heads": 16,
+        "intermediate_size": 4096,
+        "mapping": {
+            "world_size": 1,
+            "gpus_per_node": 8,
+            "cp_size": 1,
+            "tp_size": 1,
+            "pp_size": 1,
+            "moe_tp_size": 1,
+            "moe_ep_size": 1
+        },
+        "quantization": {
+            "quant_algo": null,
+            "kv_cache_quant_algo": null,
+            "group_size": 128,
+            "smoothquant_val": 0.5,
+            "clamp_val": null,
+            "has_zero_point": false,
+            "pre_quant_scale": false,
+            "exclude_modules": null
+        },
+        "use_parallel_embedding": false,
+        "embedding_sharding_dim": 0,
+        "share_embedding_table": false,
+        "head_size": 64,
+        "qk_layernorm": false,
+        "has_position_embedding": true,
+        "layernorm_type": 0,
+        "has_attention_qkvo_bias": true,
+        "has_mlp_bias": true,
+        "has_model_final_layernorm": true,
+        "has_embedding_layernorm": true,
+        "has_embedding_scale": true,
+        "q_scaling": 1.0,
+        "layernorm_position": 0,
+        "mlp_type": 0,
+        "relative_attention": false,
+        "max_distance": 0,
+        "num_buckets": 0,
+        "model_type": "bart",
+        "rescale_before_lm_head": false,
+        "encoder_hidden_size": 1024,
+        "encoder_num_heads": 16,
+        "encoder_head_size": 64,
+        "skip_cross_qkv": false,
+        "use_implicit_relative_attention": false,
+        "decoder_start_token_id": null,
+        "eos_token_id": 2,
+        "bos_token_id": 0,
+        "pad_token_id": 1,
+        "gated_act": false,
+        "type_vocab_size": null,
+        "encoder_num_kv_heads": null,
+        "residual_scaling": 1.0,
+        "has_lm_head_bias": false
+    },
+    "build_config": {
+        "max_input_len": 1,
+        "max_seq_len": 101,
+        "opt_batch_size": null,
+        "max_batch_size": 128,
+        "max_beam_width": 1,
+        "max_num_tokens": 8192,
+        "opt_num_tokens": 128,
+        "max_prompt_embedding_table_size": 0,
+        "gather_context_logits": false,
+        "gather_generation_logits": false,
+        "strongly_typed": true,
+        "builder_opt": null,
+        "force_num_profiles": null,
+        "profiling_verbosity": "layer_names_only",
+        "enable_debug_output": false,
+        "max_draft_len": 0,
+        "speculative_decoding_mode": 1,
+        "use_refit": false,
+        "input_timing_cache": null,
+        "output_timing_cache": "model.cache",
+        "lora_config": {
+            "lora_dir": [],
+            "lora_ckpt_source": "hf",
+            "max_lora_rank": 64,
+            "lora_target_modules": [],
+            "trtllm_modules_to_hf_modules": {}
+        },
+        "auto_parallel_config": {
+            "world_size": 1,
+            "gpus_per_node": 8,
+            "cluster_key": "A100-SXM-80GB",
+            "cluster_info": null,
+            "sharding_cost_model": "alpha_beta",
+            "comm_cost_model": "alpha_beta",
+            "enable_pipeline_parallelism": false,
+            "enable_shard_unbalanced_shape": false,
+            "enable_shard_dynamic_shape": false,
+            "enable_reduce_scatter": true,
+            "builder_flags": null,
+            "debug_mode": false,
+            "infer_shape": true,
+            "validation_mode": false,
+            "same_buffer_io": {
+                "past_key_value_(\\d+)": "present_key_value_\\1"
+            },
+            "same_spec_io": {},
+            "sharded_io_allowlist": [
+                "past_key_value_\\d+",
+                "present_key_value_\\d*"
+            ],
+            "fill_weights": false,
+            "parallel_config_cache": null,
+            "profile_cache": null,
+            "dump_path": null,
+            "debug_outputs": []
+        },
+        "weight_sparsity": false,
+        "weight_streaming": false,
+        "plugin_config": {
+            "dtype": "bfloat16",
+            "bert_attention_plugin": "bfloat16",
+            "gpt_attention_plugin": "bfloat16",
+            "gemm_plugin": "bfloat16",
+            "gemm_swiglu_plugin": null,
+            "fp8_rowwise_gemm_plugin": null,
+            "smooth_quant_gemm_plugin": null,
+            "identity_plugin": null,
+            "layernorm_quantization_plugin": null,
+            "rmsnorm_quantization_plugin": null,
+            "nccl_plugin": null,
+            "lookup_plugin": null,
+            "lora_plugin": null,
+            "weight_only_groupwise_quant_matmul_plugin": null,
+            "weight_only_quant_matmul_plugin": null,
+            "quantize_per_token_plugin": false,
+            "quantize_tensor_plugin": false,
+            "moe_plugin": null,
+            "mamba_conv1d_plugin": "auto",
+            "context_fmha": true,
+            "bert_context_fmha_fp32_acc": false,
+            "paged_kv_cache": false,
+            "remove_input_padding": true,
+            "reduce_fusion": false,
+            "enable_xqa": false,
+            "tokens_per_block": 64,
+            "use_paged_context_fmha": false,
+            "use_fp8_context_fmha": false,
+            "multiple_profiles": false,
+            "paged_state": true,
+            "streamingllm": false,
+            "manage_weights": false
+        },
+        "use_strip_plan": false,
+        "max_encoder_input_len": 588,
+        "use_fused_mlp": false
+    }
+}

trt_engines.b128/unimernet/1-gpu/bfloat16/decoder/rank0.engine

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e811e7cbed5b7ef98b7f8d396335c2364b678f76f35925c46cb6ac9c50602c6e
+size 478817308

trt_engines.b128/vision_encoder/config.json

@@ -0,0 +1,12 @@
+{
+  "builder_config": {
+    "force_num_profiles": null,
+    "int8": false,
+    "model_type": "nougat",
+    "precision": "float16",
+    "strongly_typed": false,
+    "tensor_parallel": 1,
+    "use_refit": false,
+    "use_strip_plan": false
+  }
+}

trt_engines.b128/vision_encoder/model.engine

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0cac0bde6aecfc15cb458ef9d23045a10d8248b3eff614dfba4878758a32ea4
+size 159963300

trt_engines.b256/unimernet/1-gpu/bfloat16/decoder/config.json

@@ -0,0 +1,168 @@
+{
+    "version": "0.12.0",
+    "pretrained_config": {
+        "architecture": "DecoderModel",
+        "dtype": "bfloat16",
+        "vocab_size": 50000,
+        "hidden_size": 1024,
+        "num_hidden_layers": 8,
+        "num_attention_heads": 16,
+        "hidden_act": "gelu",
+        "logits_dtype": "float32",
+        "norm_epsilon": false,
+        "position_embedding_type": "learned_absolute",
+        "max_position_embeddings": 1536,
+        "num_key_value_heads": 16,
+        "intermediate_size": 4096,
+        "mapping": {
+            "world_size": 1,
+            "gpus_per_node": 8,
+            "cp_size": 1,
+            "tp_size": 1,
+            "pp_size": 1,
+            "moe_tp_size": 1,
+            "moe_ep_size": 1
+        },
+        "quantization": {
+            "quant_algo": null,
+            "kv_cache_quant_algo": null,
+            "group_size": 128,
+            "smoothquant_val": 0.5,
+            "clamp_val": null,
+            "has_zero_point": false,
+            "pre_quant_scale": false,
+            "exclude_modules": null
+        },
+        "use_parallel_embedding": false,
+        "embedding_sharding_dim": 0,
+        "share_embedding_table": false,
+        "head_size": 64,
+        "qk_layernorm": false,
+        "has_position_embedding": true,
+        "layernorm_type": 0,
+        "has_attention_qkvo_bias": true,
+        "has_mlp_bias": true,
+        "has_model_final_layernorm": true,
+        "has_embedding_layernorm": true,
+        "has_embedding_scale": true,
+        "q_scaling": 1.0,
+        "layernorm_position": 0,
+        "mlp_type": 0,
+        "relative_attention": false,
+        "max_distance": 0,
+        "num_buckets": 0,
+        "model_type": "bart",
+        "rescale_before_lm_head": false,
+        "encoder_hidden_size": 1024,
+        "encoder_num_heads": 16,
+        "encoder_head_size": 64,
+        "skip_cross_qkv": false,
+        "use_implicit_relative_attention": false,
+        "decoder_start_token_id": null,
+        "eos_token_id": 2,
+        "bos_token_id": 0,
+        "pad_token_id": 1,
+        "gated_act": false,
+        "type_vocab_size": null,
+        "encoder_num_kv_heads": null,
+        "residual_scaling": 1.0,
+        "has_lm_head_bias": false
+    },
+    "build_config": {
+        "max_input_len": 1,
+        "max_seq_len": 101,
+        "opt_batch_size": null,
+        "max_batch_size": 256,
+        "max_beam_width": 1,
+        "max_num_tokens": 8192,
+        "opt_num_tokens": 256,
+        "max_prompt_embedding_table_size": 0,
+        "gather_context_logits": false,
+        "gather_generation_logits": false,
+        "strongly_typed": true,
+        "builder_opt": null,
+        "force_num_profiles": null,
+        "profiling_verbosity": "layer_names_only",
+        "enable_debug_output": false,
+        "max_draft_len": 0,
+        "speculative_decoding_mode": 1,
+        "use_refit": false,
+        "input_timing_cache": null,
+        "output_timing_cache": "model.cache",
+        "lora_config": {
+            "lora_dir": [],
+            "lora_ckpt_source": "hf",
+            "max_lora_rank": 64,
+            "lora_target_modules": [],
+            "trtllm_modules_to_hf_modules": {}
+        },
+        "auto_parallel_config": {
+            "world_size": 1,
+            "gpus_per_node": 8,
+            "cluster_key": "A100-SXM-80GB",
+            "cluster_info": null,
+            "sharding_cost_model": "alpha_beta",
+            "comm_cost_model": "alpha_beta",
+            "enable_pipeline_parallelism": false,
+            "enable_shard_unbalanced_shape": false,
+            "enable_shard_dynamic_shape": false,
+            "enable_reduce_scatter": true,
+            "builder_flags": null,
+            "debug_mode": false,
+            "infer_shape": true,
+            "validation_mode": false,
+            "same_buffer_io": {
+                "past_key_value_(\\d+)": "present_key_value_\\1"
+            },
+            "same_spec_io": {},
+            "sharded_io_allowlist": [
+                "past_key_value_\\d+",
+                "present_key_value_\\d*"
+            ],
+            "fill_weights": false,
+            "parallel_config_cache": null,
+            "profile_cache": null,
+            "dump_path": null,
+            "debug_outputs": []
+        },
+        "weight_sparsity": false,
+        "weight_streaming": false,
+        "plugin_config": {
+            "dtype": "bfloat16",
+            "bert_attention_plugin": "bfloat16",
+            "gpt_attention_plugin": "bfloat16",
+            "gemm_plugin": "bfloat16",
+            "gemm_swiglu_plugin": null,
+            "fp8_rowwise_gemm_plugin": null,
+            "smooth_quant_gemm_plugin": null,
+            "identity_plugin": null,
+            "layernorm_quantization_plugin": null,
+            "rmsnorm_quantization_plugin": null,
+            "nccl_plugin": null,
+            "lookup_plugin": null,
+            "lora_plugin": null,
+            "weight_only_groupwise_quant_matmul_plugin": null,
+            "weight_only_quant_matmul_plugin": null,
+            "quantize_per_token_plugin": false,
+            "quantize_tensor_plugin": false,
+            "moe_plugin": null,
+            "mamba_conv1d_plugin": "auto",
+            "context_fmha": true,
+            "bert_context_fmha_fp32_acc": false,
+            "paged_kv_cache": false,
+            "remove_input_padding": true,
+            "reduce_fusion": false,
+            "enable_xqa": false,
+            "tokens_per_block": 64,
+            "use_paged_context_fmha": false,
+            "use_fp8_context_fmha": false,
+            "multiple_profiles": false,
+            "paged_state": true,
+            "streamingllm": false,
+            "manage_weights": false
+        },
+        "use_strip_plan": false,
+        "max_encoder_input_len": 588,
+        "use_fused_mlp": false
+    }
+}

trt_engines.b256/unimernet/1-gpu/bfloat16/decoder/rank0.engine

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d009883eed22088756ead8fb02e8371cb850932a9bedfa39482a0b618e993e1
+size 478843092

trt_engines.b256/vision_encoder/onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:608d12681a112f8c08aa852a192c1d578cb714d70f1349cecf0de91a54e834e2
+size 151439627

trt_engines/unimernet/bfloat16/decoder/config.json

@@ -0,0 +1,52 @@
+{
+    "architecture": "DecoderModel",
+    "dtype": "bfloat16",
+    "logits_dtype": "float32",
+    "num_hidden_layers": 8,
+    "num_attention_heads": 16,
+    "hidden_size": 1024,
+    "norm_epsilon": false,
+    "vocab_size": 50000,
+    "position_embedding_type": "learned_absolute",
+    "hidden_act": "gelu",
+    "quantization": {
+        "quant_algo": null,
+        "kv_cache_quant_algo": null
+    },
+    "mapping": {
+        "world_size": 1,
+        "tp_size": 1,
+        "pp_size": 1
+    },
+    "use_parallel_embedding": false,
+    "embedding_sharding_dim": 0,
+    "share_embedding_table": false,
+    "max_position_embeddings": 1536,
+    "head_size": 64,
+    "has_position_embedding": true,
+    "layernorm_type": 0,
+    "has_attention_qkvo_bias": true,
+    "has_mlp_bias": true,
+    "has_model_final_layernorm": true,
+    "has_embedding_layernorm": true,
+    "has_embedding_scale": true,
+    "intermediate_size": 4096,
+    "q_scaling": 1.0,
+    "layernorm_position": 0,
+    "mlp_type": 0,
+    "relative_attention": false,
+    "max_distance": 0,
+    "num_buckets": 0,
+    "model_type": "bart",
+    "rescale_before_lm_head": false,
+    "encoder_hidden_size": 1024,
+    "encoder_num_heads": 16,
+    "encoder_head_size": 64,
+    "skip_cross_qkv": false,
+    "use_implicit_relative_attention": false,
+    "decoder_start_token_id": null,
+    "eos_token_id": 2,
+    "bos_token_id": 0,
+    "pad_token_id": 1,
+    "gated_act": false
+}

trt_engines/unimernet/bfloat16/decoder/rank0.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4067d58b32e551833d24b3fa930237904ba68d0d137ff3af46495daf0afa9fee
+size 476717656