Upload initial model version

config.json

@@ -0,0 +1,235 @@
+{
+  "architecture": {
+    "layout": "encoder-decoder",
+    "num_encoder_layers": 2,
+    "num_decoder_layers": 2,
+    "share_weights": false
+  },
+  "attention_blocks": {
+    "encoder_attention": {
+      "attention_type": "full",
+      "num_heads": 4,
+      "dropout": 0.1,
+      "kwargs": {}
+    },
+    "decoder_attention": {
+      "attention_type": "full",
+      "num_heads": 4,
+      "dropout": 0.1,
+      "kwargs": {}
+    },
+    "decoder_cross_attention": {
+      "attention_type": "full",
+      "num_heads": 4,
+      "dropout": 0.1,
+      "kwargs": {}
+    }
+  },
+  "value_embedding_config": {
+    "type": "value",
+    "dropout": 0.1,
+    "embedding_dim": null,
+    "kwargs": {}
+  },
+  "positional_embedding_config": {
+    "type": "stacked_embedding",
+    "dropout": 0.1,
+    "embedding_dim": null,
+    "kwargs": {
+      "embedding_configs": [
+        {
+          "type": "sinusoidal",
+          "args": {
+            "max_seq_len": 128
+          }
+        },
+        {
+          "type": "timedelta",
+          "args": {
+            "hidden_dim": 16
+          }
+        },
+        {
+          "type": "learned_abs",
+          "args": {
+            "max_seq_len": 128
+          }
+        }
+      ],
+      "max_seq_len": 4096
+    }
+  },
+  "feedforward_config": {
+    "type": "standard",
+    "intermediate_size": 256,
+    "activation": "gelu",
+    "dropout": 0.1,
+    "kwargs": {}
+  },
+  "output_head_config": {
+    "type": "linear",
+    "output_size": 1,
+    "kwargs": {}
+  },
+  "encoder_blocks": [
+    {
+      "block_type": "default_encoder",
+      "attention_config": {
+        "attention_type": "full",
+        "num_heads": 2,
+        "dropout": 0.1,
+        "kwargs": {}
+      },
+      "ffn_config": {
+        "type": "standard",
+        "intermediate_size": 64,
+        "activation": "gelu",
+        "dropout": 0.1,
+        "kwargs": {}
+      },
+      "kwargs": {}
+    },
+    {
+      "block_type": "default_encoder",
+      "attention_config": {
+        "attention_type": "full",
+        "num_heads": 2,
+        "dropout": 0.1,
+        "kwargs": {}
+      },
+      "ffn_config": {
+        "type": "standard",
+        "intermediate_size": 64,
+        "activation": "gelu",
+        "dropout": 0.1,
+        "kwargs": {}
+      },
+      "kwargs": {}
+    }
+  ],
+  "decoder_blocks": [
+    {
+      "block_type": "default_decoder",
+      "attention_config": {
+        "attention_type": "full",
+        "num_heads": 2,
+        "dropout": 0.1,
+        "kwargs": {}
+      },
+      "ffn_config": {
+        "type": "standard",
+        "intermediate_size": 64,
+        "activation": "gelu",
+        "dropout": 0.1,
+        "kwargs": {}
+      },
+      "kwargs": {}
+    },
+    {
+      "block_type": "default_decoder",
+      "attention_config": {
+        "attention_type": "full",
+        "num_heads": 2,
+        "dropout": 0.1,
+        "kwargs": {}
+      },
+      "ffn_config": {
+        "type": "standard",
+        "intermediate_size": 64,
+        "activation": "gelu",
+        "dropout": 0.1,
+        "kwargs": {}
+      },
+      "kwargs": {}
+    }
+  ],
+  "norm_config": {
+    "norm_type": "layer",
+    "eps": 1e-05,
+    "kwargs": {}
+  },
+  "head_agg_config": {
+    "type": "mean",
+    "kwargs": {}
+  },
+  "hidden_size": 32,
+  "num_quantiles": 3,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "use_teacher_forcing": true,
+  "hidden_dropout_prob": 0.1,
+  "return_dict": true,
+  "torchscript": false,
+  "torch_dtype": null,
+  "use_bfloat16": false,
+  "tf_legacy_loss": false,
+  "pruned_heads": {},
+  "tie_word_embeddings": true,
+  "chunk_size_feed_forward": 0,
+  "is_encoder_decoder": false,
+  "is_decoder": false,
+  "cross_attention_hidden_size": null,
+  "add_cross_attention": false,
+  "tie_encoder_decoder": false,
+  "max_length": 20,
+  "min_length": 0,
+  "do_sample": false,
+  "early_stopping": false,
+  "num_beams": 1,
+  "num_beam_groups": 1,
+  "diversity_penalty": 0.0,
+  "temperature": 1.0,
+  "top_k": 50,
+  "top_p": 1.0,
+  "typical_p": 1.0,
+  "repetition_penalty": 1.0,
+  "length_penalty": 1.0,
+  "no_repeat_ngram_size": 0,
+  "encoder_no_repeat_ngram_size": 0,
+  "bad_words_ids": null,
+  "num_return_sequences": 1,
+  "output_scores": false,
+  "return_dict_in_generate": false,
+  "forced_bos_token_id": null,
+  "forced_eos_token_id": null,
+  "remove_invalid_values": false,
+  "exponential_decay_length_penalty": null,
+  "suppress_tokens": null,
+  "begin_suppress_tokens": null,
+  "architectures": null,
+  "finetuning_task": null,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1"
+  },
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1
+  },
+  "tokenizer_class": null,
+  "prefix": null,
+  "bos_token_id": null,
+  "pad_token_id": null,
+  "eos_token_id": null,
+  "sep_token_id": null,
+  "decoder_start_token_id": 3.0,
+  "task_specific_params": null,
+  "problem_type": null,
+  "_name_or_path": "",
+  "_attn_implementation_autoset": false,
+  "transformers_version": "4.51.3",
+  "model_type": "transformer",
+  "feature_size": 1,
+  "context_length": 16,
+  "prediction_length": 4,
+  "quantiles": [
+    0.1,
+    0.5,
+    0.9
+  ],
+  "output_token_lengths": 1,
+  "loss_type": "quantile",
+  "use_dynamic_features": false,
+  "use_static_features": false,
+  "autoregressive": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6e48b3d3c88b34881896a31683954e5f39b707926a3c8d9aee0b74657e18a8b
+size 252476