Upload 4 files

finetuned_model_2_epoch/config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "t5-small",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 512,
+  "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": 6,
+  "num_heads": 8,
+  "num_layers": 6,
+  "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": "bfloat16",
+  "transformers_version": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 32128
+}

finetuned_model_2_epoch/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": "4.35.2"
+}

finetuned_model_2_epoch/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e174827ac407d413ad05b518ed824846a8eb5d74f947c5e2ab1833a173e717b
+size 121028656

test_t5.py

@@ -0,0 +1,50 @@
+from sklearn.model_selection import train_test_split
+from datasets import Dataset, DatasetDict, load_dataset, interleave_datasets, load_from_disk
+from transformers import AutoModelForSeq2SeqLM, AutoTokenizer, GenerationConfig, TrainingArguments, Trainer
+import torch
+import time
+import evaluate
+import pandas as pd
+import numpy as np
+model_name = 't5-small'
+
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+original_model = AutoModelForSeq2SeqLM.from_pretrained(model_name, torch_dtype=torch.bfloat16)
+original_model = original_model.to('cuda')
+
+finetuned_model = AutoModelForSeq2SeqLM.from_pretrained("finetuned_model_2_epoch")
+# finetuned_model = finetuned_model.to('cuda')
+# data = pd.read_csv("text-to-sql_from_spider.csv")
+
+question = data["question"][0] #dataset['test'][index]['question']
+context = "CREATE TABLE table_name_11 (date VARCHAR, away_team VARCHAR)" #dataset['test'][index]['schema']
+answer = data["sql"][0] #dataset['test'][index]['sql']
+
+prompt = f"""Tables:
+{context}
+
+Question:
+{question}
+
+Answer:
+"""
+
+inputs = tokenizer(prompt, return_tensors='pt')
+inputs = inputs.to('cuda')
+
+output = tokenizer.decode(
+    finetuned_model.generate(
+        inputs["input_ids"],
+        max_new_tokens=200,
+    )[0],
+    skip_special_tokens=True
+)
+
+dash_line = '-'*100
+print(dash_line)
+print(f'INPUT PROMPT:\n{prompt}')
+print(dash_line)
+print(f'BASELINE HUMAN ANSWER:\n{answer}\n')
+print(dash_line)
+print(f'MODEL GENERATION - ZERO SHOT:\n{output}')