Model Card
Example Usage
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
tokenizer = AutoTokenizer.from_pretrained('/mnt/nlpgpu-io1/data/ajayp/output/fineinstructions/dated/2025-08-21-02:05:11/data/sft_v2_fineinstructions-pretraining_experiments-ipt_fineinstructions_all_exp_chat-hf/export_path', revision=None) # Load tokenizer
tokenizer.padding_side = 'left'
model = AutoModelForCausalLM.from_pretrained('/mnt/nlpgpu-io1/data/ajayp/output/fineinstructions/dated/2025-08-21-02:05:11/data/sft_v2_fineinstructions-pretraining_experiments-ipt_fineinstructions_all_exp_chat-hf/export_path', revision=None) # Load model
pipe = pipeline('text-generation', model=model, tokenizer=tokenizer, pad_token_id=tokenizer.pad_token_id, return_full_text=False)
inputs = ["<|start_header_id|>user<|end_header_id|>\nI want you to use the Titanic dataset available in the seaborn package. You are required not only to conduct Preprocessing, Exploratory Data Analysis and Prediction using this dataset, but also perform Feature Engineering. \n\nAdditionally, here is a snippet of a model trained with Logistic Regression:\n\n```python\nimport seaborn as sns\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.linear_model import LogisticRegression\n\ndf = sns.load_dataset('titanic')\n\nx_train, x_test, y_train, y_test = train_test_split(\n df.drop('survived', axis=1), df['survived'], test_size=0.25, random_state=42)\n\nmodel = LogisticRegression()\nmodel.fit(x_train, y_train)\n```\n\nThe above code results in an error. Identify the error and modify the code accordingly. \n\nFurthermore, provide high-quality documentation for your code, giving detailed insights into every step of your analysis from data preprocessing, analysis to prediction. Lastly, make use of visualization tools to present the results in a more understandable manner. Your code should be efficient and well-structured so it's easily readable and maintainable.\n\n<|start_header_id|>assistant<|end_header_id|>\n"]
print(pipe(inputs, max_length=8192, do_sample=False))
This model was trained with DataDreamer 🤖💤.