README.md

metadata

license: apache-2.0
base_model: unsloth/Qwen2.5-Coder-7B-Instruct-bnb-4bit
tags:
  - code
  - python
  - synthetic-data
  - numpy
  - pandas
  - vectorized
library_name: peft
pipeline_tag: text-generation

FastData-LM-7B-SFT

FastData-LM-7B-SFT is a specialized language model fine-tuned on the thlurte/VSG-lite-1.5k dataset. It functions as a zero-shot High-Throughput Vectorized Data Compiler — translating dataset schema requirements into 100% vectorized, loop-free NumPy and Pandas execution graphs.

Model Details

• Base Architecture: unsloth/Qwen2.5-Coder-7B-Instruct-bnb-4bit
• Fine-Tuning Dataset: thlurte/VSG-lite-1.5k
• Primary Domain: Vectorized Synthetic Data Generation across 13 industrial schemas.
• Strict Anti-Loop Constraint: Eliminates .apply(), .iterrows(), and all for/while row-level iteration.

Usage Example

from unsloth import FastLanguageModel

model, tokenizer = FastLanguageModel.from_pretrained(
    model_name = "thlurte/FastData-LM-7B-SFT",
    max_seq_length = 2048,
    load_in_4bit = True,
)

messages = [
    {"role": "system", "content": "You are a zero-shot Python Data Compiler. Generate 100% vectorized NumPy/Pandas code."},
    {"role": "user", "content": "Generate a synthetic bank ledger dataset with entry_id, balance, and transaction_type."}
]

prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
outputs = model.generate(**inputs, max_new_tokens=1024)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))