MasterControlAIML/DeepSeek-R1-Qwen2.5-3b-LLM-Judge-Reward-JSON-Unstructured-To-Structured-Merged-Lora-16bit

# ─────────────────────────────────────────────────────────────────────────────
# QUICK-START
# Structured-data extraction with reasoning + JSON output
# ─────────────────────────────────────────────────────────────────────────────
from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
import torch, json, textwrap, inspect
from pydantic import BaseModel
from typing import List, Optional

MODEL = "MasterControlAIML/DeepSeek-R1-Qwen2.5-3b-LLM-Judge-Reward-JSON-Unstructured-To-Structured-Lora"

# 1️⃣  Inline schema (keeps the LLM on-rails) ─────────────────────────────────
class MultipleChoice(BaseModel):
    question: str
    options: List[str]
    selected: str

class FormField(BaseModel):
    fieldName: str
    value: str
    notes: Optional[str] = ""

class Calculation(BaseModel):
    formula: str
    result: str
    notes: Optional[str] = ""

class Metadata(BaseModel):
    reportDate: str
    auditorId: Optional[str] = None
    comments: Optional[str] = None

class Content(BaseModel):
    paragraphs: List[str]
    tables: List["Table"]          # assume Table defined elsewhere
    checkboxes: List["Checkbox"]   #          〃
    multipleChoice: List[MultipleChoice]
    formFields: List[FormField]
    calculations: List[Calculation]
    metadata: Optional[Metadata] = Metadata(reportDate="")

class Section(BaseModel):
    id: str
    title: str
    content: Content

class Document(BaseModel):
    documentTitle: str
    documentDate: str
    sections: List[Section]

SCHEMA_TEXT = inspect.getsource(Document)

# 2️⃣  Build prompts ──────────────────────────────────────────────────────────
SYSTEM_PROMPT = textwrap.dedent(f"""
    You are an expert **data-extraction assistant**.
    Extract structured info from unstructured text **exactly** following the Pydantic schema.

    ── Schema ──
    {SCHEMA_TEXT}
    ─────────────

    Rules:
      1. Follow the schema for keys & nesting.
      2. Copy values verbatim when possible.
      3. If a field is missing, return null.
      4. Output your step-by-step reasoning first.
      5. Then return ONLY the JSON inside this wrapper:
         final answer[ json object: {{ ... }} ]

    Format:
      <reasoning>…</reasoning>
      <answer>
      final answer[ json object: {{ … }} ]
      </answer>
""").strip()

UNSTRUCTURED_TEXT = """
    12 April 2025 – Onsite audit performed by Jane Smith.
    Observations: Two fire extinguishers past expiry; emergency lights functional.
    Calculations: Total extinguishers = 8, expired = 2 → 25 % overdue.
"""

USER_PROMPT = textwrap.dedent(f"""
    ### Task
    Convert the following *hier* text to the schema.

    ### hier
    {UNSTRUCTURED_TEXT}
""").strip()

# 3️⃣  Generate ───────────────────────────────────────────────────────────────
tok   = AutoTokenizer.from_pretrained(MODEL, use_fast=True)
model = AutoModelForCausalLM.from_pretrained(
    MODEL,
    device_map="auto",
    torch_dtype=torch.bfloat16
)
gen = pipeline("text-generation", model=model, tokenizer=tok,
               max_new_tokens=512, do_sample=False)

prompt = f"<|system|>\n{SYSTEM_PROMPT}\n<|user|>\n{USER_PROMPT}"
raw_out = gen(prompt)[0]["generated_text"]

# 4️⃣  Slice out the JSON ─────────────────────────────────────────────────────
start = raw_out.find("final answer[")
end   = raw_out.rfind("]") + 1
json_text = raw_out[start:].split("json object:")[-1].strip(" []\n")
data = json.loads(json_text)    # ✅ Raises if malformed

print(raw_out)  # reasoning + JSON
print("\n✅ Parsed object:\n", data)

@misc{bhaviktheslider_2025_unsloth_qwen2.5_3b_grpo,
  title  = {An Unsloth-accelerated GRPO-trained Qwen 2.5-3B for JSON structuring},
  author = {MasterControlAIML},
  year   = {2025},
  howpublished = {\url{https://huggingface.co/MasterControlAIML/DeepSeek-R1-Qwen2.5-3b-LLM-Judge-Reward-JSON-Unstructured-To-Structured-Lora}}
}