README.md

---
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
tags:
- sft
- structured-generation
- table-generation
- llama-3.1
- flash-attention-2
license: other
language:
- en
---

# mohdusman001/Text-to-Table-Stage2

Stage‑2 (π₂) **text + schema → table** model fine‑tuned from **meta-llama/Meta-Llama-3.1-8B-Instruct** with a 3‑stage schedule
(2k → 4k → **8k** context). This repo includes merged weights + tokenizer and sample artifacts.

## TL;DR
- Context window: **8192** tokens (final stage)  
- Final eval (loss / ppl): 2.395211 / 10.9705  
- Sanity (json_valid / key_order / type): 0.078 / 0.078 / 0.078
- Artifacts: see `metrics/` and `samples/`.

## How to prompt (JSONL rows)
The model expects a schema and a document snippet. It should emit **one JSON object per line**,
with keys **exactly** in schema order (no code fences, no prose).

```text
[SCHEMA]
{{"fields":[{{"name":"order_id","type":"string"}},{{"name":"item","type":"string"}},{{"name":"qty","type":"integer"}}]}}

<|document|>
Orders today:
- O-1003: 2x pencil
- O-1004: 1x notebook
```

### Python usage (deterministic table emission)
```python
import torch, json
from transformers import AutoTokenizer, AutoModelForCausalLM

model_id = "mohdusman001/Text-to-Table-Stage2"
tok = AutoTokenizer.from_pretrained(model_id, use_fast=True)
if tok.pad_token is None: tok.pad_token = tok.eos_token
dtype = torch.bfloat16 if torch.cuda.is_available() else torch.float32
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=dtype, device_map="auto",
                                             attn_implementation="flash_attention_2")
prompt = (
    "[SCHEMA]
"
    '{{"fields":[{{"name":"order_id","type":"string"}},{{"name":"item","type":"string"}},{{"name":"qty","type":"integer"}}]}}\n\n'
    "<|document|>
"
    "Orders today:
- O-1003: 2x pencil
- O-1004: 1x notebook
"
)
chat = [{{"role":"user","content":prompt}}]
txt = tok.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)
inp = tok(txt, return_tensors="pt").to(model.device)

with torch.no_grad():
    out = model.generate(**inp, max_new_tokens=256, do_sample=False, temperature=0.0,
                         eos_token_id=tok.eos_token_id, pad_token_id=tok.pad_token_id)
generated = tok.decode(out[0][inp["input_ids"].shape[1]:], skip_special_tokens=True)

rows = [json.loads(l) for l in generated.splitlines() if l.strip()]
print(rows)  # list of dicts
```

## Example generations
**Sample 1**

**user**: [SCHEMA]
{"fields": [{"name": "order_id", "type": "string"}, {"name": "item", "type": "string"}, {"name": "qty", "type": "integer"}]}

<|document|>
Orders today:
- O-1003: 2x pencil
- O-1004: 1x notebook

**generation (head)**:

```
Based on the provided schema, here's a breakdown of the data:

- **order_id**: a unique identifier for each order (e.g., O-1003, O-1004)
- **item**: the product being ordered (e.g., pencil, notebook)
- **qty**: the quantity of the item ordered (e.g., 2, 1)

So, the data can be represented as a list of dictionaries, where each dictionary represents an order:

```json
[
```

---

**Sample 2**

**user**: [SCHEMA]
{"fields": [{"name": "name", "type": "string"}, {"name": "department", "type": "string"}, {"name": "start_date", "type": "date"}, {"name": "full_time", "type": "boolean"}]}

<|document|>
New hires:
- Priya Singh joined Sales on 2024-08-01 full‑time.
- Ken Adams joined Engineering on 2024-09-15 part‑time.

**generation (head)**:

```
Based on the provided schema and the given information, we can create a JSON object for each new hire. However, since the schema specifies that the "full_time" field should be a boolean, we will assume that "part-time" is equivalent to False and "full-time" is equivalent to True.

Here's the JSON data:

```json
[
  {
    "name": "Priya Singh",
    "department": "Sales",
    "start_date": "2024-08-01",
```

---

**Sample 3**

**system**: You convert documents into tabular data strictly under a provided JSON schema. Output ONLY JSON Lines (one JSON object per row), with EXACT columns and order as the schema, and no commentary.
**user**: <|policy|>
[POLICY]
- Extract only facts explicitly supported by the document. No guessing, no background knowledge, no synonyms.
- Never invent rows or columns. If a value is not present, output an empty string for that cell.
- Output exactly the columns listed in [SCHEMA]. The key order in each JSON object MUST match the schema order.
- Do not add headers, comments, explanations, or markdown. Emit ONLY raw JSONL (one JSON object per line).
- Output must be deterministic for identical input.
- Trim leading/trailing whitespace in strings; preserve internal spacing and case from the document.
- IDs/codes stay strings (preserve leading zeros). Do not convert units or reformat currencies.
- Booleans accept tokens ⊆ {true,false,yes,no,1,0,t,f} (case-insensitive). Keep the surface form unless the schema requires normalization.
- Integers: ^[+-]?\d+$ (after trim). Numbers: plain JSON numbers if unambiguous; otherwise keep as strings.
- Dates: prefer ISO-like YYYY, YYYY-MM, or YYYY-MM-DD if explicitly present; otherwise keep as strings.
- Treat as missing (case-insensitive, after trim): "", -, —, –, N/A, NA, None, Null, Unknown, TBD, and the na_token from [METADATA]. For missing values, emit empty string "".
- For pivot-like tables, emit a single row per entity with all columns populated when available.
- For key–value (slot/value) tables, emit one row per pair with exactly the two columns from the schema.
- No trailing commas. Ensure every line is valid JSON. Do not wrap rows in an array. No code fences.

<|metadata|>
[METADATA]
{"language": "en", "script": "auto", "direction": "auto", "source_modality": "plain_text", "na_token": "", "document_char_len": 76, "table_count": "auto", "structure_candidates": ["kv_single", "kv_multi", "flat_single_row", "row_grouped"], "table_hints": {"header_rows_max": 3, "header_cols_max": 2, "row_header_possible": true, "col_header_possible": true, "ragged_rows_possible": false, "multiple_tables_possible": true}, "locale": {"numeric": "auto", "decimal_separators": [".", ","], "thousand_separators": [",", ".", " "], "negative_patterns": ["-x", "(x)"], "percent_symbol": "%", "permille_symbol": "‰"}, "parsing_hints": {"kv_markers": [":", "—", "–", "=", "→"], "list_markers": ["- ", "* ", "• ", "•\t", "▪ "], "section_markers": ["###", "##", "--", "__", "**", ":"]}, "missing_tokens": ["", "-", "—", "–", "N/A", "NA", "None", "Null", "Unknown", "TBD"]}

<|schema|>
[SCHEMA]
{"schema_id": "gold.e2137f3600e1", "structure": "kv_multi", "description": "Schema induced from the gold table.", "fields": [{"name": "slot", "type": "string", "required": true}, {"name": "value", "type": "string", "required": true}], "constraints": {"enums": {"slot": ["name", "area", "familyFriendly"], "value": ["Alimentum", "city centre", "no"]}}}

<|document|>
[DOCUMENT]
There is a place in the city centre, Alimentum, that is not family-friendly.

<|output_format|>
[OUTPUT_FORMAT]
Emit ONLY JSON Lines (JSONL), one JSON object per row, with keys exactly as in [SCHEMA] and in the same order. Do NOT wrap in an array. No comments or markdown.

<|task|>
[TASK]
Fill the table under the given [SCHEMA] using facts from [DOCUMENT]. If a value is not explicitly present, output an empty string for that cell. Ensure every line is valid JSON.
**assistant**: {"slot": "name", "value": "Alimentum"}
{"slot": "area", "value": "city centre"}
{"slot": "familyFriendly", "value": "no"}

**generation (head)**:

```
I've generated the output based on the provided schema and document.
```

## Notes
* Trained with FA‑2 + FSDP; LoRA in earlier stages then merged for the final artifact.
* For higher validity, keep decoding **deterministic** (no sampling) and validate lines downstream.
* Respect the base model license and your data licenses.