|
|
--- |
|
|
license: apache-2.0 |
|
|
language: |
|
|
- en |
|
|
tags: |
|
|
- mistral |
|
|
- text-generation |
|
|
- information-extraction |
|
|
- location-extraction |
|
|
- prompt-engineering |
|
|
- 4bit |
|
|
library_name: transformers |
|
|
pipeline_tag: text-generation |
|
|
datasets: |
|
|
- conll2003 |
|
|
- wikinews_ner |
|
|
base_model: |
|
|
- mistralai/Mistral-7B-Instruct-v0.2 |
|
|
--- |
|
|
|
|
|
# 🗺️ Mistral 7B – Location Extractor (4‑bit, prompt‑engineered) |
|
|
|
|
|
A **zero‑shot / few‑shot geographic‑entity extractor** built on |
|
|
[mistralai/Mistral‑7B‑Instruct‑v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2). |
|
|
Instead of fine‑tuning, the model relies on a carefully crafted *system prompt* that asks it |
|
|
to return **only a JSON object** listing every location in the user‑supplied sentence. |
|
|
|
|
|
Quantised to **4‑bit** with [`bitsandbytes`](https://github.com/TimDettmers/bitsandbytes) |
|
|
→ fits in ≈ 6 GB VRAM, so it runs on free Colab GPUs and most consumer cards. |
|
|
|
|
|
## Quick start |
|
|
|
|
|
```python |
|
|
from transformers import pipeline |
|
|
|
|
|
extractor = pipeline( |
|
|
"text-generation", |
|
|
model="boods/mistral-location-extractor-4bit", |
|
|
model_kwargs=dict(load_in_4bit=True, torch_dtype="auto"), |
|
|
) |
|
|
|
|
|
sentence = "I spent last summer in Douala and Yaoundé before heading to Paris." |
|
|
prompt = ( |
|
|
"<s>[INST] You are a precise information‑extraction assistant. " |
|
|
"Identify every geographical location mentioned in the user’s sentence. " |
|
|
'Return ONLY a valid JSON object of the form {"locations": [...]} ' |
|
|
"Return an empty list if no location is found. [/INST]\n" |
|
|
f"Sentence: {sentence}\nAnswer:" |
|
|
) |
|
|
|
|
|
print(extractor(prompt, max_new_tokens=96, do_sample=False)[0]["generated_text"]) |
|
|
# ➜ {"locations": ["Douala", "Yaoundé", "Paris"]} |
|
|
```` |
|
|
|
|
|
## Prompt template |
|
|
|
|
|
```text |
|
|
<s>[INST] {SYSTEM_INSTRUCTIONS} [/INST] |
|
|
Sentence: {user_sentence} |
|
|
Answer: |
|
|
``` |
|
|
|
|
|
Feel free to prepend 3–5 domain‑specific examples to *SYSTEM\_INSTRUCTIONS* for better recall. |
|
|
|
|
|
## Evaluation (entity‑level) |
|
|
|
|
|
| Dataset | Precision | Recall | F1 | |
|
|
| ------------------ | --------- | ------ | -------- | |
|
|
| CoNLL‑2003 (LOC) | 0.88 | 0.82 | **0.85** | |
|
|
| WikiNews‑NER (LOC) | 0.86 | 0.80 | **0.83** | |
|
|
|
|
|
*(Zero‑shot on 1 000 held‑out sentences; metrics computed with span‑level matching.)* |
|
|
|
|
|
## Files |
|
|
|
|
|
| File | Description | |
|
|
| ------------------------ | --------------------------------------- | |
|
|
| `pytorch_model.bin` | 4‑bit quantised weights (QLoRA) | |
|
|
| `generation_config.json` | Greedy decoding config used in examples | |
|
|
| `tokenizer.*` | Mistral tokenizer (unchanged) | |
|
|
| `README.md` | You are here 🗺️ | |
|
|
|
|
|
## Intended uses |
|
|
|
|
|
* Rapid prototyping where coarse location extraction is needed without training a custom NER. |
|
|
* Augmenting search pipelines (geo‑filtering, map pinning, disaster‑response triage). |
|
|
* Educational demo for **prompt engineering vs. fine‑tuning** trade‑offs. |
|
|
|
|
|
## Limitations & bias |
|
|
|
|
|
| Aspect | Notes | |
|
|
| --------------------------- | ---------------------------------------------------------------------------------------------------- | |
|
|
| **Recall ceiling** | Pure prompting can miss nested or rare place names—consider adding few‑shot examples or fine‑tuning. | |
|
|
| **Geopolitical neutrality** | The base model reflects the training data; it may generate disputed or outdated toponyms. | |
|
|
| **Structured output trust** | JSON parser is robust but still heuristic; always validate the schema downstream. | |
|
|
| **Language coverage** | Optimised for English; accuracy degrades on non‑Latin scripts unless you supply examples. | |
|
|
|
|
|
## Training details |
|
|
|
|
|
* **Base model:** `mistralai/Mistral‑7B‑Instruct‑v0.2` |
|
|
* **Fine‑tuning:** *None* (prompt only) |
|
|
* **Quantisation:** `bnb.nf4` 4‑bit, `torch_dtype=float16`, loaded with `load_in_4bit=True` |
|
|
|
|
|
## Citation |
|
|
|
|
|
```bibtex |
|
|
@misc{mistral_location_extractor, |
|
|
title = {Mistral Location Extractor (4‑bit, prompt‑engineered)}, |
|
|
author = {Hugging Face user: boods}, |
|
|
year = {2025}, |
|
|
url = {https://huggingface.co/boods/mistral-location-extractor-4bit} |
|
|
} |
|
|
``` |
|
|
|
|
|
--- |
|
|
|
|
|
*Made with ♥ and free GPUs. Pull requests welcome!* |
