---
license: mit
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: microsoft/Phi-3-mini-4k-instruct
datasets:
- shujatoor/ner_instruct-chat
model-index:
- name: checkpoint_dir
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# phi3nedtuned-ner

This model is a fine-tuned version of [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) on the generator dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6568

## For Inference
```python
from peft import PeftModel, PeftConfig
from transformers import AutoModelForCausalLM
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline

config = PeftConfig.from_pretrained("shujatoor/phi3nedtuned-ner")
model = AutoModelForCausalLM.from_pretrained(
    "microsoft/Phi-3-mini-4k-instruct", 
    device_map="cuda", 
    torch_dtype="auto", 
    trust_remote_code=True, 
)
model = PeftModel.from_pretrained(model, "shujatoor/phi3nedtuned-ner")
model.config.to_json_file('adapter_config.json')


torch.random.manual_seed(0)
tokenizer = AutoTokenizer.from_pretrained("shujatoor/phi3nedtuned-ner")


text = "Hasan Pharmacy Madina Market Mustafa Chowk.PCsiR Staff Society College Road, Lahore Drug Lic#441-A/AIT No.1023874 24/04/202422:18:03 M/s*CASH SALES-WALKING CUST Remarks: Ref.: Item Name Qty Price Total Advant Tab 16mg 28 37.50 1050.00 Kepra 500mg Tab 30 85.91 2577.30 Kabrokin 200mg 240 10.67 2560.80 Tab Myteka 10mg Tab 14 37.71 527.94 Cipocain Ear/drops 1 168.00 168.00 Medicam T/paste 1 240.00 240.00 100gm Total items:6 Gross Total : 7,124.04 Disc: 523.68 DR.HASAN Net Total. 6,600.00 (Computer Software developed by Abuzar Consultancy Ph 042-37426911-15)."
qs = f'{text} What is the drug license number of the store??'
print('Question:',qs, '\n')
messages = [
    #{"role": "system", "content": "Only output the answer, nothing else"},
    {"role": "user", "content": qs},

]

pipe = pipeline(
    "text-generation",
    model=model,
    tokenizer=tokenizer,
)

generation_args = {
    "max_new_tokens": 512,
    "return_full_text": False,
    #"temperature": 0.0,
    "do_sample": False,
}

output = pipe(messages, **generation_args)

print('Answer:', output[0]['generated_text'], '\n')

"""
expected answer:

Answer: 441-A/AIT No.1023874

"""

```

## Intended uses & limitations

Named Entity Recognition (NER)

## Training and evaluation data

More information needed

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 1
- eval_batch_size: 1
- seed: 0
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.2
- num_epochs: 1

### Training results



### Framework versions

- PEFT 0.10.1.dev0
- Transformers 4.41.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1

### License

The model is licensed under the MIT license.