Create README.md

README.md

@@ -0,0 +1,78 @@
+---
+license: llama2
+language:
+- en
+- ar
+metrics:
+- accuracy
+- f1
+library_name: transformers
+---
+
+# llama-7b-v2-Receipt-Key-Extraction
+
+llama-7b-v2-Receipt-Key-Extraction is a 7 billion parameter based on LLamA v1
+
+[AMuRD: Annotated Multilingual Receipts Dataset for Cross-lingual Key Information Extraction and Classification](https://arxiv.org/abs/2309.09800)
+
+## Uses
+
+The model is intended for research-only use in English and Arabic for key information extraction for items in receipts.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+```bibtex
+# pip install -q transformers
+
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig
+
+checkpoint = "abdoelsayed/llama-7b-v2-Receipt-Key-Extraction"
+device = "cuda" if torch.cuda.is_available() else "cpu"
+
+tokenizer = AutoTokenizer.from_pretrained(checkpoint, model_max_length=512,
+        padding_side="right",
+        use_fast=False,)
+model = AutoModelForCausalLM.from_pretrained(checkpoint).to(device)
+
+def generate_response(instruction, input_text, max_new_tokens=100, temperature=0.1,  num_beams=4 ,top_k=40):
+    prompt = f"Below is an instruction that describes a task, paired with an input that provides further context.\n\n### Instruction:\n{instruction}\n\n### Input:\n{input_text}\n\n### Response:"
+    inputs = tokenizer(prompt, return_tensors="pt")
+    input_ids = inputs["input_ids"].to(device)
+    generation_config = GenerationConfig(
+            temperature=temperature,
+            top_p=top_p,
+            top_k=top_k,
+            num_beams=num_beams,
+        )
+    with torch.no_grad():
+        outputs = model.generate(input_ids,generation_config=generation_config, max_new_tokens=max_new_tokens)
+    outputs = tokenizer.decode(outputs.sequences[0])
+    return output.split("### Response:")[-1].strip().replace("</s>","")
+
+instruction = "Extract the class, Brand, Weight, Number of units, Size of units, Price, T.Price, Pack, Unit from the following sentence"
+input_text = "Americana Okra zero 400 gm"
+
+response = generate_response(instruction, input_text)
+print(response)
+
+```
+
+
+
+## How to Cite
+
+Please cite this model using this format.
+
+```bibtex
+@misc{abdallah2023amurd,
+    title={AMuRD: Annotated Multilingual Receipts Dataset for Cross-lingual Key Information Extraction and Classification},
+    author={Abdelrahman Abdallah and Mahmoud Abdalla and Mohamed Elkasaby and Yasser Elbendary and Adam Jatowt},
+    year={2023},
+    eprint={2309.09800},
+    archivePrefix={arXiv},
+    primaryClass={cs.CL}
+}
+```