Sourabh2_-_purchase_order_gone-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

purchase_order_gone - GGUF

• Model creator: https://huggingface.co/Sourabh2/
• Original model: https://huggingface.co/Sourabh2/purchase_order_gone/

Original model description:

language: en tags:

• gpt2
• text-generation

---

Model Name

This model is a fine-tuned version of GPT-2, trained on custom data for specific text generation tasks.

Usage

You can use this model for text generation tasks. Here's a sample code:

# Load model directly
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("Sourabh2/purchase_order_gone")
model = AutoModelForCausalLM.from_pretrained("Sourabh2/purchase_order_gone")

# Assuming you have a CUDA device available
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

text = "Robinson-Carson GSTIN 37LTOQASACEIZS Address:28713 Hart Fort Suite 267 ‘Stewarttown, Ml 55458 US Buyer :Monique Russell 71450 Love Way Suite 139 Lake Tammyton, NJ 38932 US Tel:+(586)876-1260 Email:[email protected] Site:https://wong.com/ 260 INVOICE # INV16851863, BILL_To: Christe Porter ‘5549 Bell Station ‘South Theresaberg, NM 73237 US Tol:+(562)703-2501 [email protected] Site:http:/www.memahon.com! Dog attention hit. Eat remember walk. Receive international Raise truth assume. $32.81 4.00 $131.44 $27.15 5.00 $135.75 $90.05 1.00 $90.05 $27.47 5.00 $137.35 ‘SUB_TOTAL : 494.59 USD BALANCE DUE : 505.77 USD Total in words: five hundred and fi- ve point seven seven"
text = text.lower()

messages = [{"role": "user", "content": test}]

prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipe = pipeline(
    "text-generation",
    model=model,
    tokenizer=tokenizer,
    torch_dtype=torch.float16,
    device=device.type,
)

outputs = pipe(prompt, max_new_tokens=1200, do_sample=True, temperature=0.1, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])