Uploaded model
- Developed by: Ellight
- License: apache-2.0
- Finetuned from model : unsloth/llama-3.2-1b-bnb-4bit
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
For Inference
The Llama model is trained using Bitext-customer-support-llm-chatbot-training-dataset for generating more accurate responses to customer queries. The model can be further finetuned based on specific companies data.
from unsloth import FastLanguageModel
model, tokenizer = FastLanguageModel.from_pretrained(
model_name = "Ellight/Llama-3.2-1B-Customer-support-Chatbot", # YOUR MODEL YOU USED FOR TRAINING
max_seq_length = max_seq_length,
dtype = dtype,
load_in_4bit = load_in_4bit,
)
FastLanguageModel.for_inference(model) # Enable native 2x faster inference
alpaca_prompt = """Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
### Instruction:
{}
### Response:
{}"""
inputs = tokenizer(
[
alpaca_prompt.format(
"I want assistance to cancel order", # instruction
"", # output - leave this blank for generation!
)
], return_tensors = "pt").to("cuda")
from transformers import TextStreamer
text_streamer = TextStreamer(tokenizer)
_ = model.generate(**inputs, streamer = text_streamer, max_new_tokens = 512)
Model Response:
<|begin_of_text|>Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
### Instruction:
I want assistance to cancel order
### Response:
I understand that you need assistance in canceling your order. I'm here to guide you through the process. To cancel your order, you can follow these steps:
1. Log in to your account on our website.
2. Navigate to the "Orders" or "My Account" section.
3. Locate your order and click on it.
4. On the order details page, locate the "Cancel Order" or "Cancel Order" option.
5. Click on it to initiate the cancellation process.
If you encounter any difficulties or have any questions during the cancellation process, please don't hesitate to reach out to us. We're here to assist you every step of the way.<|end_of_text|>
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.