| license: llama2 | |
| base_model: NousResearch/Llama-2-7b-hf | |
| tags: | |
| - e-commerce | |
| - llama | |
| - text-generation | |
| - merged | |
| pipeline_tag: text-generation | |
| # LLaMA-Ecommerce | |
| This is a merged model combining [NousResearch/Llama-2-7b-hf](https://huggingface.co/NousResearch/Llama-2-7b-hf) with [DSMI/LLaMA-E](https://huggingface.co/DSMI/LLaMA-E) LoRA adapter. | |
| ## Model Description | |
| LLaMA-E is specialized for e-commerce content generation tasks including: | |
| - Product descriptions | |
| - Advertisements | |
| - Product titles | |
| - E-commerce Q&A | |
| - Purchase intent analysis | |
| ## Usage | |
| ```python | |
| from transformers import AutoModelForCausalLM, AutoTokenizer | |
| model = AutoModelForCausalLM.from_pretrained("askcatalystai/llama-ecommerce") | |
| tokenizer = AutoTokenizer.from_pretrained("askcatalystai/llama-ecommerce") | |
| prompt = "***Instruction: Write a product description\n***Input: Blue cotton t-shirt, comfortable fit\n***Response:" | |
| inputs = tokenizer(prompt, return_tensors="pt") | |
| outputs = model.generate(**inputs, max_new_tokens=200) | |
| print(tokenizer.decode(outputs[0])) | |
| ``` | |
| ## Original Work | |
| Based on research: [LLaMA-E: Empowering E-commerce Authoring with Multi-Aspect Instruction Following](https://arxiv.org/abs/2308.04913) | |
| ## License | |
| This model is subject to the [Llama 2 Community License](https://ai.meta.com/llama/license/). | |