Instructions to use BaSalam/Llama2-7b-entity-attr-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BaSalam/Llama2-7b-entity-attr-v2 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="BaSalam/Llama2-7b-entity-attr-v2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("BaSalam/Llama2-7b-entity-attr-v2")
model = AutoModelForCausalLM.from_pretrained("BaSalam/Llama2-7b-entity-attr-v2")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use BaSalam/Llama2-7b-entity-attr-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "BaSalam/Llama2-7b-entity-attr-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "BaSalam/Llama2-7b-entity-attr-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/BaSalam/Llama2-7b-entity-attr-v2

SGLang

How to use BaSalam/Llama2-7b-entity-attr-v2 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "BaSalam/Llama2-7b-entity-attr-v2" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "BaSalam/Llama2-7b-entity-attr-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "BaSalam/Llama2-7b-entity-attr-v2" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "BaSalam/Llama2-7b-entity-attr-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use BaSalam/Llama2-7b-entity-attr-v2 with Docker Model Runner:
```
docker model run hf.co/BaSalam/Llama2-7b-entity-attr-v2
```

Product catalog generator (V2)

This is a the version 2 of Product catalog generator. The dataset has changed with GPT-4 generated data to produce a higer quality response.

Github repo: https://github.com/basalam/product-catalog-generator

Sample input

prompt = """instruction': \"here is a product title from a Iranian marketplace.  \n         give me 
                 the Product Entity and Attributes of this product in Persian language.\n         give the output in 
                 this json format: {'attributes': {'attribute_name' : <attribute value>, ...}, 'product_entity': 
                 '<product entity>'}.\n         Don't make assumptions about what values to plug into json. Just give 
                 Json not a single word more.\n         \nproduct title:"""
title = """: ست شابلون ژله ای دو قلو صریر 20سانتی 1 عدد
1 عدد ست شابلون ژله ای دو قلو سریر 20سانتی متر
با کیفیت مناسب و صادراتی
شامل دو تکه شابلون ژله ای
در چهار رنگ سبز، قرمز، نارنجی و آبی موجود است.
پخش لوازم التحریر کیان""""

Model response

{
  "attributes": {
    "تعداد در بسته": [
      "1 عدد"],
    "نوع": [
      "ژله ای"],
    "تعداد قلو": [
      "دو قلو"],
    "اندازه": [
      "20 سانتی متر"],
    "کیفیت": [
      "مناسب",
      "صادراتی"],
    "تعداد تکه": [
      "دو تکه"],
    "رنگ": [
      "سبز",
      "قرمز",
      "نارنجی",
      "آبی"],
    "برند": [
      "پخش لوازم التحریر کیان"]
  },
  "product_entity": [
    "لوازم التحریر",
    "لوازم هنری",
    "شابلون",
    "ست شابلون ژله ای"]
}

Downloads last month: 9

Safetensors

Model size

7B params

Tensor type

F32

Dataset used to train BaSalam/Llama2-7b-entity-attr-v2

Collection including BaSalam/Llama2-7b-entity-attr-v2

Product Catalog Generator

Collection

Product Catalog Generator for Persian products which is hosted by Basalam • 7 items • Updated Sep 7, 2024 • 8