metadata
base_model: unsloth/qwen2.5-3b-instruct-unsloth-bnb-4bit
tags:
- text-generation
- conversational
- emotional-ai
- mental-health
- multilingual
- bengali
- unsloth
- qwen2
- transformers
language:
- en
- bn
license: apache-2.0
datasets:
- Amod/mental_health_counseling_conversations
- iamshnoo/alpaca-cleaned-bengali
library_name: transformers
pipeline_tag: text-generation
Arete OSS 3B 🧠❤️
An emotionally intelligent AI that actually listens.
Built by Iseer & Co. - Making AI that understands humans, not just language.
What makes Arete different?
Most AI assistants optimize for being "smart." Arete optimizes for being empathetic.
- 🇧🇩 Speaks English and Bengali fluently
- 💬 Trained on real emotional support conversations
- 🎯 Recognizes when you're struggling and responds with care
- 🌍 Understands cultural context (especially South Asian family dynamics)
3 billion parameters. Infinite empathy.
Try it
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("inanxr/Arete-OSS-3B")
tokenizer = AutoTokenizer.from_pretrained("inanxr/Arete-OSS-3B")
prompt = """Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
Respond with empathy and understanding to the following message.
### Input:
I'm feeling overwhelmed and don't know what to do.
### Response:
"""
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=200, temperature=0.7)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))