Discovery-Qwen2.5-7B-v0.8

Multilingual (English/Hindi/Marathi) model for Hyperlocal AI Assistant. Fine-tuned from Qwen2.5-7B using SFT + DPO + RAFT.

Model Description

Discovery is a specialized conversational AI trained to help residents of Wagholi find local businesses, restaurants, gyms, hospitals, schools, and services. It understands Hindi, English, Marathi, and Hinglish (mixed informal input).

Training

  • Base Model: Qwen/Qwen2.5-7B
  • Training Methods: SFT + DPO + RAFT
  • Version: v0.8

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("tbqguy/Discovery-Qwen2.5-7B-v0.8")
tokenizer = AutoTokenizer.from_pretrained("tbqguy/Discovery-Qwen2.5-7B-v0.8")
Downloads last month
92
Safetensors
Model size
8B params
Tensor type
F16
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for tbqguy/Discovery-Qwen2.5-7B-v0.8

Base model

Qwen/Qwen2.5-7B
Finetuned
(757)
this model