Dhee-NxtGen-Qwen3-Hindi-v2
Model Description
Dhee-NxtGen-Qwen3-Hindi-v2 is a large language model developed by DheeYantra in collaboration with NxtGen Cloud Technologies Pvt. Ltd.
It is based on the Qwen3 architecture and fine-tuned for assistant-style, function-calling, and reasoning-based conversational tasks in Hindi.
This model generates fluent and contextually accurate Hindi responses, suitable for building chatbots, reasoning systems, and multilingual AI assistants.
Key Features
- Fluent and context-aware Hindi text generation
- Optimized for reasoning and assistant-style dialogues
- Handles summarization, question answering, and open-ended text generation
- Fully compatible with 🤗 Hugging Face Transformers
- Works seamlessly with VLLM for high-performance inference
Example Usage
from transformers import AutoTokenizer, AutoModelForCausalLM
model_name = "dheeyantra/dhee-nxtgen-qwen3-hindi-v2"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True)
# Example prompt
prompt = """<|im_start|>system
You are a helpful assistant.<|im_end|>
<|im_start|>user
क्या आप मेरे लिए एक अपॉइंटमेंट शेड्यूल कर सकते हैं?nd|<|im_end|>
<|im_start|>assistant
"""
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=150)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
Intended Uses & Limitations
Intended Uses
- Hindi conversational chatbots and assistants
- Function-calling and structured response generation
- Story generation and summarization in Hindi
- Natural dialogue systems for Indic AI applications
Limitations
- May generate inaccurate or biased responses in rare cases
- Performance can vary on out-of-domain or code-mixed inputs
- Primarily optimized for Hindi; other languages may produce less fluent results
VLLM / High-Performance Serving Requirements
For high-throughput serving with vLLM, ensure the following environment:
- GPU with compute capability ≥ 8.0 (e.g., NVIDIA A100)
- PyTorch 2.1+ and CUDA toolkit installed
- For V100 GPUs (sm70), vLLM GPU inference is not supported; CPU fallback is possible but slower.
Install dependencies:
pip install torch transformers vllm sentencepiece
Run vLLM server:
vllm serve --model dheeyantra/dhee-nxtgen-qwen3-hindi-v2 --host 0.0.0.0 --port 8000
License
Released under the Apache 2.0 License.
Developed by DheeYantra in collaboration with NxtGen Cloud Technologies Pvt. Ltd.