Downloads · 30 days
9
10% of all-time downloads
dheeyantra/dhee-nxtgen-qwen3-bengali-v1
dhee-nxtgen-qwen3-bengali-v1 is a machine learning model from dheeyantra. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Dhee-nxtgen-qwen3-bengali-v1 is a large language model designed for high-quality natural language understanding and generation in Bengali. It is based on the Qwen3 architecture and optimized for both dialogue and reas…
Downloads · 30 days
9
10% of all-time downloads
All-time downloads
90
Public
Parameters
2B
4.1 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors4.1 GB · 100%
From the Hugging Face model README
Dhee-nxtgen-qwen3-bengali-v1 is a large language model designed for high-quality natural language understanding and generation in Bengali. It is based on the Qwen3 architecture and optimized for both dialogue and reasoning tasks.
The model supports fluent conversational responses and reasoning-style outputs, making it suitable for applications like chatbots, virtual assistants, and step-by-step question answering.
from transformers import AutoTokenizer, AutoModelForCausalLM
model_name = "dheeyantra/dhee-nxtgen-qwen3-bengali-v1"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True)
# Regular conversation
prompt = "নমস্কার! আজকের আবহাওয়া কেমন?"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=100)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
To serve this model using vLLM, ensure the following:
GPU with compute capability ≥ 8.0 (e.g., NVIDIA A100).
PyTorch 2.1+ with CUDA toolkit installed.
For Tesla V100 (sm70), vLLM GPU inference is not supported; CPU-only fallback is possible but slow.
Python dependencies:
pip install torch transformers vllm sentencepiece
Example vLLM command:
vllm serve \
--model dheeyantra/dhee-nxtgen-qwen3-bengali-v1 \
--host 0.0.0.0 \
--port 8000
Released under the Apache 2.0 License.