metadata
license: mit
tags:
- svector
- theta-35-mini
- theta
Theta-35-mini
A lightweight, high-efficiency reasoning model distilled from Theta-35. Theta-35-Mini is a compact 3B parameter language model developed by SVECTOR, built on the Qwen architecture and trained using Group Relative Policy Optimization (GRPO). It is the smaller sibling of our flagship Theta-35 model (33B parameters), offering efficient performance for resource-constrained environments.
π Overview
- Architecture: Based on Qwen2-style transformer blocks
- Training Objective: Autoregressive next-token prediction
- Technique: Trained using Group Relative Policy Optimization (GRPO) β a reinforcement learning optimization strategy enabling fine-grained control and alignment
- Size: 3 billion parameters
- Parent Model: Theta-35 (33B)
π Model Highlights
- β Compact and Capable: Achieves strong performance despite its small size
- βοΈ GRPO-trained: Trained with Group Relative Policy Optimization for better alignment, coherence, and efficiency
- π‘ Low-latency Inference: Ideal for edge and on-device applications
π¦ How to Use
Install dependencies:
pip install transformers
Run model in Python:
from transformers import AutoModelForCausalLM, AutoTokenizer
# Force use of the slow tokenizer to avoid tokenizer.json issues
tokenizer = AutoTokenizer.from_pretrained("SVECTOR-CORPORATION/Theta-35-Mini", use_fast=False)
model = AutoModelForCausalLM.from_pretrained("SVECTOR-CORPORATION/Theta-35-Mini")
inputs = tokenizer("Once upon a time", return_tensors="pt")
outputs = model.generate(**inputs, max_length=100, temperature=0.7)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
π License
This model is released under the MIT License.
π’ About SVECTOR
π Visit us at svector.co.in
π Acknowledgements
- DeepSeek GRPO Paper
- Qwen2 Architecture