Downloads · 30 days
12
24% of all-time downloads
drok-v4
Digirocket/drok-v4
drok-v4 is a text generation model from Digirocket. Use it when you need the model to write or continue text. The card lists the license as llama3.2.
Fine-tuned Llama 3.2 3B Instruct specialized for DigiRocket Technologies — a digital marketing and technology solutions provider.
All-time downloads
49
Public
Repo size
4.7 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf4.7 GB · 100%
At a glance
- Task
- Text Generation
- License
- llama3.2
- Access
- Public
- Created
- May 30, 2026
- Updated
- May 30, 2026
- SHA
- c15eb07b
Try a prompt
Base models
Model card
From the Hugging Face model README
DROK v2 — DigiRocket Technologies AI Assistant
Fine-tuned Llama 3.2 3B Instruct specialized for DigiRocket Technologies — a digital marketing and technology solutions provider.
Specialization
DROK is an expert in:
- Digital Marketing (SEO, SEM, SMM, CRO, email marketing, content)
- Web Development (responsive design, e-commerce platforms, UI/UX)
- Branding (logo design, visual identity, brand storytelling)
- Dropshipping (supplier sourcing, store setup, scaling)
- DigiRocket Services (pricing tiers, case studies, consultation)
Training Details
- Base model: meta-llama/Llama-3.2-3B-Instruct
- Method: QLoRA 4-bit fine-tuning (NF4 quantization, LoRA r=16)
- Dataset: 1,343 DigiRocket-domain Q&A pairs (synthetic, qwen2.5-7b generated)
- Epochs: 3
- Training infrastructure: Lightning.ai Tesla T4
Quantization
This release is the Q8_0 GGUF quantized version (~3.4 GB), suitable for llama.cpp / HF Inference Endpoints serving.
Company
DigiRocket Technologies — global digital marketing agency:
- 🇮🇳 Gurgaon, India (HQ)
- 🇺🇸 Dover, USA
- 🇬🇧 London, UK
Websites: digirocket.io | digirockett.com
- Task
- Text Generation
- License
- llama3.2
- Languages
- en
- Created
- May 30, 2026
- Updated
- May 30, 2026