GilbertAkham/deepseek-R1-multitask-lora
🧠 Deepseek-R1-multitask-lora
Author: Gilbert Akham License: Apache-2.0 Base model: `deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B` Adapter type: LoRA (PEFT) Capabilities: Multi-task generalization & reasoning
🚀 What It Can Do
This multitask fine-tuned model handles a broad set of natural language and reasoning-based tasks, such as:
✉️ Email & message writing — generate clear, friendly, or professional communications.
📖 Story & creative writing — craft imaginative narratives, poems, and dialogues.
💬 Conversational chat — maintain coherent, context-aware conversations.
💡 Explanations & tutoring — explain technical or abstract topics simply.
🧩 Reasoning & logic tasks — provide step-by-step answers for analytical questions.
💻 Code generation & explanation — write and explain Python or general programming code.
🌍 Translation & summarization — translate between multiple languages or condense information.
The model’s multi-domain training (based on datasets like SmolTalk, Everyday Conversations, and reasoning-rich samples) makes it suitable for assistants, chatbots, content generators, or educational tools. ---
🧩 Training Details
🧠 Reasoning Capability
Thanks to integration of SmolTalk and diverse multi-task prompts, the model learns:
- Chain-of-thought style reasoning
- Conversational grounding
- Multi-step logical inferences
- Instruction following across domains
Example:
### Task: Explain reasoning
### Input:
If a train leaves City A at 3 PM and arrives at City B at 6 PM, covering 180 km, what is its average speed?
### Output:
The train travels 180 km in 3 hours.
Average speed = 180 ÷ 3 = 60 km/h.