Gemma 2 2B AI Books Instructor (QA Fine-tune)
Summary
This model is a fine-tuned version of google/gemma-2-2b trained on ~4,800 Q/A pairs distilled from 11 AI/LLM/agent engineering books.
It is optimized for answering questions about AI engineering, LLMs, RAG, agents, and MLOps.
Base Model
google/gemma-2-2b
Training Data
- ~4,800 instruction-style Q/A pairs from 11 AI books (not released publicly)
Training Procedure
- SFT (LoRA fine-tuning)
- merged weights
- converted to GGUF using llama.cpp
- quantized (Q4_K_M, Q8_0)
Intended Use
- AI/LLM learning assistant
- fast local inference
- RAG/agent system support
Limitations
- May hallucinate
- Not suited for medical/legal advice
- Not guaranteed to reproduce book-accurate quotes
How to Run (llama.cpp)
./llama-cli -m model-Q4_K_M.gguf -p "Explain ReAct agents with an example."
- Downloads last month
- 361
Hardware compatibility
Log In
to add your hardware
We're not able to determine the quantization variants.
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for navid72m/gemma-ai-books
Base model
google/gemma-2-2b