Gemma 2B Coder is an open-source language model by MAISAAI. Features: 2b LLM, VRAM: 5.1GB, Context: 8K, LLM Explorer Score: 0.14, Arc: 49, HellaSwag: 71.4, MMLU: 37, GSM8K: 16.1.
Gemma 2B Coder Parameters and Internals
Model Type text-to-text, decoder-only, large language model
Use Cases
Primary Use Cases: text generation tasks, including question answering, summarization, and reasoning
Additional Notes The model is fine-tuned and optimized for coding tasks.
Supported Languages Training Details
Data Sources: HuggingFaceH4/CodeAlpaca_20K
Data Volume: 20K instruction-following data
Methodology: Fine-tuning using QLoRA with PEFT library
Training Time: 1h 40 min on Free Colab T4 GPU (16GB VRAM)
Hardware Used: Free Colab T4 GPU (16GB VRAM)
Model Architecture: Text-to-text, decoder-only large language model
Input Output
Input Format: Formatted prompt with system and user input indicators
Accepted Modalities: Output Format: Text response separated by <|assistant|> indicator
Rank the Gemma 2B Coder capabilities
Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.
Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation
Quantized Models of the Gemma 2B Coder
Best Alternatives to Gemma 2B Coder
Note: green Score (e.g. "73.2 ") means that the model is better than MAISAAI/gemma-2b-coder .
Expand