CodeLlama 13B Instruct GGUF is an open-source language model by TheBloke. Features: 13b LLM, VRAM: 5.4GB, License: llama2, Quantized, Instruction-Based, Code Generating, LLM Explorer Score: 0.11.
CodeLlama 13B Instruct GGUF Parameters and Internals
Model Type Use Cases
Areas: Applications: Code synthesis, Understanding tasks
Limitations: Use in manner violating applicable laws or regulations, Use in languages other than English
Additional Notes 1100 hours of GPU computation required for training. Estimated total emissions were 65.3 tCO2eq, 100% offset by Meta’s sustainability program.
Supported Languages Training Details
Hardware Used: Model Architecture: Auto-regressive language model using an optimized transformer architecture.
Safety Evaluation
Ethical Considerations: Code Llama may produce inaccurate or objectionable responses, and safety testing should be performed before deployment.
Responsible Ai Considerations
Mitigation Strategies: See Responsible Use Guide at https://ai.meta.com/llama/responsible-user-guide.
Input Output
Input Format: Accepted Modalities: Output Format:
Rank the CodeLlama 13B Instruct GGUF 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
Best Alternatives to CodeLlama 13B Instruct GGUF
Note: green Score (e.g. "73.2 ") means that the model is better than TheBloke/CodeLlama-13B-Instruct-GGUF .
Expand