Wizardcoder 1B Merged is an open-source language model by epinnock. Features: 1b LLM, VRAM: 2.3GB, License: bigcode-openrail-m, Instruction-Based, Code Generating, LLM Explorer Score: 0.08.
Wizardcoder 1B Merged Parameters and Internals
Model Type causal_lm, Fill-in-the-Middle
Use Cases
Areas: source code generation, multilingual programming
Applications: Primary Use Cases: generating and reconstructing code snippets
Limitations: Inconsistent code quality, potential bugs, and exploits
Considerations: Consider verifying generated code manually
Additional Notes Pretraining dataset filtered for permissive licenses; offers a search index for pretraining data to apply proper attribution.
Supported Languages Training Details
Data Sources: nickrosh/Evol-Instruct-Code-80k-v1
Methodology: LoRa finetuning on Evol-Instruct-Code-80k-v1 dataset
Context Length: Training Time: Hardware Used: Model Architecture: StarCoder GPT-2 model with multi-query attention and Fill-in-the-Middle objective with LoRA layers merged
Input Output
Input Format: Text encoded as input tensors
Accepted Modalities: Output Format: Text encoded as output tensors
Performance Tips: Use GPUs like A5000 for optimal performance
Rank the Wizardcoder 1B Merged 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 Wizardcoder 1B Merged
Note: green Score (e.g. "73.2 ") means that the model is better than epinnock/wizardcoder-1b-merged .
Expand