Starcoder GPTQ is an open-source language model by TheBloke. Features: 15.8b LLM, VRAM: 8.9GB, License: bigcode-openrail-m, Quantized, Code Generating, LLM Explorer Score: 0.07.
Starcoder GPTQ Parameters and Internals
Model Type Use Cases
Primary Use Cases: Technical assistant with Tech Assistant prompt
Limitations: The model is not an instruction model; commands like 'Write a function that computes the square root.' do not work well.
Additional Notes The model was trained on GitHub code and is primarily designed for code generation, not general text generation.
Supported Languages languages_and_proficiency_levels (>80 programming languages)
Training Details
Data Sources: The Stack (v1.2) with opt-out requests excluded
Data Volume: Methodology: Fill-in-the-Middle objective, Multi Query Attention
Context Length: Training Time: Hardware Used: Model Architecture: GPT-2 model with multi-query attention and Fill-in-the-Middle objective
Input Output
Input Format: Accepted Modalities: Output Format: Performance Tips: Use the Tech Assistant prompt for better results.
Rank the Starcoder GPTQ 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 Starcoder GPTQ
Note: green Score (e.g. "73.2 ") means that the model is better than TheBloke/starcoder-GPTQ .
Expand