1.5 Pints 2K V0.1 is an open-source language model by pints-ai. Features: 1.6b LLM, VRAM: 3.1GB, Context: 2K, License: mit, Instruction-Based, LLM Explorer Score: 0.15.
1.5 Pints 2K V0.1 Parameters and Internals
Model Type Use Cases
Areas: Primary Use Cases: Considerations: Use with Retrieval Augmented Generation for improved knowledge retrieval.
Additional Notes Focuses on data quality for efficiency and environmentally friendly training
Supported Languages Training Details
Data Sources: pints-ai/Expository-Prose-V1, HuggingFaceH4/ultrachat_200k, Open-Orca/SlimOrca-Dedup, meta-math/MetaMathQA, HuggingFaceH4/deita-10k-v0-sft, WizardLM/WizardLM_evol_instruct_V2_196k, togethercomputer/llama-instruct, LDJnr/Capybara, HuggingFaceH4/ultrafeedback_binarized
Data Volume: Methodology: Pre-Train and Finetuning used a fork of the LitGPT Framework
Context Length: Model Architecture: Llama 2 Autoregressive Model with Mistral tokenizer
Input Output
Accepted Modalities: Performance Tips: Use repetition penalty of 1.3 for full performance.
Rank the 1.5 Pints 2K V0.1 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 1.5 Pints 2K V0.1
Note: green Score (e.g. "73.2 ") means that the model is better than pints-ai/1.5-Pints-2K-v0.1 .
Expand