Small Instruct by amphora

 ยป  All LLMs  ยป  amphora  ยป  Small Instruct   URL Share it on

  Autotrain compatible   Endpoints compatible   Instruct   Llama   Lora   Pytorch   Region:us
Model Card on HF ๐Ÿค—: https://huggingface.co/amphora/small-instruct 

Small Instruct Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Small Instruct (amphora/small-instruct)

Small Instruct Parameters and Internals

LLM NameSmall Instruct
Repository ๐Ÿค—https://huggingface.co/amphora/small-instruct 
Required VRAM2.9 GB
Updated2024-12-22
Maintaineramphora
Model Typellama
Instruction-BasedYes
Model Files  2.9 GB
Model ArchitectureLlamaForCausalLM
Licensecc-by-nc-4.0
Context Length4096
Model Max Length4096
Transformers Version4.35.0.dev0
Tokenizer ClassGPT2TokenizerFast
Padding Token<||pad||>
Vocabulary Size50304
LoRA ModelYes
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Small Instruct

Best Alternatives
Context / RAM
Downloads
Likes
Reverse Instruct32K / 27 GB353
Etri Ones Solar4K / 42.9 GB750
Law Chat4K / 27 GB121432
Phi 3 Orpo V8.164K / 7.6 GB210
Tinyllama Python4K / 2.2 GB241
Taiwan LLaMa V1.04K / 26 GB55776
Model 007 Preview4K / 138 GB5511
Taiwan LLaMa V0.04K / 26 GB191
Taiwan LLaMa V0.94K / 26 GB190
Kolong Llama V0.12K / 13.7 GB48510
Note: green Score (e.g. "73.2") means that the model is better than amphora/small-instruct.

Rank the Small Instruct Capabilities

๐Ÿ†˜ Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! ๐ŸŒŸ

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  

What open-source LLMs or SLMs are you in search of? 40066 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217