Akins 3B by acrastt

 ยป  All LLMs  ยป  acrastt  ยป  Akins 3B   URL Share it on

  Arxiv:2305.14314   Autotrain compatible   Custom code Dataset:norquinal/claude multi...   En   Pytorch   Region:us   Stablelm epoch
Model Card on HF ๐Ÿค—: https://huggingface.co/acrastt/Akins-3B 

Akins 3B Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Akins 3B (acrastt/Akins-3B)

Akins 3B Parameters and Internals

Model Type 
text generation
Additional Notes 
GGUF quantizations available [here](https://huggingface.co/TheBloke/Akins-3B-GGUF). GPTQ quantizations available [here](https://huggingface.co/TheBloke/Akins-3B-GPTQ).
Supported Languages 
en (English)
Training Details 
Data Sources:
Norquinal/claude_multiround_chat_1k
Methodology:
instruction-tuned with QLoRA
Training Time:
2 epochs
Input Output 
Input Format:
USER: {prompt} ASSISTANT:
Accepted Modalities:
text
LLM NameAkins 3B
Repository ๐Ÿค—https://huggingface.co/acrastt/Akins-3B 
Model Size3b
Required VRAM5.6 GB
Updated2024-12-23
Maintaineracrastt
Model Typestablelm_epoch
Model Files  5.6 GB
Supported Languagesen
Model ArchitectureStableLMEpochForCausalLM
Licensecc-by-sa-4.0
Context Length4096
Model Max Length4096
Transformers Version4.35.0.dev0
Tokenizer ClassGPTNeoXTokenizerFast
Vocabulary Size50304
Torch Data Typefloat16

Quantized Models of the Akins 3B

Model
Likes
Downloads
VRAM
Akins 3B GGUF81401 GB
Akins 3B GPTQ2261 GB

Best Alternatives to Akins 3B

Best Alternatives
Context / RAM
Downloads
Likes
Stable Code 3B Mlx16K / 5.6 GB91
Aura 3B4K / 5.6 GB112
Slim Extract4K / 5.6 GB2512
Slim Boolean4K / 5.6 GB194
Slim Summary4K / 5.6 GB597
Slim Tags 3B4K / 5.6 GB124
Slim Sa Ner4K / 5.6 GB86
Slim Xsum4K / 5.6 GB56
Memphis CoT 3B4K / 5.6 GB7329
Tofu 3B4K / 5.6 GB102
Note: green Score (e.g. "73.2") means that the model is better than acrastt/Akins-3B.

Rank the Akins 3B 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? 40126 in total.

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