Jellyfish 13B by NECOUDBFM

 ยป  All LLMs  ยป  NECOUDBFM  ยป  Jellyfish 13B   URL Share it on

  Arxiv:1904.02285   Arxiv:2004.00584   Arxiv:2205.09911   Arxiv:2301.13688   Arxiv:2306.00745   Arxiv:2306.02707   Arxiv:2308.07317   Arxiv:2308.16361   Arxiv:2310.12537   Arxiv:2312.01678   Autotrain compatible   En   Endpoints compatible   Llama   Pytorch   Region:us   Sharded
Model Card on HF ๐Ÿค—: https://huggingface.co/NECOUDBFM/Jellyfish-13B 

Jellyfish 13B Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Jellyfish 13B (NECOUDBFM/Jellyfish-13B)

Jellyfish 13B Parameters and Internals

Model Type 
Large Language Model, Data Preprocessing
Use Cases 
Areas:
data preprocessing, NLP
Primary Use Cases:
error detection, data imputation, schema matching, entity matching
Supported Languages 
English (High proficiency)
Training Details 
Data Sources:
HazyResearch/fm_data_tasks, RAHA, SMAT, IPM
Methodology:
Fine-tuning using instruction tuning datasets
LLM NameJellyfish 13B
Repository ๐Ÿค—https://huggingface.co/NECOUDBFM/Jellyfish-13B 
Model Size13b
Required VRAM26 GB
Updated2025-01-15
MaintainerNECOUDBFM
Model Typellama
Model Files  9.9 GB: 1-of-3   9.9 GB: 2-of-3   6.2 GB: 3-of-3
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licensecc-by-nc-4.0
Context Length4096
Model Max Length4096
Transformers Version4.34.1
Tokenizer ClassLlamaTokenizer
Vocabulary Size32002
Torch Data Typefloat16

Best Alternatives to Jellyfish 13B

Best Alternatives
Context / RAM
Downloads
Likes
Yarn Llama 2 13B 128K128K / 26 GB3984113
Luminaura RP 13B128K / 26 GB220
Agent Llama2 13B 80K80K / 26.4 GB120
Chat Llama2 13B 80K80K / 52.8 GB90
LongAlign 13B 64K64K / 26 GB4013
LongAlign 13B 64K Base64K / 26 GB143
Openbuddy Llama2 13B V15p1 64K64K / 26.1 GB144
Yarn Llama 2 13B 64K64K / 26 GB195817
Openbuddy Llama2 13b64k V1564K / 26.1 GB181
Airoboros L2 13B 2.1 YaRN 64K64K / 26 GB147
Note: green Score (e.g. "73.2") means that the model is better than NECOUDBFM/Jellyfish-13B.

Rank the Jellyfish 13B 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? 41363 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227