LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

LION Gemma 2B Sft V1.0 by Columbia-NLP

 »  All LLMs  »  Columbia-NLP  »  LION Gemma 2B Sft V1.0   URL Share it on

  72   
  Arxiv:2407.06542   Autotrain compatible   Conversational   Endpoints compatible   Gemma   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Columbia-NLP/LION-Gemma-2b-sft-v1.0 

LION Gemma 2B Sft V1.0 Benchmarks

MMLU Pro: 8.69
GPQA: 0.78
MUSR: 8.31
BBH: 14.12
IFEval: 36.92 vs 88 (so35)-58%
MATH Lvl 5: 6.8
LLME Score: 0.23123
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
LION Gemma 2B Sft V1.0 (Columbia-NLP/LION-Gemma-2b-sft-v1.0)

LION Gemma 2B Sft V1.0 Parameters and Internals

Model Type 
text-generation
Supported Languages 
English (Primary)
Training Details 
Methodology:
SFT, DPO, and online preference learning (online DPO)
LLM NameLION Gemma 2B Sft V1.0
Repository 🤗https://huggingface.co/Columbia-NLP/LION-Gemma-2b-sft-v1.0 
Model Size2b
Required VRAM5.1 GB
Updated2025-03-12
MaintainerColumbia-NLP
Model Typegemma
Model Files  5.0 GB: 1-of-2   0.1 GB: 2-of-2
Model ArchitectureGemmaForCausalLM
Context Length8192
Model Max Length8192
Transformers Version4.41.1
Tokenizer ClassGemmaTokenizer
Padding Token<pad>
Vocabulary Size256000
Torch Data Typebfloat16

Best Alternatives to LION Gemma 2B Sft V1.0

Best Alternatives
Context / RAM
Downloads
Likes
Gemma 1.1 2B It8K / 5.1 GB117661156
Codegemma 2B8K / 5.1 GB499978
Gemma Ko 1.1 2B It8K / 5.1 GB20491
EMO 2B8K / 5.1 GB44642
Octopus V28K / 5.1 GB1059882
Gemma 2B It Customer Support8K / 10 GB238161
... 2B Finetuned Sft Navarasa 2.08K / 10 GB29423
Gemma 2B Orpo8K / 5.1 GB16628
2B Or Not 2B8K / 5.1 GB5827
Gemma2b Lungcancerqa8K / 3.1 GB122
Note: green Score (e.g. "73.2") means that the model is better than Columbia-NLP/LION-Gemma-2b-sft-v1.0.

Rank the LION Gemma 2B Sft V1.0 Capabilities

🆘 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! 🌟

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? 44887 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227
  Support LLM Explorer