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

Gemma 2B Openhermes by QueryloopAI

 »  All LLMs  »  QueryloopAI  »  Gemma 2B Openhermes   URL Share it on

  7   
  Axolotl Base model:finetune:google/gem...   Base model:google/gemma-2b-it   Chatml   Conversational Dataset:mlabonne/chatml-openhe...   Distillation   En   Endpoints compatible   Feature-extraction   Finetuned   Gemma   Generated from trainer   Gpt4   Instruct   Region:us   Safetensors   Sharded   Synthetic data   Tensorflow
Model Card on HF 🤗: https://huggingface.co/QueryloopAI/gemma-2b-openhermes 

Gemma 2B Openhermes Benchmarks

ARC: 43.86 vs 96.7 (so35)-54.6%
HellaSwag: 62.76 vs 95.3 (gpt4)-34.1%
MMLU: 37.7 vs 88.3 (so35)-57.3%
TruthfulQA: 45.84 vs 59 (gpt4)-22.3%
WinoGrande: 61.01 vs 87.5 (gpt4)-30.3%
GSM8K: 5.61 vs 96.4 (so35)-94.2%
LLME Score: 0.19584
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Gemma 2B Openhermes (QueryloopAI/gemma-2b-openhermes)

Gemma 2B Openhermes Parameters and Internals

Model Type 
text generation, instruct, chatml
Use Cases 
Areas:
research, non-commercial applications
Primary Use Cases:
chat-style interactions, language model tasks
Considerations:
Intended for non-commercial use, model is contingent on a chat template for conversational applications.
Additional Notes 
Model integrates Axolotl's customization features for enhanced performance.
Supported Languages 
en (English)
Training Details 
Data Sources:
mlabonne/chatml-OpenHermes2.5-dpo-binarized-alpha
Methodology:
Fine-tuned on the OpenHermes-2.5 preference dataset using QLoRA.
Context Length:
1800
Hardware Used:
cuda (GPU)
Input Output 
Input Format:
Text string input, structured for chat if needed.
Accepted Modalities:
text
Output Format:
Generated English text response.
Performance Tips:
Use chat template as recommended for optimal performance in conversational tasks.
LLM NameGemma 2B Openhermes
Repository 🤗https://huggingface.co/QueryloopAI/gemma-2b-openhermes 
Base Model(s)  Gemma 2B It   google/gemma-2b-it
Model Size2b
Required VRAM10 GB
Updated2025-04-30
MaintainerQueryloopAI
Model Typegemma
Model Files  4.9 GB: 1-of-3   5.0 GB: 2-of-3   0.1 GB: 3-of-3
Supported Languagesen
Model ArchitectureGemmaModel
Licensecc-by-nc-4.0
Context Length8192
Model Max Length8192
Transformers Version4.38.2
Tokenizer ClassGemmaTokenizer
Padding Token<pad>
Vocabulary Size256000
Torch Data Typefloat32

Best Alternatives to Gemma 2B Openhermes

Best Alternatives
Context / RAM
Downloads
Likes
Gemma 2B Def8K / 2.2 GB70
Note: green Score (e.g. "73.2") means that the model is better than QueryloopAI/gemma-2b-openhermes.

Rank the Gemma 2B Openhermes 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? 46860 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