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

DPOpenHermes 7B V2 by openaccess-ai-collective

 »  All LLMs  »  openaccess-ai-collective  »  DPOpenHermes 7B V2   URL Share it on

  27   
  Autotrain compatible Base model:finetune:teknium/op... Base model:teknium/openhermes-...   Conversational Dataset:allenai/ultrafeedback ...   Dataset:intel/orca dpo pairs   Dataset:teknium/openhermes   En   Endpoints compatible   Mistral   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/openaccess-ai-collective/DPOpenHermes-7B-v2 

DPOpenHermes 7B V2 Benchmarks

ARC: 66.64 vs 96.7 (so35)-31.1%
HellaSwag: 85.22 vs 95.3 (gpt4)-10.6%
MMLU: 63.64 vs 88.3 (so35)-27.9%
TruthfulQA: 59.22 vs 59 (gpt4)0.4%
WinoGrande: 79.16 vs 87.5 (gpt4)-9.5%
GSM8K: 63.61 vs 96.4 (so35)-34%
LLME Score: 0.16506
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
DPOpenHermes 7B V2 (openaccess-ai-collective/DPOpenHermes-7B-v2)

DPOpenHermes 7B V2 Parameters and Internals

Model Type 
text generation
Additional Notes 
This model uses Direct Preference Optimization (DPO) for reinforcement learning and supports a more structured dialogue format enabling multi-turn interactions.
Supported Languages 
en (fluent)
Training Details 
Data Sources:
teknium/openhermes, allenai/ultrafeedback_binarized_cleaned, Intel/orca_dpo_pairs
Methodology:
Fine-tuned using RL with DPO (Direct Preference Optimization).
Training Time:
~13 hours
Hardware Used:
single H100 80GB
Input Output 
Input Format:
ChatML
Accepted Modalities:
text
Output Format:
structured text
LLM NameDPOpenHermes 7B V2
Repository 🤗https://huggingface.co/openaccess-ai-collective/DPOpenHermes-7B-v2 
Base Model(s)  teknium/OpenHermes-2.5-Mistral-7B   teknium/OpenHermes-2.5-Mistral-7B
Model Size7b
Required VRAM14.4 GB
Updated2025-02-05
Maintaineropenaccess-ai-collective
Model Typemistral
Model Files  4.9 GB: 1-of-3   5.0 GB: 2-of-3   4.5 GB: 3-of-3
Supported Languagesen
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.35.2
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32002
Torch Data Typebfloat16

Quantized Models of the DPOpenHermes 7B V2

Model
Likes
Downloads
VRAM
DPOpenHermes 7B V2 GGUF81243 GB
DPOpenHermes 7B V2 GPTQ1254 GB
DPOpenHermes 7B V2 AWQ164 GB

Best Alternatives to DPOpenHermes 7B V2

Best Alternatives
Context / RAM
Downloads
Likes
...Nemo Instruct 2407 Abliterated1000K / 24.5 GB522710
MegaBeam Mistral 7B 512K512K / 14.4 GB655449
SpydazWeb AI HumanAI RP512K / 14.4 GB51
SpydazWeb AI HumanAI 002512K / 14.4 GB181
...daz Web AI ChatML 512K Project512K / 14.5 GB120
MegaBeam Mistral 7B 300K282K / 14.4 GB647215
Hebrew Mistral 7B 200K256K / 30 GB489915
Astral 256K 7B V2250K / 14.4 GB60
Astral 256K 7B250K / 14.4 GB50
Test001128K / 14.5 GB90
Note: green Score (e.g. "73.2") means that the model is better than openaccess-ai-collective/DPOpenHermes-7B-v2.

Rank the DPOpenHermes 7B V2 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? 42577 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