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

Nous Hermes 2 Mixtral 8x7B DPO by NousResearch

 »  All LLMs  »  NousResearch  »  Nous Hermes 2 Mixtral 8x7B DPO   URL Share it on

  2900   
  Autotrain compatible Base model:finetune:mistralai/... Base model:mistralai/mixtral-8...   Chatml   Conversational   Dataset:teknium/openhermes-2.5   Distillation   Dpo   En   Endpoints compatible   Finetuned   Gpt4   Instruct   Mixtral   Moe   Region:us   Rlhf   Safetensors   Sharded   Synthetic data   Tensorflow
Model Card on HF 🤗: https://huggingface.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO 

Nous Hermes 2 Mixtral 8x7B DPO Benchmarks

LMSys ELO: 1084 vs 1272 (so35)-14.8%
MMLU Pro: 29.62
GPQA: 9.51
MUSR: 16.68
BBH: 37.11
IFEval: 58.97 vs 88 (so35)-33%
ARC: 71.42 vs 96.7 (so35)-26.1%
HellaSwag: 87.21 vs 95.3 (gpt4)-8.5%
MMLU: 72.28 vs 88.3 (so35)-18.1%
TruthfulQA: 54.53 vs 59 (gpt4)-7.6%
WinoGrande: 82.64 vs 87.5 (gpt4)-5.6%
GSM8K: 70.66 vs 96.4 (so35)-26.7%
MATH Lvl 5: 11.86
LLME Score: 0.4001
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Nous Hermes 2 Mixtral 8x7B DPO (NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO)

Nous Hermes 2 Mixtral 8x7B DPO Parameters and Internals

Model Type 
instruct, finetune, chatml, DPO, RLHF, gpt4, synthetic data, distillation
Additional Notes 
Nous Hermes 2 Mixtral 8x7B DPO is the new flagship Nous Research model.
Supported Languages 
en (English)
Training Details 
Data Sources:
teknium/OpenHermes-2.5
Data Volume:
1,000,000 entries
Methodology:
SFT + DPO
Model Architecture:
Mixtral 8x7B MoE LLM
Input Output 
Input Format:
ChatML
Accepted Modalities:
text
Output Format:
text
LLM NameNous Hermes 2 Mixtral 8x7B DPO
Repository 🤗https://huggingface.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO 
Base Model(s)  mistralai/Mixtral-8x7B-v0.1   mistralai/Mixtral-8x7B-v0.1
Model Size46.7b
Required VRAM93.6 GB
Updated2025-01-14
MaintainerNousResearch
Model Typemixtral
Model Files  4.9 GB: 1-of-19   5.0 GB: 2-of-19   5.0 GB: 3-of-19   4.9 GB: 4-of-19   5.0 GB: 5-of-19   5.0 GB: 6-of-19   4.9 GB: 7-of-19   5.0 GB: 8-of-19   5.0 GB: 9-of-19   4.9 GB: 10-of-19   5.0 GB: 11-of-19   5.0 GB: 12-of-19   5.0 GB: 13-of-19   4.9 GB: 14-of-19   5.0 GB: 15-of-19   5.0 GB: 16-of-19   4.9 GB: 17-of-19   5.0 GB: 18-of-19   4.2 GB: 19-of-19
Supported Languagesen
Model ArchitectureMixtralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.37.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32002
Torch Data Typebfloat16

Quantized Models of the Nous Hermes 2 Mixtral 8x7B DPO

Model
Likes
Downloads
VRAM
...Hermes 2 Mixtral 8x7B DPO GGUF57138917 GB
...Hermes 2 Mixtral 8x7B DPO GPTQ2625623 GB
...Hermes 2 Mixtral 8x7B DPO GGUF216017 GB
... Hermes 2 Mixtral 8x7B DPO AWQ227124 GB
...Hermes 2 Mixtral 8x7B DPO GPTQ12724 GB

Best Alternatives to Nous Hermes 2 Mixtral 8x7B DPO

Best Alternatives
Context / RAM
Downloads
Likes
Mixtral 8x7B Instruct V0.132K / 93.6 GB40519094265
Mixtral 8x7B V0.132K / 93.6 GB36842181659
GritLM 8x7B KTO32K / 93.6 GB31723
Dolphin 2.5 Mixtral 8x7b32K / 93.6 GB142311221
Smaug Mixtral V0.132K / 187.7 GB325812
...enbuddy Mixtral 7bx8 V18.1 32K32K / 93.7 GB101214
Merge Mixtral Prometheus 8x7B32K / 91.9 GB362
Sensualize Mixtral Bf1632K / 93.6 GB00
XLAM 8x7b R32K / 93.6 GB149112
Skadi Mixtral V132K / 93.5 GB00
Note: green Score (e.g. "73.2") means that the model is better than NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO.

Rank the Nous Hermes 2 Mixtral 8x7B DPO 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? 41362 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