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 SFT by NousResearch

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

  229   
  Autotrain compatible Base model:finetune:mistralai/... Base model:mistralai/mixtral-8...   Chatml   Conversational   Dataset:teknium/openhermes-2.5   Distillation   En   Endpoints compatible   Finetuned   Gpt4   Instruct   Mixtral   Moe   Region:us   Safetensors   Sharded   Synthetic data   Tensorflow
Model Card on HF 🤗: https://huggingface.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT 

Nous Hermes 2 Mixtral 8x7B SFT Benchmarks

MMLU Pro: 22.96
GPQA: 6.94
MUSR: 11.14
BBH: 30.59
IFEval: 57.31 vs 88 (so35)-34.9%
ARC: 69.71 vs 96.7 (so35)-27.9%
HellaSwag: 86.74 vs 95.3 (gpt4)-9%
MMLU: 72.21 vs 88.3 (so35)-18.2%
TruthfulQA: 51.22 vs 59 (gpt4)-13.2%
WinoGrande: 82.95 vs 87.5 (gpt4)-5.2%
GSM8K: 69.6 vs 96.4 (so35)-27.8%
MATH Lvl 5: 2.11
LLME Score: 0.23155
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 SFT (NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT)

Nous Hermes 2 Mixtral 8x7B SFT Parameters and Internals

Model Type 
instruct, finetune, chatml, gpt4, synthetic data, distillation
Use Cases 
Areas:
research, commercial applications
Applications:
finetuning and demonstrations
Primary Use Cases:
chat-oriented tasks
Limitations:
Requires more than 24GB of VRAM for inference
Considerations:
Use quantized models for lower VRAM devices.
Additional Notes 
First SFT version; Quantized GGUF models recommended for better performance with lower VRAM.
Supported Languages 
en (high)
Training Details 
Data Sources:
GPT-4 generated data, open datasets
Data Volume:
1,000,000 entries
Methodology:
Supervised finetune only
Hardware Used:
Sponsored by Together.ai
Model Architecture:
Mixtral 8x7B MoE LLM
Input Output 
Input Format:
ChatML; system prompts allow steerability.
Accepted Modalities:
text
Output Format:
text
Performance Tips:
Use quantized versions for reduced VRAM requirements.
LLM NameNous Hermes 2 Mixtral 8x7B SFT
Repository 🤗https://huggingface.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT 
Base Model(s)  mistralai/Mixtral-8x7B-v0.1   mistralai/Mixtral-8x7B-v0.1
Model Size46.7b
Required VRAM93.6 GB
Updated2025-03-12
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 Version4.36.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32002
Torch Data Typebfloat16

Quantized Models of the Nous Hermes 2 Mixtral 8x7B SFT

Model
Likes
Downloads
VRAM
...Hermes 2 Mixtral 8x7B SFT GGUF25209617 GB
...Hermes 2 Mixtral 8x7B SFT GGUF438117 GB
...Hermes 2 Mixtral 8x7B SFT GPTQ1110623 GB
... Hermes 2 Mixtral 8x7B SFT AWQ33824 GB

Best Alternatives to Nous Hermes 2 Mixtral 8x7B SFT

Best Alternatives
Context / RAM
Downloads
Likes
Mixtral 8x7B Instruct V0.132K / 93.6 GB5590644343
Nous Hermes 2 Mixtral 8x7B DPO32K / 93.6 GB8428426
Mixtral 8x7B V0.132K / 93.6 GB338761687
Mixtral 8x7B Instruct V0.1 FP832K / 47.1 GB22820
PLLuM 8x7B Chat32K / 93.6 GB111412
GritLM 8x7B KTO32K / 93.6 GB18663
Sensualize Mixtral Bf1632K / 93.6 GB00
Smaug Mixtral V0.132K / 187.7 GB187712
Skadi Mixtral V132K / 93.5 GB00
Franziska 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-SFT.

Rank the Nous Hermes 2 Mixtral 8x7B SFT 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? 44949 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