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

OpenHermes 2.5 Mistral 7B Bnb 4bit by unsloth

 »  All LLMs  »  unsloth  »  OpenHermes 2.5 Mistral 7B Bnb 4bit   URL Share it on

  230   
  4-bit   4bit   Autotrain compatible   Bitsandbytes   Conversational   En   Endpoints compatible   Mistral   Quantized   Region:us   Safetensors   Unsloth
Model Card on HF 🤗: https://huggingface.co/unsloth/OpenHermes-2.5-Mistral-7B-bnb-4bit 

OpenHermes 2.5 Mistral 7B Bnb 4bit Benchmarks

ARC: 67.49 vs 96.7 (so35)-30.2%
HellaSwag: 85.23 vs 95.3 (gpt4)-10.6%
MMLU: 63.46 vs 88.3 (so35)-28.1%
TruthfulQA: 54.41 vs 59 (gpt4)-7.8%
WinoGrande: 78.22 vs 87.5 (gpt4)-10.6%
GSM8K: 33.51 vs 96.4 (so35)-65.2%
LLME Score: 0.16814
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
OpenHermes 2.5 Mistral 7B Bnb 4bit (unsloth/OpenHermes-2.5-Mistral-7B-bnb-4bit)
🌟 Advertise your project 🚀

OpenHermes 2.5 Mistral 7B Bnb 4bit Parameters and Internals

Use Cases 
Areas:
Finetuning and Performance Optimization
Applications:
Finetuning models such as Gemma, Mistral, Llama, and CodeLlama
Primary Use Cases:
Optimizing model finetuning to be faster and more memory efficient
Limitations:
Specific efficiencies and improvements may vary based on hardware used
Considerations:
Beginner friendly approach emphasizing ease of use.
LLM NameOpenHermes 2.5 Mistral 7B Bnb 4bit
Repository 🤗https://huggingface.co/unsloth/OpenHermes-2.5-Mistral-7B-bnb-4bit 
Base Model(s)  monster119120/OpenHermes-2.5-Mistral-7B-new   monster119120/OpenHermes-2.5-Mistral-7B-new
Model Size7b
Required VRAM4.1 GB
Updated2025-09-23
Maintainerunsloth
Model Typemistral
Model Files  4.1 GB
Supported Languagesen
Quantization Type4bit
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.38.2
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32002
Torch Data Typebfloat16

Quantized Models of the OpenHermes 2.5 Mistral 7B Bnb 4bit

Model
Likes
Downloads
VRAM
Kheops Hermes E1 V0.6 Bnb 4bit0624 GB
Kheops Fr En Epoch1 16bit V408214 GB
Kheops Fr En Epoch1 4bit V40614 GB
Redhermes02014 GB
Kheops Fr En Epoch1 16bit V301514 GB
Kheops Fr En Epoch7 16bit V201314 GB
Kheops Epoch 105614 GB
Kheops Fr En Epoch1 16bit01814 GB
Kheops Fr En Epoch1 4bit V20174 GB
Kheops Fr En Epoch1 V1 16b01628 GB

Best Alternatives to OpenHermes 2.5 Mistral 7B Bnb 4bit

Best Alternatives
Context / RAM
Downloads
Likes
...al Nemo Instruct 2407 Bnb 4bit128K / 8.3 GB450229
...istral Nemo Base 2407 Bnb 4bit128K / 8.3 GB141015
...t 3.5 0106 128K 4.0bpw H6 EXL2128K / 3.9 GB81
...t 3.5 0106 128K 8.0bpw H8 EXL2128K / 7.4 GB71
Mistral 7B V0.3 Bnb 4bit32K / 4.1 GB40516318
...tral 7B Instruct V0.3 Bnb 4bit32K / 4.1 GB3043728
Mistral 7B Instruct V0.2 Fp1632K / 14.4 GB260
Mistral 7B Instruct V0.2 4bit32K / 4.3 GB1331
...tral 7B Instruct V0.2 Bnb 4bit32K / 4.1 GB1376233
Mixtral V0.3 Full 16bit32K / 14.5 GB60
Note: green Score (e.g. "73.2") means that the model is better than unsloth/OpenHermes-2.5-Mistral-7B-bnb-4bit.

Rank the OpenHermes 2.5 Mistral 7B Bnb 4bit 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? 51544 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 v20241124
  Support LLM Explorer