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

Hebrew Mistral 7B by yam-peleg

 »  All LLMs  »  yam-peleg  »  Hebrew Mistral 7B   URL Share it on

  3706   
  Autotrain compatible   En   Endpoints compatible   He   Mistral   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/yam-peleg/Hebrew-Mistral-7B 

Hebrew Mistral 7B Benchmarks

MMLU Pro: 19.78
GPQA: 3.91
MUSR: 7.67
BBH: 20.18
IFEval: 23.28 vs 88 (so35)-73.5%
ARC: 59.73 vs 96.7 (so35)-38.2%
HellaSwag: 80.77 vs 95.3 (gpt4)-15.2%
MMLU: 59.52 vs 88.3 (so35)-32.6%
TruthfulQA: 48.16 vs 59 (gpt4)-18.4%
WinoGrande: 74.03 vs 87.5 (gpt4)-15.4%
GSM8K: 30.33 vs 96.4 (so35)-68.5%
MATH Lvl 5: 4.98
LLME Score: 0.24713
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Hebrew Mistral 7B (yam-peleg/Hebrew-Mistral-7B)
🌟 Advertise your project 🚀

Hebrew Mistral 7B Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
natural language processing
Limitations:
No built-in moderation mechanisms
Additional Notes 
The model is continuously pretrained from Mistral-7B on tokens in both English and Hebrew.
Supported Languages 
languages_list (en, he), proficiency (high)
Training Details 
Model Architecture:
Large Language Model (LLM)
Input Output 
Input Format:
Text input in Hebrew or English.
Accepted Modalities:
text
Output Format:
Generated text output.
LLM NameHebrew Mistral 7B
Repository 🤗https://huggingface.co/yam-peleg/Hebrew-Mistral-7B 
Model Size7b
Required VRAM15 GB
Updated2025-08-20
Maintaineryam-peleg
Model Typemistral
Model Files  5.0 GB: 1-of-4   4.9 GB: 2-of-4   4.6 GB: 3-of-4   0.5 GB: 4-of-4
Supported Languagesen he
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.38.1
Tokenizer ClassLlamaTokenizer
Padding Token[PAD]
Vocabulary Size64001
Torch Data Typebfloat16

Quantized Models of the Hebrew Mistral 7B

Model
Likes
Downloads
VRAM
Hebrew Mistral 7B Chat GGUF0515 GB

Best Alternatives to Hebrew Mistral 7B

Best Alternatives
Context / RAM
Downloads
Likes
...Nemo Instruct 2407 Abliterated1000K / 24.5 GB18718
MegaBeam Mistral 7B 512K512K / 14.4 GB837950
SpydazWeb AI HumanAI RP512K / 14.4 GB941
SpydazWeb AI HumanAI 002512K / 14.4 GB181
...daz Web AI ChatML 512K Project512K / 14.5 GB120
MegaBeam Mistral 7B 300K282K / 14.4 GB377916
MegaBeam Mistral 7B 300K282K / 14.4 GB739216
Hebrew Mistral 7B 200K256K / 30 GB116415
Astral 256K 7B V2250K / 14.4 GB50
Astral 256K 7B250K / 14.4 GB50
Note: green Score (e.g. "73.2") means that the model is better than yam-peleg/Hebrew-Mistral-7B.

Rank the Hebrew Mistral 7B 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? 50767 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