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

Mistral 7B Merge 14 V0.3 by EmbeddedLLM

 »  All LLMs  »  EmbeddedLLM  »  Mistral 7B Merge 14 V0.3   URL Share it on

  23   
  Merged Model   Autotrain compatible Base model:arc53/docsgpt-7b-mi... Base model:beowolx/mistralherm... Base model:cognitivecomputatio... Base model:cognitivecomputatio... Base model:huggingfaceh4/zephy... Base model:meta-math/metamath-... Base model:mistralai/mistral-7... Base model:mlabonne/neuralherm... Base model:open-orca/mistral-7... Base model:openchat/openchat-3... Base model:sciphi/sciphi-mistr... Base model:teknium/openhermes-... Base model:tiger-lab/mammoth-7... Base model:weyaxi/openhermes-2...   En   Endpoints compatible   Instruct   Mistral   Pytorch   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/EmbeddedLLM/Mistral-7B-Merge-14-v0.3 

Mistral 7B Merge 14 V0.3 Benchmarks

ARC: 65.96 vs 96.7 (so35)-31.8%
HellaSwag: 85.29 vs 95.3 (gpt4)-10.5%
MMLU: 64.35 vs 88.3 (so35)-27.1%
TruthfulQA: 57.8 vs 59 (gpt4)-2%
WinoGrande: 78.3 vs 87.5 (gpt4)-10.5%
GSM8K: 66.26 vs 96.4 (so35)-31.3%
LLME Score: 0.13897
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Mistral 7B Merge 14 V0.3 (EmbeddedLLM/Mistral-7B-Merge-14-v0.3)
🌟 Advertise your project 🚀

Mistral 7B Merge 14 V0.3 Parameters and Internals

Additional Notes 
This is an experiment to test merging 14 models using DARE TIES. The model performs well but may require further chat fine-tuning.
Supported Languages 
en (full)
Release Notes 
Version:
v0.4
Date:
2024-01-03
Notes:
Check out the v0.4 model which achieves better scores than v0.3.
LLM NameMistral 7B Merge 14 V0.3
Repository 🤗https://huggingface.co/EmbeddedLLM/Mistral-7B-Merge-14-v0.3 
Base Model(s)  mistralai/Mistral-7B-Instruct-v0.2   ehartford/dolphin-2.2.1-mistral-7b   SciPhi Mistral 7B 32K   ehartford/samantha-1.2-mistral-7b   Docsgpt 7B Mistral   Zephyr 7B Beta   MetaMath Mistral 7B   Mistral 7B OpenOrca   openchat/openchat-3.5-1210   MistralHermes CodePro 7B V1   MAmmoTH 7B Mistral   teknium/OpenHermes-2.5-Mistral-7B   Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp   mlabonne/NeuralHermes-2.5-Mistral-7B   mistralai/Mistral-7B-Instruct-v0.2   ehartford/dolphin-2.2.1-mistral-7b   SciPhi/SciPhi-Mistral-7B-32k   ehartford/samantha-1.2-mistral-7b   Arc53/docsgpt-7b-mistral   HuggingFaceH4/zephyr-7b-beta   meta-math/MetaMath-Mistral-7B   Open-Orca/Mistral-7B-OpenOrca   openchat/openchat-3.5-1210   beowolx/MistralHermes-CodePro-7B-v1   TIGER-Lab/MAmmoTH-7B-Mistral   teknium/OpenHermes-2.5-Mistral-7B   Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp   mlabonne/NeuralHermes-2.5-Mistral-7B
Merged ModelYes
Model Size7b
Required VRAM14.5 GB
Updated2025-09-15
MaintainerEmbeddedLLM
Model Typemistral
Instruction-BasedYes
Model Files  10.0 GB: 1-of-2   4.5 GB: 2-of-2
Supported Languagesen
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.36.1
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to Mistral 7B Merge 14 V0.3

Best Alternatives
Context / RAM
Downloads
Likes
...Nemo Instruct 2407 Abliterated1000K / 24.5 GB6718
SpydazWeb AI HumanAI RP512K / 14.4 GB131
SpydazWeb AI HumanAI 002512K / 14.4 GB181
...daz Web AI ChatML 512K Project512K / 14.5 GB120
... Summarize 64K QLoRANET Merged128K / 4.1 GB60
...1 Summarize 64K LoRANET Merged128K / 14.4 GB80
Mistral 7B Instruct V0.232K / 14.4 GB33160952630
Mistral 7B Instruct V0.132K / 14.4 GB1495791794
Seed X Instruct 7B32K / 15 GB2475123
Mixtral AI CyberCoder32K / 14.3 GB00
Note: green Score (e.g. "73.2") means that the model is better than EmbeddedLLM/Mistral-7B-Merge-14-v0.3.

Rank the Mistral 7B Merge 14 V0.3 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? 51387 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