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

Mahou 1.3 Mistral 7B by flammenai

 »  All LLMs  »  flammenai  »  Mahou 1.3 Mistral 7B   URL Share it on

  8   
  Autotrain compatible Base model:finetune:nbeerbower... Base model:nbeerbower/flammen-...   Conversational   Dataset:flammenai/mahoumix-v1   Endpoints compatible   Mistral   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/flammenai/Mahou-1.3-mistral-7B 

Mahou 1.3 Mistral 7B Benchmarks

ARC: 70.05 vs 96.7 (so35)-27.6%
HellaSwag: 87.29 vs 95.3 (gpt4)-8.4%
MMLU: 64.57 vs 88.3 (so35)-26.9%
TruthfulQA: 67.59 vs 59 (gpt4)14.6%
WinoGrande: 80.03 vs 87.5 (gpt4)-8.5%
GSM8K: 58.07 vs 96.4 (so35)-39.8%
LLME Score: 0.19839
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Mahou 1.3 Mistral 7B (flammenai/Mahou-1.3-mistral-7B)

Mahou 1.3 Mistral 7B Parameters and Internals

Model Type 
conversational, roleplay
Use Cases 
Applications:
Conversational, Roleplay
Additional Notes 
Version is iteratively finetuned from flammen.ai conversational data.
Training Details 
Data Sources:
flammenai/MahouMix-v1
Methodology:
Model has been finetuned iteratively from flammen.ai conversational data. Trained to use ChatML format. Fine-tuned using ORPO for 10 epochs on an A100 on Google Colab.
Hardware Used:
A100 on Google Colab
Input Output 
Input Format:
ChatML
Performance Tips:
Recommended to add newline as a stopping string: ['\n'].
LLM NameMahou 1.3 Mistral 7B
Repository 🤗https://huggingface.co/flammenai/Mahou-1.3-mistral-7B 
Base Model(s)  Flammen Mahou Mistral 7B   nbeerbower/Flammen-Mahou-mistral-7B
Model Size7b
Required VRAM14.4 GB
Updated2025-02-22
Maintainerflammenai
Model Typemistral
Model Files  4.9 GB: 1-of-3   5.0 GB: 2-of-3   4.5 GB: 3-of-3
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.41.1
Tokenizer ClassLlamaTokenizer
Padding Token<|im_end|>
Vocabulary Size32002
Torch Data Typebfloat16

Quantized Models of the Mahou 1.3 Mistral 7B

Model
Likes
Downloads
VRAM
Mahou 1.3 Mistral 7B AWQ0874 GB

Best Alternatives to Mahou 1.3 Mistral 7B

Best Alternatives
Context / RAM
Downloads
Likes
...Nemo Instruct 2407 Abliterated1000K / 24.5 GB462011
MegaBeam Mistral 7B 512K512K / 14.4 GB568150
SpydazWeb AI HumanAI RP512K / 14.4 GB121
SpydazWeb AI HumanAI 002512K / 14.4 GB181
...daz Web AI ChatML 512K Project512K / 14.5 GB120
MegaBeam Mistral 7B 300K282K / 14.4 GB563316
Hebrew Mistral 7B 200K256K / 30 GB1461915
Astral 256K 7B V2250K / 14.4 GB70
Astral 256K 7B250K / 14.4 GB50
Test001128K / 14.5 GB90
Note: green Score (e.g. "73.2") means that the model is better than flammenai/Mahou-1.3-mistral-7B.

Rank the Mahou 1.3 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? 43470 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