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

Mahou 1.2a Llama3 8B by flammenai

 »  All LLMs  »  flammenai  »  Mahou 1.2a Llama3 8B   URL Share it on

  21   
  Autotrain compatible Base model:finetune:nbeerbower... Base model:nbeerbower/llama-3-...   Conversational Dataset:flammenai/flamemix-dpo... Dataset:flammenai/grill-prepro... Dataset:flammenai/grill-prepro...   Endpoints compatible   Llama   Model-index   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/flammenai/Mahou-1.2a-llama3-8B 

Mahou 1.2a Llama3 8B Benchmarks

MMLU Pro: 31.3
GPQA: 5.15
MUSR: 6.02
BBH: 28.97
IFEval: 50.93 vs 88 (so35)-42.1%
ARC: 68.86 vs 96.7 (so35)-28.8%
HellaSwag: 83.97 vs 95.3 (gpt4)-11.9%
MMLU: 68.52 vs 88.3 (so35)-22.4%
TruthfulQA: 58.76 vs 59 (gpt4)-0.4%
WinoGrande: 77.58 vs 87.5 (gpt4)-11.3%
GSM8K: 71.11 vs 96.4 (so35)-26.2%
MATH Lvl 5: 8.38
LLME Score: 0.24256
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
🌟 Advertise your project 🚀

Mahou 1.2a Llama3 8B Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
conversational AI, roleplay
Additional Notes 
The model is intended to be production-ready and suitable for conversational and roleplay functionalities.
Training Details 
Data Sources:
flammenai/FlameMix-DPO-v1, flammenai/Grill-preprod-v1_chatML, flammenai/Grill-preprod-v2_chatML
Methodology:
Fine-tuned using Direct Preference Optimization on an A100 on Google Colab.
Hardware Used:
A100 GPU
Model Architecture:
LoRA configuration with additional fine-tuning settings specified
Input Output 
Input Format:
ChatML
Accepted Modalities:
text
LLM NameMahou 1.2a Llama3 8B
Repository 🤗https://huggingface.co/flammenai/Mahou-1.2a-llama3-8B 
Base Model(s)  Llama 3 Stheno Mahou 8B   nbeerbower/llama-3-Stheno-Mahou-8B
Model Size8b
Required VRAM16.1 GB
Updated2025-06-11
Maintainerflammenai
Model Typellama
Model Files  5.0 GB: 1-of-4   5.0 GB: 2-of-4   4.9 GB: 3-of-4   1.2 GB: 4-of-4
Model ArchitectureLlamaForCausalLM
Licensellama3
Context Length8192
Model Max Length8192
Transformers Version4.41.0
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
Torch Data Typebfloat16
Mahou 1.2a Llama3 8B (flammenai/Mahou-1.2a-llama3-8B)

Quantized Models of the Mahou 1.2a Llama3 8B

Model
Likes
Downloads
VRAM
Mahou 1.2a Llama3 8B AWQ1265 GB

Best Alternatives to Mahou 1.2a Llama3 8B

Best Alternatives
Context / RAM
Downloads
Likes
...otron 8B UltraLong 4M Instruct4192K / 32.1 GB3715108
UltraLong Thinking4192K / 16.1 GB8292
...a 3.1 8B UltraLong 4M Instruct4192K / 32.1 GB17624
...otron 8B UltraLong 2M Instruct2096K / 32.1 GB92315
...a 3.1 8B UltraLong 2M Instruct2096K / 32.1 GB8759
Zero Llama 3.1 8B Beta61048K / 16.1 GB14161
...otron 8B UltraLong 1M Instruct1048K / 32.1 GB207045
...a 3.1 8B UltraLong 1M Instruct1048K / 32.1 GB138729
...xis Bookwriter Llama3.1 8B Sft1048K / 16.1 GB634
....1 1million Ctx Dark Planet 8B1048K / 32.3 GB952
Note: green Score (e.g. "73.2") means that the model is better than flammenai/Mahou-1.2a-llama3-8B.

Rank the Mahou 1.2a Llama3 8B 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? 48104 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