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

MN 12B Lyra V3 by Sao10K

 »  All LLMs  »  Sao10K  »  MN 12B Lyra V3   URL Share it on

  0   
  En   Mistral   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Sao10K/MN-12B-Lyra-v3 

MN 12B Lyra V3 Benchmarks

MMLU Pro: 24.99
GPQA: 3.69
MUSR: 9.04
BBH: 25.87
IFEval: 44.86 vs 88 (so35)-49%
MATH Lvl 5: 7.93
LLME Score: 0.29082
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
MN 12B Lyra V3 (Sao10K/MN-12B-Lyra-v3)

MN 12B Lyra V3 Parameters and Internals

Model Type 
text generation
Additional Notes 
Original format was meant for an 8B pruned NeMo train.
Training Details 
Data Sources:
A custom, cleaned mix of Stheno-v3.4's Dataset
Methodology:
Multi-turn training with RL step, Magpie-style responses.
Training Time:
6 Hours
Hardware Used:
4xH100 SXM
Input Output 
Input Format:
ChatML-style prompting Format
Accepted Modalities:
text
Output Format:
text
Performance Tips:
Recommended samplers: Temperature: 0.7 - 1.2, min_p: 0.1 - 0.2
LLM NameMN 12B Lyra V3
Repository 🤗https://huggingface.co/Sao10K/MN-12B-Lyra-v3 
Model Size12b
Required VRAM24.4 GB
Updated2024-11-27
MaintainerSao10K
Model Typemistral
Model Files  2.0 GB: 1-of-13   1.9 GB: 2-of-13   1.9 GB: 3-of-13   1.9 GB: 4-of-13   1.9 GB: 5-of-13   1.9 GB: 6-of-13   1.9 GB: 7-of-13   1.9 GB: 8-of-13   1.9 GB: 9-of-13   1.9 GB: 10-of-13   1.9 GB: 11-of-13   1.9 GB: 12-of-13   1.5 GB: 13-of-13
Supported Languagesen
Gated ModelYes
Model ArchitectureMistralForCausalLM
Licenseproprietary
Context Length1024000
Model Max Length1024000
Transformers Version4.43.4
Tokenizer ClassPreTrainedTokenizerFast
Padding Token[/INST]
Vocabulary Size131072
Torch Data Typebfloat16

Best Alternatives to MN 12B Lyra V3

Best Alternatives
Context / RAM
Downloads
Likes
...r Nemo 12B Instruct R 21 09 241000K / 24.5 GB2128796
SauerkrautLM Nemo 12B Instruct1000K / 24.5 GB10688822
MISCHIEVOUS 12B Mix 0.4v1000K / 24.5 GB1771
MISCHIEVOUS 12B1000K / 24.5 GB2242
Dolphin 2.9.3 Mistral Nemo 12B1000K / 24.5 GB924587
MISCHIEVOUS 12B Mix III Ex V1000K / 24.5 GB1730
MISCHIEVOUS 12B Mix 0.2v1000K / 24.5 GB1401
MISCHIEVOUS 12B Mix 0.5v1000K / 24.5 GB731
MISCHIEVOUS 12B Mix III IV V1000K / 24.5 GB171
MISCHIEVOUS 12B Mix 0.3v1000K / 24.5 GB1490
Note: green Score (e.g. "73.2") means that the model is better than Sao10K/MN-12B-Lyra-v3.

Rank the MN 12B Lyra V3 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? 40013 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 v20241217
  Support LLM Explorer