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

Laserxtral by cognitivecomputations

 »  All LLMs  »  cognitivecomputations  »  Laserxtral   URL Share it on

  4231   
  Autotrain compatible   Endpoints compatible   Mixtral   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/cognitivecomputations/laserxtral 

Laserxtral Benchmarks

ARC: 69.03 vs 96.7 (so35)-28.6%
HellaSwag: 86.76 vs 95.3 (gpt4)-9%
MMLU: 64.68 vs 88.3 (so35)-26.7%
TruthfulQA: 63.8 vs 59 (gpt4)8.1%
WinoGrande: 80.03 vs 87.5 (gpt4)-8.5%
GSM8K: 69.75 vs 96.4 (so35)-27.6%
LLME Score: 0.2115
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Laserxtral (cognitivecomputations/laserxtral)

Laserxtral Parameters and Internals

Model Type 
Mixture of Experts
Additional Notes 
The model is an experimentation focusing on 'lasering' each expert to denoise and enhance capabilities. It shows high truthfulness and reasoning capabilities.
LLM NameLaserxtral
Repository 🤗https://huggingface.co/cognitivecomputations/laserxtral 
Model Size7b
Required VRAM48.3 GB
Updated2025-02-05
Maintainercognitivecomputations
Model Typemixtral
Model Files  9.9 GB: 1-of-5   10.0 GB: 2-of-5   10.0 GB: 3-of-5   10.0 GB: 4-of-5   8.4 GB: 5-of-5
Model ArchitectureMixtralForCausalLM
Licensecc-by-nc-2.0
Context Length32768
Model Max Length32768
Transformers Version4.36.2
Tokenizer ClassLlamaTokenizer
Padding Token<s>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to Laserxtral

Best Alternatives
Context / RAM
Downloads
Likes
Multimaster 7B V632K / 142.5 GB41781
NeuralStar FusionWriter 4x7b32K / 48.3 GB65
Mixtral 7B 8expert32K / 93.6 GB9186264
Multilingual Mistral32K / 93.5 GB12332
MultiverseBuddy 15B MoE32K / 25.8 GB90
Mini Mixtral V0.232K / 25.8 GB574
OpenMistral MoE32K / 48.3 GB12180
Merged Model MoE32K / 53.3 GB61
Lumina 232K / 37.1 GB50
RogerWizard 12B MoE32K / 25.8 GB61
Note: green Score (e.g. "73.2") means that the model is better than cognitivecomputations/laserxtral.

Rank the Laserxtral 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? 42577 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