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

MistralTrix V1 by CultriX

 »  All LLMs  »  CultriX  »  MistralTrix V1   URL Share it on

  1828   
  Merged Model   Autotrain compatible   En   Endpoints compatible   Mistral   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/CultriX/MistralTrix-v1 

MistralTrix V1 Benchmarks

ARC: 72.27 vs 96.7 (so35)-25.3%
HellaSwag: 88.33 vs 95.3 (gpt4)-7.3%
MMLU: 65.24 vs 88.3 (so35)-26.1%
TruthfulQA: 70.73 vs 59 (gpt4)19.9%
WinoGrande: 80.98 vs 87.5 (gpt4)-7.5%
GSM8K: 62.77 vs 96.4 (so35)-34.9%
LLME Score: 0.1948
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
MistralTrix V1 (CultriX/MistralTrix-v1)

MistralTrix V1 Parameters and Internals

Model Type 
text-generation
Additional Notes 
Model has been further fine-tuned to surpass original benchmarks and is inspired by RLHF processes described by Intel.
Supported Languages 
en (proficient)
Training Details 
Data Sources:
Intel's dataset for neural-chat-7b-v3-1
Methodology:
Fine-tuning with Direct Preference Optimization (DPO) and applying ChatML template.
Context Length:
1024
Training Time:
less than a few hours
Hardware Used:
Google Colab A-1000 GPU with 40GB VRAM
LLM NameMistralTrix V1
Repository 🤗https://huggingface.co/CultriX/MistralTrix-v1 
Merged ModelYes
Model Size9b
Required VRAM17.9 GB
Updated2025-02-22
MaintainerCultriX
Model Typemistral
Model Files  4.9 GB: 1-of-4   5.0 GB: 2-of-4   4.9 GB: 3-of-4   3.1 GB: 4-of-4
Supported Languagesen
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.35.2
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to MistralTrix V1

Best Alternatives
Context / RAM
Downloads
Likes
Peagle 9B32K / 18 GB105500
Alphacode MALI 9B32K / 17.9 GB20340
GML Mistral Merged V132K / 18 GB19291
MetaMath Mistral Pro32K / 17.9 GB205
...onarch Neurotic 9B Passthrough32K / 17.9 GB260
Mistral 9B Instruct32K / 35.9 GB70
Garbage 9B32K / 17.9 GB243
Notus TheTop 7B Passthrough32K / 18 GB90
Neuronovo 9B V0.432K / 35.9 GB17445
Bepis 9B32K / 18 GB356
Note: green Score (e.g. "73.2") means that the model is better than CultriX/MistralTrix-v1.

Rank the MistralTrix V1 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