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

Bigstral 12B 32K 8xMoE by bartowski

 »  All LLMs  »  bartowski  »  Bigstral 12B 32K 8xMoE   URL Share it on

  5   
  Autotrain compatible Base model:finetune:mistralai/... Base model:mistralai/mistral-7...   Conversational   Endpoints compatible   Instruct   Merge   Mergekit   Mixtral   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/bartowski/bigstral-12b-32k-8xMoE 

Bigstral 12B 32K 8xMoE Benchmarks

LLME Score: 0.17242
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Bigstral 12B 32K 8xMoE (bartowski/bigstral-12b-32k-8xMoE)

Bigstral 12B 32K 8xMoE Parameters and Internals

Additional Notes 
The model is created using Mergekit MoE branch with abacusai/bigstral-12b-32k as a base model. It uses MoE configuration with random gate_mode, and incorporates numerous expert models from the same source without specific prompt modifications.
LLM NameBigstral 12B 32K 8xMoE
Repository 🤗https://huggingface.co/bartowski/bigstral-12b-32k-8xMoE 
Base Model(s)  mistralai/Mistral-7B-Instruct-v0.2   mistralai/Mistral-7B-Instruct-v0.2
Model Size7b
Required VRAM163.3 GB
Updated2025-02-05
Maintainerbartowski
Model Typemixtral
Instruction-BasedYes
Model Files  9.9 GB: 1-of-17   10.0 GB: 2-of-17   10.0 GB: 3-of-17   10.0 GB: 4-of-17   10.0 GB: 5-of-17   10.0 GB: 6-of-17   10.0 GB: 7-of-17   10.0 GB: 8-of-17   10.0 GB: 9-of-17   10.0 GB: 10-of-17   10.0 GB: 11-of-17   10.0 GB: 12-of-17   10.0 GB: 13-of-17   10.0 GB: 14-of-17   10.0 GB: 15-of-17   10.0 GB: 16-of-17   3.4 GB: 17-of-17
Model ArchitectureMixtralForCausalLM
Context Length32768
Model Max Length32768
Transformers Version4.38.2
Tokenizer ClassLlamaTokenizer
Padding Token<s>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to Bigstral 12B 32K 8xMoE

Best Alternatives
Context / RAM
Downloads
Likes
Multilingual Mistral32K / 93.5 GB12332
Mini Mixtral V0.232K / 25.8 GB574
OpenMistral MoE32K / 48.3 GB12180
Magiq 332K / 37.1 GB73
FNCARL900032K / 48.3 GB90
CollAIborate4x7B32K / 48.7 GB51
CollAIborate4x7B32K / 48.7 GB11
OpenMistral MoE32K / 48.3 GB480
...t V0.2 2x7B MoE 6.0bpw H6 EXL232K / 9.9 GB91
Note: green Score (e.g. "73.2") means that the model is better than bartowski/bigstral-12b-32k-8xMoE.

Rank the Bigstral 12B 32K 8xMoE 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