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

Mistral Math 2x7b Mix by AmeerH

 »  All LLMs  »  AmeerH  »  Mistral Math 2x7b Mix   URL Share it on

  80   
  Autotrain compatible Base model:merge:meta-math/met... Base model:merge:mistralai/mis... Base model:meta-math/metamath-... Base model:mistralai/mistral-7...   Conversational   Endpoints compatible   Frankenmoe   Instruct   Lazymergekit   Merge   Mergekit   Meta-math/metamath-mistral-7b Mistralai/mistral-7b-instruct-...   Mixtral   Moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/AmeerH/Mistral-Math-2x7b-mix 

Mistral Math 2x7b Mix Benchmarks

LLME Score: 0.18777
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Mistral Math 2x7b Mix (AmeerH/Mistral-Math-2x7b-mix)

Mistral Math 2x7b Mix Parameters and Internals

Model Type 
moe, frankenmoe, merge, mergekit, lazymergekit
Additional Notes 
Mistral-Math-2x7b-mix is a Mixture of Experts (MoE) model made by combining mistralai/Mistral-7B-Instruct-v0.2 and meta-math/MetaMath-Mistral-7B models using LazyMergekit.
LLM NameMistral Math 2x7b Mix
Repository 🤗https://huggingface.co/AmeerH/Mistral-Math-2x7b-mix 
Base Model(s)  mistralai/Mistral-7B-Instruct-v0.2   MetaMath Mistral 7B   mistralai/Mistral-7B-Instruct-v0.2   meta-math/MetaMath-Mistral-7B
Model Size12.9b
Required VRAM25.8 GB
Updated2024-12-14
MaintainerAmeerH
Model Typemixtral
Instruction-BasedYes
Model Files  1.9 GB: 1-of-13   2.0 GB: 2-of-13   2.0 GB: 3-of-13   2.0 GB: 4-of-13   2.0 GB: 5-of-13   2.0 GB: 6-of-13   2.0 GB: 7-of-13   2.0 GB: 8-of-13   2.0 GB: 9-of-13   2.0 GB: 10-of-13   2.0 GB: 11-of-13   2.0 GB: 12-of-13   1.9 GB: 13-of-13
Model ArchitectureMixtralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.38.2
Tokenizer ClassLlamaTokenizer
Padding Token<s>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Mistral Math 2x7b Mix

Best Alternatives
Context / RAM
Downloads
Likes
MergedExpert 2x8b32K / 25.8 GB50
MergedExperts 2x8b32K / 25.8 GB60
NearalMistral 2x7B32K / 25.8 GB871
Megatron V3 2x7B32K / 25.8 GB763
MistarlingMaid 2x7B Base32K / 25.8 GB790
Orthogonal 2x7B Base32K / 25.8 GB12080
...afted Hermetic Platypus C 2x7B32K / 25.8 GB810
...tral 7B Instruct V0.2 2x7B MoE32K / 25.8 GB11314
Mistral 2x7b V0.132K / 25.8 GB131
...tral Instruct MoE Experimental32K / 25.8 GB802
Note: green Score (e.g. "73.2") means that the model is better than AmeerH/Mistral-Math-2x7b-mix.

Rank the Mistral Math 2x7b Mix 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? 39237 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