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

Mistralmath 15B Pass by allknowingroger

 »  All LLMs  »  allknowingroger  »  Mistralmath 15B Pass   URL Share it on

  11   
  Merged Model   Ameerh/mistral-math-2x7b-mix   Autotrain compatible Base model:ameerh/mistral-math... Base model:finetune:ameerh/mis...   Conversational   Endpoints compatible   Mixtral   Moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/allknowingroger/Mistralmath-15B-pass 

Mistralmath 15B Pass Benchmarks

ARC: 60.07 vs 96.7 (so35)-37.9%
HellaSwag: 83.12 vs 95.3 (gpt4)-12.8%
MMLU: 59.52 vs 88.3 (so35)-32.6%
TruthfulQA: 60.46 vs 59 (gpt4)2.5%
WinoGrande: 76.64 vs 87.5 (gpt4)-12.4%
GSM8K: 43.14 vs 96.4 (so35)-55.2%
LLME Score: 0.20507
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Mistralmath 15B Pass (allknowingroger/Mistralmath-15B-pass)

Mistralmath 15B Pass Parameters and Internals

Training Details 
Methodology:
passthrough merge using LazyMergekit
LLM NameMistralmath 15B Pass
Repository 🤗https://huggingface.co/allknowingroger/Mistralmath-15B-pass 
Base Model(s)  Mistral Math 2x7b Mix   Mistral Math 2x7b Mix   Mistral Math 2x7b Mix   Mistral Math 2x7b Mix   Mistral Math 2x7b Mix   AmeerH/Mistral-Math-2x7b-mix   AmeerH/Mistral-Math-2x7b-mix   AmeerH/Mistral-Math-2x7b-mix   AmeerH/Mistral-Math-2x7b-mix   AmeerH/Mistral-Math-2x7b-mix
Merged ModelYes
Model Size19.2b
Required VRAM38.5 GB
Updated2024-12-03
Maintainerallknowingroger
Model Typemixtral
Model Files  1.9 GB: 1-of-20   1.9 GB: 2-of-20   2.0 GB: 3-of-20   2.0 GB: 4-of-20   2.0 GB: 5-of-20   2.0 GB: 6-of-20   2.0 GB: 7-of-20   2.0 GB: 8-of-20   2.0 GB: 9-of-20   2.0 GB: 10-of-20   2.0 GB: 11-of-20   2.0 GB: 12-of-20   2.0 GB: 13-of-20   2.0 GB: 14-of-20   2.0 GB: 15-of-20   2.0 GB: 16-of-20   2.0 GB: 17-of-20   2.0 GB: 18-of-20   2.0 GB: 19-of-20   0.7 GB: 20-of-20
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 Mistralmath 15B Pass

Best Alternatives
Context / RAM
Downloads
Likes
MixTAO 19B Pass32K / 38.1 GB161
Multimerge 19B Pass32K / 38 GB100
Lorge 2x7B UAMM32K / 38.2 GB160
TaoPassthrough 15B S32K / 38.4 GB200
Raccoon Small32K / 38.4 GB861
...oundary Solar Chat 2x10.7B MoE4K / 38 GB1231
Mixtral 11Bx2 MoE 19B4K / 38.4 GB127538
Truthful DPO MoE 19B4K / 38.4 GB12071
Venus DPO 504K / 38.4 GB12100
SOLAR Math 2x10.7B V0.24K / 38.4 GB12153
Note: green Score (e.g. "73.2") means that the model is better than allknowingroger/Mistralmath-15B-pass.

Rank the Mistralmath 15B Pass 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