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

BagelMIsteryTour V2 8x7B by ycros

 »  All LLMs  »  ycros  »  BagelMIsteryTour V2 8x7B   URL Share it on

  76   

BagelMIsteryTour V2 8x7B is an open-source language model by ycros. Features: 46.7b LLM, VRAM: 93.5GB, Context: 32K, License: cc-by-nc-4.0, MoE, Instruction-Based, Merged, HF Score: 75, LLM Explorer Score: 0.19, Arc: 72.7, HellaSwag: 87.4, MMLU: 71.2, TruthfulQA: 74.5, WinoGrande: 82.6, GSM8K: 61.3.

  Merged Model   Arxiv:2306.01708   Arxiv:2311.03099 Base model:ds-archive/limarp-z... Base model:jondurbin/bagel-dpo... Base model:mistralai/mixtral-8... Base model:mistralai/mixtral-8... Base model:sao10k/sensualize-m...   Endpoints compatible   Instruct   Mixtral   Moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/ycros/BagelMIsteryTour-v2-8x7B 

BagelMIsteryTour V2 8x7B Benchmarks

MMLU Pro: 27.56
GPQA: 7.72
MUSR: 10.32
BBH: 31.37
IFEval: 62.62 vs 88 (so35)-28.8%
ARC: 72.7 vs 96.7 (so35)-24.8%
HellaSwag: 87.36 vs 95.3 (gpt4)-8.3%
MMLU: 71.16 vs 88.3 (so35)-19.4%
TruthfulQA: 74.54 vs 59 (gpt4)26.3%
WinoGrande: 82.64 vs 87.5 (gpt4)-5.6%
GSM8K: 61.33 vs 96.4 (so35)-36.4%
MATH Lvl 5: 9.37
LLME Score: 0.19182
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
BagelMIsteryTour V2 8x7B (ycros/BagelMIsteryTour-v2-8x7B)
🌟 Advertise your project 🚀

BagelMIsteryTour V2 8x7B Parameters and Internals

Additional Notes 
The model is a merge of several existing models, including jondurbin/bagel-dpo-8x7b-v0.2, Sao10K/Sensualize-Mixtral-bf16, mistralai/Mixtral-8x7B-v0.1, Doctor-Shotgun/limarp-zloss-mixtral-8x7b-qlora, and mistralai/Mixtral-8x7B-Instruct-v0.1 using the DARE TIES merge method.
LLM NameBagelMIsteryTour V2 8x7B
Repository 🤗https://huggingface.co/ycros/BagelMIsteryTour-v2-8x7B 
Base Model(s)  mistralai/Mixtral-8x7B-v0.1   jondurbin/bagel-dpo-8x7b-v0.2   Sensualize Mixtral Bf16   mistralai/Mixtral-8x7B-v0.1   ...imarp Zloss Mixtral 8x7b Qlora   mistralai/Mixtral-8x7B-Instruct-v0.1   mistralai/Mixtral-8x7B-v0.1   jondurbin/bagel-dpo-8x7b-v0.2   Sao10K/Sensualize-Mixtral-bf16   mistralai/Mixtral-8x7B-v0.1   Doctor-Shotgun/limarp-zloss-mixtral-8x7b-qlora   mistralai/Mixtral-8x7B-Instruct-v0.1
Merged ModelYes
Model Size46.7b
Required VRAM93.5 GB
Updated2026-04-16
Maintainerycros
Model Typemixtral
Instruction-BasedYes
Model Files  9.9 GB: 1-of-10   10.0 GB: 2-of-10   10.0 GB: 3-of-10   10.0 GB: 4-of-10   10.0 GB: 5-of-10   10.0 GB: 6-of-10   10.0 GB: 7-of-10   10.0 GB: 8-of-10   9.9 GB: 9-of-10   3.7 GB: 10-of-10
Model ArchitectureMixtralForCausalLM
Licensecc-by-nc-4.0
Context Length32768
Model Max Length32768
Transformers Version4.36.2
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to BagelMIsteryTour V2 8x7B

Best Alternatives
Context / RAM
Downloads
Likes
Mixtral 8x7B Instruct V0.132K / 93.6 GB6362164670
Mixtral 8x7B Instruct V0.1 FP832K / 47.1 GB48450
...xtral 8x7B Yes Instruct LimaRP32K / 93.5 GB131
Merge Mixtral Prometheus 8x7B32K / 91.9 GB742
...rkrautLM Mixtral 8x7B Instruct32K / 93.6 GB53922
Notux 8x7b V132K / 93.6 GB86164
Mixtral 8x7B Instruct V0.1 FP832K / 47.1 GB3740
Sage Ft Mixtral 8x7b32K / 90 GB9124
Dolphin 2.5 Mixtral 8x7b32K / 93.6 GB41251235
GritLM 8x7B32K / 93.6 GB798538
Note: green Score (e.g. "73.2") means that the model is better than ycros/BagelMIsteryTour-v2-8x7B.

Rank the BagelMIsteryTour V2 8x7B 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? 53232 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.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer