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

StrangeMerges 46 7B Dare Ties by Gille

 »  All LLMs  »  Gille  »  StrangeMerges 46 7B Dare Ties   URL Share it on

  81   
  Merged Model   Autotrain compatible Base model:chihoonlee10/t3q-mi... Base model:kettleguts/zephyr-7... Chihoonlee10/t3q-mistral-orca-...   Endpoints compatible Kettleguts/zephyr-7b-beta spar...   Mistral   Model-index   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Gille/StrangeMerges_46-7B-dare_ties 

StrangeMerges 46 7B Dare Ties Benchmarks

ARC: 67.24 vs 96.7 (so35)-30.5%
HellaSwag: 86.4 vs 95.3 (gpt4)-9.3%
MMLU: 62.17 vs 88.3 (so35)-29.6%
TruthfulQA: 65.17 vs 59 (gpt4)10.5%
WinoGrande: 79.48 vs 87.5 (gpt4)-9.2%
GSM8K: 59.29 vs 96.4 (so35)-38.5%
LLME Score: 0.19625
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
StrangeMerges 46 7B Dare Ties (Gille/StrangeMerges_46-7B-dare_ties)

StrangeMerges 46 7B Dare Ties Parameters and Internals

Model Type 
text-generation
Training Details 
Methodology:
Merge using LazyMergekit
LLM NameStrangeMerges 46 7B Dare Ties
Repository 🤗https://huggingface.co/Gille/StrangeMerges_46-7B-dare_ties 
Base Model(s)  StrangeMerges 45 7B Dare Ties   Zephyr 7B Beta Sparse05   T3Q Mistral Orca Math DPO   Gille/StrangeMerges_45-7B-dare_ties   kettleguts/zephyr-7b-beta_sparse05   chihoonlee10/T3Q-Mistral-Orca-Math-DPO
Merged ModelYes
Model Size7b
Required VRAM14.5 GB
Updated2025-01-02
MaintainerGille
Model Typemistral
Model Files  9.8 GB: 1-of-2   4.7 GB: 2-of-2
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.38.2
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to StrangeMerges 46 7B Dare Ties

Best Alternatives
Context / RAM
Downloads
Likes
...Nemo Instruct 2407 Abliterated1000K / 24.5 GB26679
MegaBeam Mistral 7B 512K512K / 14.4 GB704947
SpydazWeb AI HumanAI RP512K / 14.4 GB281
SpydazWeb AI HumanAI 002512K / 14.4 GB141
...daz Web AI ChatML 512K Project512K / 14.5 GB120
MegaBeam Mistral 7B 300K282K / 14.4 GB324015
Hebrew Mistral 7B 200K256K / 30 GB287715
Astral 256K 7B V2250K / 14.4 GB160
Astral 256K 7B250K / 14.4 GB120
Boptruth Agatha 7B128K / 14.4 GB3690
Note: green Score (e.g. "73.2") means that the model is better than Gille/StrangeMerges_46-7B-dare_ties.

Rank the StrangeMerges 46 7B Dare Ties 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? 40769 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