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

DARE TIES 13B by yunconglong

 »  All LLMs  »  yunconglong  »  DARE TIES 13B   URL Share it on

  6038   
  Merged Model   Arxiv:2306.01708   Arxiv:2311.03099   Autotrain compatible   Dare ties   Endpoints compatible   Mixtral   Moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/yunconglong/DARE_TIES_13B 

DARE TIES 13B Benchmarks

ARC: 74.32 vs 96.7 (so35)-23.1%
HellaSwag: 89.5 vs 95.3 (gpt4)-6.1%
MMLU: 64.47 vs 88.3 (so35)-27%
TruthfulQA: 78.66 vs 59 (gpt4)33.3%
WinoGrande: 88.08 vs 87.5 (gpt4)0.7%
GSM8K: 67.55 vs 96.4 (so35)-29.9%
LLME Score: 0.20388
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
DARE TIES 13B (yunconglong/DARE_TIES_13B)

DARE TIES 13B Parameters and Internals

Additional Notes 
This model is a merge of pre-trained language models using the DARE TIES method and various density and weight parameters. It utilizes mergekit for merging models based on the Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B as a base.
LLM NameDARE TIES 13B
Repository 🤗https://huggingface.co/yunconglong/DARE_TIES_13B 
Merged ModelYes
Model Size12.9b
Required VRAM25.7 GB
Updated2025-02-22
Maintaineryunconglong
Model Typemixtral
Model Files  9.9 GB: 1-of-3   10.0 GB: 2-of-3   5.8 GB: 3-of-3
Model ArchitectureMixtralForCausalLM
Licenseother
Context Length32768
Model Max Length32768
Transformers Version4.37.2
Tokenizer ClassLlamaTokenizer
Padding Token<s>
Vocabulary Size32000
Torch Data Typebfloat16

Quantized Models of the DARE TIES 13B

Model
Likes
Downloads
VRAM
DARE TIES 13B GGUF4864 GB

Best Alternatives to DARE TIES 13B

Best Alternatives
Context / RAM
Downloads
Likes
MixTAO 7Bx2 MoE V8.132K / 25.8 GB957855
Inf Silent Kunoichi V0.1 2x7B32K / 25.6 GB50
Inf Silent Kunoichi V0.2 2x7B32K / 25.6 GB80
MixTAO 7Bx2 MoE V8.132K / 25.8 GB876052
MultiMash8 13B Slerp32K / 25.7 GB60
MultiMash11 13B Slerp32K / 25.7 GB60
MultiMash9 13B Slerp32K / 25.7 GB80
MultiMash10 13B Slerp32K / 25.7 GB120
Mixtral 7Bx2 MoE32K / 25.8 GB183236
MixTaoTruthful 13B Slerp32K / 25.7 GB80
Note: green Score (e.g. "73.2") means that the model is better than yunconglong/DARE_TIES_13B.

Rank the DARE TIES 13B 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? 43470 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