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

POLAR 14B DPO V1.3 by x2bee

 »  All LLMs  »  x2bee  »  POLAR 14B DPO V1.3   URL Share it on

  2941   
  Arxiv:1910.09700   Autotrain compatible Dataset:we-want-gpu/yi-ko-dpo-...   Endpoints compatible   Ko   Llama   Region:us   Safetensors   Sharded   Tensorflow

POLAR 14B DPO V1.3 Benchmarks

ARC: 38.99 vs 96.7 (so35)-59.7%
HellaSwag: 68.63 vs 95.3 (gpt4)-28%
MMLU: 23.12 vs 88.3 (so35)-73.8%
TruthfulQA: 60.56 vs 59 (gpt4)2.6%
WinoGrande: 53.04 vs 87.5 (gpt4)-39.4%
LLME Score: 0.30715
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

POLAR 14B DPO V1.3 Parameters and Internals

LLM NamePOLAR 14B DPO V1.3
Repository 🤗https://huggingface.co/x2bee/POLAR-14B-DPO-v1.3 
Model Size14b
Required VRAM28.4 GB
Updated2024-09-07
Maintainerx2bee
Model Typellama
Model Files  4.9 GB: 1-of-6   5.0 GB: 2-of-6   4.9 GB: 3-of-6   4.9 GB: 4-of-6   5.0 GB: 5-of-6   3.7 GB: 6-of-6
Supported Languagesko
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Transformers Version4.37.2
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32000
Torch Data Typefloat16
POLAR 14B DPO V1.3 (x2bee/POLAR-14B-DPO-v1.3)

Best Alternatives to POLAR 14B DPO V1.3

Best Alternatives
Context / RAM
Downloads
Likes
GeM2 Llamion 14B LongChat195K / 29 GB26673
Openbuddy Zero 14B V22.3 32K32K / 28 GB6161
14B8K / 28.4 GB1487299
Qwen 14B Llamafied8K / 28.4 GB16935
Dolus 14B Mini8K / 23 GB265
Qwen 14B Chat LLaMAfied8K / 28.4 GB7268
JerseyDevil 14B8K / 28.5 GB52
CausalLM Platypus 14B8K / 28.4 GB6981
SkunkApe 14B8K / 28.5 GB83
Qwen 14B Llamafied8K / 28.4 GB111
Note: green Score (e.g. "73.2") means that the model is better than x2bee/POLAR-14B-DPO-v1.3.

Rank the POLAR 14B DPO V1.3 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? 35693 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 v2024072803
  Support LLM Explorer