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

Eclipse 13B DPO by Xenon1

 »  All LLMs  »  Xenon1  »  Eclipse 13B DPO   URL Share it on

  32   
  Arxiv:2401.10020   Autotrain compatible   Eclipse-13b-dpo   En   Endpoints compatible   Mistral   Mixtral   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Xenon1/Eclipse-13B-dpo 

Eclipse 13B DPO Benchmarks

ARC: 64.59 vs 96.7 (so35)-33.2%
HellaSwag: 85 vs 95.3 (gpt4)-10.8%
MMLU: 64.85 vs 88.3 (so35)-26.6%
TruthfulQA: 54.76 vs 59 (gpt4)-7.2%
WinoGrande: 84.61 vs 87.5 (gpt4)-3.3%
GSM8K: 69.37 vs 96.4 (so35)-28%
LLME Score: 0.17568
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Eclipse 13B DPO (Xenon1/Eclipse-13B-dpo)

Eclipse 13B DPO Parameters and Internals

Model Type 
text-generation
Supported Languages 
en (English)
Training Details 
Data Sources:
Ultrafeedback dataset
Methodology:
Instruction fine-tuning
Model Architecture:
Transformer with Grouped-Query Attention, Sliding-Window Attention, Byte-fallback BPE tokenizer
Input Output 
Input Format:
Surrounded by `[INST]` and `[/INST]` tokens
Accepted Modalities:
text
Output Format:
Text generation
LLM NameEclipse 13B DPO
Repository 🤗https://huggingface.co/Xenon1/Eclipse-13B-dpo 
Model Size13b
Required VRAM25.8 GB
Updated2025-02-22
MaintainerXenon1
Model Typemixtral
Model Files  5.0 GB: 1-of-6   4.9 GB: 2-of-6   5.0 GB: 3-of-6   5.0 GB: 4-of-6   4.9 GB: 5-of-6   1.0 GB: 6-of-6
Supported Languagesen
Model ArchitectureMixtralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.37.1
Tokenizer ClassLlamaTokenizer
Padding Token<s>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Eclipse 13B DPO

Best Alternatives
Context / RAM
Downloads
Likes
LuminRP 13B 128K128K / 25.8 GB132
Yunconglong 13B Slerp32K / 25.7 GB130
T3Q MSlerp 13B32K / 51.8 GB200
13B MATH DPO32K / 25.8 GB341
...et 7Bx2 MoE 13B 6.0bpw H6 EXL232K / 9.8 GB103
...et 7Bx2 MoE 13B 4.0bpw H6 EXL232K / 6.7 GB71
...et 7Bx2 MoE 13B 3.0bpw H6 EXL232K / 5.1 GB80
WordWoven 13B AWQ32K / 7.1 GB642
WordWoven 13B GPTQ32K / 7.1 GB93
Note: green Score (e.g. "73.2") means that the model is better than Xenon1/Eclipse-13B-dpo.

Rank the Eclipse 13B DPO 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