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

Merge Model Test2 by kimdeokgi

 »  All LLMs  »  kimdeokgi  »  Merge Model Test2   URL Share it on

  8   
  Merged Model   Autotrain compatible   En   Endpoints compatible   Llama   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/kimdeokgi/merge_model_test2 

Merge Model Test2 Benchmarks

ARC: 79.35 vs 96.7 (so35)-17.9%
HellaSwag: 89.75 vs 95.3 (gpt4)-5.8%
MMLU: 67.89 vs 88.3 (so35)-23.1%
TruthfulQA: 71.58 vs 59 (gpt4)21.3%
WinoGrande: 86.58 vs 87.5 (gpt4)-1.1%
GSM8K: 55.57 vs 96.4 (so35)-42.4%
LLME Score: 0.19034
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Merge Model Test2 (kimdeokgi/merge_model_test2)

Merge Model Test2 Parameters and Internals

Additional Notes 
This model is a test version and alignment-tuned.
Supported Languages 
en (fluent)
Training Details 
Methodology:
Uses state-of-the-art instruction fine-tuning including direct preference optimization (DPO) and linear merging post-DPO to enhance performance.
LLM NameMerge Model Test2
Repository 🤗https://huggingface.co/kimdeokgi/merge_model_test2 
Merged ModelYes
Model Size21.4b
Required VRAM42.8 GB
Updated2025-02-20
Maintainerkimdeokgi
Model Typellama
Model Files  9.8 GB: 1-of-5   9.8 GB: 2-of-5   9.9 GB: 3-of-5   9.9 GB: 4-of-5   3.4 GB: 5-of-5
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.37.2
Is Biased0
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size92544
Torch Data Typebfloat16

Best Alternatives to Merge Model Test2

Best Alternatives
Context / RAM
Downloads
Likes
Luxia 21.4B Alignment V1.232K / 43 GB55539
Luxia 21.4B Alignment V1.032K / 42.8 GB968633
UNA ThePitbull 21.4B V232K / 43 GB4316
Final Model Test V232K / 43 GB100
DPO Model Test132K / 43 GB50
UNA ThePitbull 21.4 V132K / 43 GB195
Sft Model Test132K / 43 GB100
Merge Model Test132K / 42.8 GB60
Sft Model Test032K / 43 GB70
All DPO Model Test132K / 43 GB70
Note: green Score (e.g. "73.2") means that the model is better than kimdeokgi/merge_model_test2.

Rank the Merge Model Test2 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