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

GALAXY V03 Slimorca 1 Epoch 50K DPO 1 Epoch 30K by TeeZee

 »  All LLMs  »  TeeZee  »  GALAXY V03 Slimorca 1 Epoch 50K DPO 1 Epoch 30K   URL Share it on

  68   
  Autotrain compatible   Conversational Dataset:allenai/ultrafeedback ...   Dataset:open-orca/slimorca   En   Endpoints compatible   Llama   Model-index   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/TeeZee/GALAXY_v03_slimorca_1_epoch_50k_DPO_1_epoch_30k 

GALAXY V03 Slimorca 1 Epoch 50k DPO 1 Epoch 30k Benchmarks

ARC: 65.27 vs 96.7 (so35)-32.5%
HellaSwag: 85.62 vs 95.3 (gpt4)-10.2%
MMLU: 65.61 vs 88.3 (so35)-25.7%
TruthfulQA: 53.46 vs 59 (gpt4)-9.4%
WinoGrande: 82.72 vs 87.5 (gpt4)-5.5%
GSM8K: 0.08 vs 96.4 (so35)-99.9%
LLME Score: 0.21218
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
🌟 Advertise your project 🚀

GALAXY V03 Slimorca 1 Epoch 50K DPO 1 Epoch 30K Parameters and Internals

Model Type 
text-generation
Additional Notes 
Experiment, can DUS be taken one or more steps further?
Training Details 
Data Sources:
Open-Orca/SlimOrca, allenai/ultrafeedback_binarized_cleaned
Methodology:
model v03 finetuned on 50k entries from SlimOrca dataset and then DPO on 30k entries from ultrachat
Model Architecture:
12 layers removed from both models, 4 more than in original paper but its 1/4 of all layers(48) as per original paper
LLM NameGALAXY V03 Slimorca 1 Epoch 50k DPO 1 Epoch 30k
Repository 🤗https://huggingface.co/TeeZee/GALAXY_v03_slimorca_1_epoch_50k_DPO_1_epoch_30k 
Model Size16b
Required VRAM31.8 GB
Updated2024-12-02
MaintainerTeeZee
Model Typellama
Model Files  4.9 GB: 1-of-7   5.0 GB: 2-of-7   4.9 GB: 3-of-7   4.9 GB: 4-of-7   5.0 GB: 5-of-7   4.9 GB: 6-of-7   2.2 GB: 7-of-7
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Transformers Version4.39.1
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Torch Data Typebfloat16
GALAXY V03 Slimorca 1 Epoch 50K DPO 1 Epoch 30K (TeeZee/GALAXY_v03_slimorca_1_epoch_50k_DPO_1_epoch_30k)

Best Alternatives to GALAXY V03 Slimorca 1 Epoch 50K DPO 1 Epoch 30K

Best Alternatives
Context / RAM
Downloads
Likes
Phi 3.5 Mini Investigator 16B128K / 7.6 GB150
...o Sft Ties Post Merge Auto DPO8K / 141.2 GB60
Nanbeige2 16B Chat4K / 31.6 GB11990
...ALAXY V03 Slimorca 1 Epoch 50k4K / 31.8 GB900
Nanbeige 16B Base Llama4K / 31.6 GB12763
GALAXY XB V.034K / 31.9 GB720
FusionNet SOLAR4K / 31.9 GB13031
Llama 2 16B Nastychat4K / 32.4 GB13008
Vinallama 16B Chat Franken4K / 31.6 GB111
Nanbeige 16B Chat4K / 31.6 GB2412
Note: green Score (e.g. "73.2") means that the model is better than TeeZee/GALAXY_v03_slimorca_1_epoch_50k_DPO_1_epoch_30k.

Rank the GALAXY V03 Slimorca 1 Epoch 50K DPO 1 Epoch 30K 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? 38765 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 v20241124
  Support LLM Explorer