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

Thea V2 3B 50r by lunahr

 »  All LLMs  »  lunahr  »  Thea V2 3B 50r   URL Share it on

  13   
  Autotrain compatible Base model:finetune:lunahr/her... Base model:lunahr/hermes-3-lla...   Conversational Dataset:kingnish/reasoning-bas... Dataset:lunahr/thea-name-overr...   En   Endpoints compatible   Llama   Llama-3   Reasoning   Region:us   Safetensors   Sft   Sharded   Tensorflow   Trl
Model Card on HF 🤗: https://huggingface.co/lunahr/thea-v2-3b-50r 

Thea V2 3B 50r Benchmarks

MMLU Pro: 15.66
GPQA: 1.45
MUSR: 2.44
BBH: 18.71
IFEval: 37.04 vs 88 (so35)-57.9%
MATH Lvl 5: 2.11
LLME Score: 0.28055
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Thea V2 3B 50r (lunahr/thea-v2-3b-50r)

Thea V2 3B 50r Parameters and Internals

LLM NameThea V2 3B 50r
Repository 🤗https://huggingface.co/lunahr/thea-v2-3b-50r 
Base Model(s)  lunahr/Hermes-3-Llama-3.2-3B-abliterated   lunahr/Hermes-3-Llama-3.2-3B-abliterated
Model Size3b
Required VRAM6.5 GB
Updated2025-01-21
Maintainerlunahr
Model Typellama
Model Files  5.0 GB: 1-of-2   1.5 GB: 2-of-2
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licensellama3.2
Context Length131072
Model Max Length131072
Transformers Version4.46.3
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|im_end|>
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to Thea V2 3B 50r

Best Alternatives
Context / RAM
Downloads
Likes
Llama 3.2 3B Instruct128K / 6.5 GB1405328905
Llama 3.2 3B128K / 6.5 GB425944464
Hermes 3 Llama 3.2 3B128K / 6.5 GB18327127
Omni Reasoner3 Merged128K / 6.4 GB477
Orca Mini V9 5 3B Instruct128K / 6.5 GB3996
Dolphin3.0 Llama3.2 3B128K / 6.5 GB499725
Llama Deepsync 3B128K / 6.5 GB42915
Calme 3.1 Llamaloi 3B128K / 10.6 GB27941
Llama 3.2 3B RP DeepThink128K / 7.2 GB3712
Llama 3.2 3B Instruct128K / 6.5 GB5369302
Note: green Score (e.g. "73.2") means that the model is better than lunahr/thea-v2-3b-50r.

Rank the Thea V2 3B 50r 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? 41727 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