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

Llama3.2 3B ShiningValiant2 by ValiantLabs

 »  All LLMs  »  ValiantLabs  »  Llama3.2 3B ShiningValiant2   URL Share it on

  2818   
  3b Base model:finetune:meta-llama... Base model:meta-llama/llama-3....   Biology   Chat   Chemistry   Compsci   Computer-science   Conversational   Dataset:sequelbox/celestia   Dataset:sequelbox/spurline   Dataset:sequelbox/supernova   En   Engineering   Instruct   Llama   Llama-3   Llama-3-instruct   Llama-3-instruct-3b   Llama-3.2   Llama-3.2-instruct   Llama-3.2-instruct-3b   Model-index   Physics   Region:us   Safetensors   Science   Sharded   Shining-valiant   Shining-valiant-2   Technical   Tensorflow   Valiant   Valiant-labs
Model Card on HF 🤗: https://huggingface.co/ValiantLabs/Llama3.2-3B-ShiningValiant2 

Llama3.2 3B ShiningValiant2 Benchmarks

MMLU Pro: 20.32
GPQA: 4.03
MUSR: 8.6
BBH: 18.91
IFEval: 26.25 vs 88 (so35)-70.2%
MATH Lvl 5: 8.23
LLME Score: 0.27778
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama3.2 3B ShiningValiant2 (ValiantLabs/Llama3.2-3B-ShiningValiant2)

Llama3.2 3B ShiningValiant2 Parameters and Internals

Model Type 
text generation
Additional Notes 
Shining Valiant 2 is a chat model built for friendship, insight, knowledge, and enthusiasm.
Training Details 
Data Sources:
sequelbox/Celestia, sequelbox/Supernova
Input Output 
Input Format:
Llama 3.2 Instruct prompt format
Release Notes 
Version:
2024-09-27
Date:
2024-09-27
Notes:
Release of Shining Valiant 2 for Llama 3.2 3b with improvements in physics, chemistry, biology, and computer science.
LLM NameLlama3.2 3B ShiningValiant2
Repository 🤗https://huggingface.co/ValiantLabs/Llama3.2-3B-ShiningValiant2 
Base Model(s)  meta-llama/Llama-3.2-3B-Instruct   meta-llama/Llama-3.2-3B-Instruct
Model Size3b
Required VRAM12.8 GB
Updated2025-05-21
MaintainerValiantLabs
Model Typellama
Instruction-BasedYes
Model Files  5.0 GB: 1-of-3   4.9 GB: 2-of-3   2.9 GB: 3-of-3
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licensellama3.2
Context Length131072
Model Max Length131072
Transformers Version4.46.1
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|eot_id|>
Vocabulary Size128256
Torch Data Typefloat32

Best Alternatives to Llama3.2 3B ShiningValiant2

Best Alternatives
Context / RAM
Downloads
Likes
Llama 3.2 3B Instruct128K / 6.5 GB16537241462
DeepSeek R1 Distill Llama 3B128K / 6.5 GB28011
Llama 3.2 3B RP Toxic Fuse128K / 6.4 GB122
Orpheus 3B 0.1 Pretrained128K / 6.6 GB72130
Zeitgeist 3B V1128K / 6.5 GB1055
Llama 3.2 3B Instruct128K / 6.5 GB11880564
ReasoningCore 3B T1 1128K / 6.5 GB591
... 3.2 3B Math Instruct RE1 ORPO128K / 6.5 GB480
Llama 3.2 3B ToxicKod128K / 6.4 GB92
FuseChat Llama 3.2 3B Instruct128K / 6.5 GB907
Note: green Score (e.g. "73.2") means that the model is better than ValiantLabs/Llama3.2-3B-ShiningValiant2.

Rank the Llama3.2 3B ShiningValiant2 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? 47473 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