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 Enigma by ValiantLabs

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

  29   
  3b Base model:finetune:meta-llama... Base model:meta-llama/llama-3....   Chat   Code   Code-instruct   Conversational   Dataset:sequelbox/supernova   Dataset:sequelbox/tachibana   En   Enigma   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   Python   Region:us   Safetensors   Sharded   Tensorflow   Valiant   Valiant-labs
Model Card on HF 🤗: https://huggingface.co/ValiantLabs/Llama3.2-3B-Enigma 

Llama3.2 3B Enigma Benchmarks

MMLU Pro: 15.86
GPQA: 1.57
MUSR: 8.05
BBH: 12.43
IFEval: 27.86 vs 88 (so35)-68.3%
MATH Lvl 5: 4.38
LLME Score: 0.23694
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 Enigma (ValiantLabs/Llama3.2-3B-Enigma)

Llama3.2 3B Enigma Parameters and Internals

Model Type 
text-generation, code-instruct, conversational
Additional Notes 
Enigma is created by Valiant Labs and built on top of Llama 3.2 3b Instruct, using high quality code-instruct data and general chat data in Llama 3.2 Instruct prompt style to supplement overall performance. Our current version of Enigma is trained on code-instruct data from sequelbox/Tachibana and general chat data from sequelbox/Supernova.
Training Details 
Data Sources:
sequelbox/Tachibana, sequelbox/Supernova
Methodology:
Finetuned on synthetic code-instruct data generated with Llama 3.1 405b and generalist synthetic data.
Release Notes 
Version:
2024-09-30
Notes:
Enhancing code-instruct and general chat capabilities.
LLM NameLlama3.2 3B Enigma
Repository 🤗https://huggingface.co/ValiantLabs/Llama3.2-3B-Enigma 
Base Model(s)  meta-llama/Llama-3.2-3B-Instruct   meta-llama/Llama-3.2-3B-Instruct
Model Size3b
Required VRAM12.8 GB
Updated2025-05-14
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 Version4.45.1
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|eot_id|>
Vocabulary Size128256
Torch Data Typefloat32

Best Alternatives to Llama3.2 3B Enigma

Best Alternatives
Context / RAM
Downloads
Likes
Llama 3.2 3B Instruct128K / 6.5 GB19156581441
DeepSeek R1 Distill Llama 3B128K / 6.5 GB32011
Llama 3.2 3B RP Toxic Fuse128K / 6.4 GB132
Orpheus 3B 0.1 Pretrained128K / 6.6 GB68330
Zeitgeist 3B V1128K / 6.5 GB1055
ReasoningCore 3B T1 1128K / 6.5 GB611
Llama 3.2 3B Instruct128K / 6.5 GB12098362
... 3.2 3B Math Instruct RE1 ORPO128K / 6.5 GB480
Llama 3.2 3B ToxicKod128K / 6.4 GB82
FuseChat Llama 3.2 3B Instruct128K / 6.5 GB987
Note: green Score (e.g. "73.2") means that the model is better than ValiantLabs/Llama3.2-3B-Enigma.

Rank the Llama3.2 3B Enigma 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? 47368 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