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 Esper2 by ValiantLabs

 »  All LLMs  »  ValiantLabs  »  Llama3.2 3B Esper2   URL Share it on

  34   
  3b   Architect   Aws   Azure Base model:finetune:meta-llama... Base model:meta-llama/llama-3....   Chat   Code   Code-instruct   Conversational   Dataset:sequelbox/supernova   Dataset:sequelbox/tachibana   Dataset:sequelbox/titanium   Dev-ops   Developer   En   Engineer   Esper   Esper-2   Gcp   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   Terraform   Valiant   Valiant-labs
Model Card on HF 🤗: https://huggingface.co/ValiantLabs/Llama3.2-3B-Esper2 

Llama3.2 3B Esper2 Benchmarks

MMLU Pro: 13.97
GPQA: 2.68
MUSR: 4.04
BBH: 13.85
IFEval: 27.5 vs 88 (so35)-68.8%
MATH Lvl 5: 2.34
LLME Score: 0.26704
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 Esper2 (ValiantLabs/Llama3.2-3B-Esper2)

Llama3.2 3B Esper2 Parameters and Internals

Model Type 
text-generation
Additional Notes 
Esper 2 improves performance through high quality DevOps, code, and chat data.
Training Details 
Data Sources:
sequelbox/Titanium, sequelbox/Tachibana, sequelbox/Supernova
Methodology:
Finetuned on synthetic DevOps-instruct and code-instruct data generated with Llama 3.1 405b
Input Output 
Input Format:
Llama 3.2 Instruct prompt format
Performance Tips:
Use the example script provided for general chat.
Release Notes 
Version:
2024-10-03
Notes:
Release of Esper 2 for Llama 3.2 3b.
LLM NameLlama3.2 3B Esper2
Repository 🤗https://huggingface.co/ValiantLabs/Llama3.2-3B-Esper2 
Base Model(s)  meta-llama/Llama-3.2-3B-Instruct   meta-llama/Llama-3.2-3B-Instruct
Model Size3b
Required VRAM12.8 GB
Updated2024-12-21
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 Version4.45.1
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|eot_id|>
Vocabulary Size128256
Torch Data Typefloat32

Best Alternatives to Llama3.2 3B Esper2

Best Alternatives
Context / RAM
Downloads
Likes
Llama 3.2 3B Instruct128K / 6.5 GB2165514808
Llama 3.2 3B Instruct128K / 6.4 GB6393735
Llama Song Stream 3B Instruct128K / 6.5 GB299
Llama Chat Summary 3.2 3B128K / 6.5 GB577
...lama 3.2 Rabbit Ko 3B Instruct128K / 6.5 GB15538
Llama 3.2 3B Instruct128K / 6.5 GB554272
SummLlama3.2 3B128K / 6.5 GB482135
FinMatcha 3B Instruct128K / 6.5 GB3590
...3.2 Rabbit Ko 3B Instruct 2412128K / 6.5 GB270
... Instruct JankMixBread V0.1 3B128K / 6.4 GB3430
Note: green Score (e.g. "73.2") means that the model is better than ValiantLabs/Llama3.2-3B-Esper2.

Rank the Llama3.2 3B Esper2 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? 40013 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 v20241217
  Support LLM Explorer