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

Tara 3.8B by Sakalti

 »  All LLMs  »  Sakalti  »  Tara 3.8B   URL Share it on

  93   
  Autotrain compatible Base model:finetune:unsloth/ph... Base model:unsloth/phi-3.5-min...   Conversational   Dataset:lazycuber/alpaca-jp   En   Endpoints compatible   Instruct   Ja   Llama   Region:us   Safetensors   Sft   Sharded   Tensorflow   Trl   Unsloth
Model Card on HF 🤗: https://huggingface.co/Sakalti/tara-3.8B 

Tara 3.8B Benchmarks

MMLU Pro: 25.35
GPQA: 5.93
MUSR: 19.44
BBH: 28.91
IFEval: 40.77 vs 88 (so35)-53.7%
MATH Lvl 5: 10.95
LLME Score: 0.32764
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Tara 3.8B (Sakalti/tara-3.8B)

Tara 3.8B Parameters and Internals

LLM NameTara 3.8B
Repository 🤗https://huggingface.co/Sakalti/tara-3.8B 
Base Model(s)  unsloth/Phi-3.5-mini-instruct   unsloth/Phi-3.5-mini-instruct
Model Size3.8b
Required VRAM7.6 GB
Updated2025-02-05
MaintainerSakalti
Model Typellama
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   2.6 GB: 2-of-2
Supported Languagesen ja
Model ArchitectureLlamaForCausalLM
Licensemit
Context Length150000
Model Max Length150000
Transformers Version4.47.1
Tokenizer ClassLlamaTokenizer
Padding Token<|placeholder6|>
Vocabulary Size32064
Torch Data Typefloat16

Best Alternatives to Tara 3.8B

Best Alternatives
Context / RAM
Downloads
Likes
Phi 3.5 Mini Instruct128K / 7.6 GB1665842
Phi 3 5 Mini Kp 12k Cfr Sft128K / 7.6 GB1310
Phi 3 5 Mini Tictactoe1200128K / 7.6 GB810
...3 Mini 128K Instruct LLaMAfied128K / 7.6 GB803
Llamaphi 3 128K Instruct128K / 7.6 GB821
...i 3 Mini 4K Instruct LLaMAfied4K / 7.6 GB24611
Phillama 3.8B V0.14K / 7.6 GB8310
Phillama 3.8B V14K / 7.6 GB795
Model128K / 7.6 GB410
Phi 3 5 Mini 3k Each128K / 7.6 GB60

Rank the Tara 3.8B 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? 42577 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