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

SJT 3.7B by Sakalti

 »  All LLMs  »  Sakalti  »  SJT 3.7B   URL Share it on

  7   
  Merged Model   Arxiv:2306.01708   Autotrain compatible Base model:finetune:llm-jp/llm... Base model:llm-jp/llm-jp-3-3.7...   Conversational   Endpoints compatible   Instruct   Llama   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Sakalti/SJT-3.7B 

SJT 3.7B Benchmarks

MMLU Pro: 5.61
GPQA: 0.78
MUSR: 4.35
BBH: 7.81
IFEval: 10.78 vs 88 (so35)-87.8%
MATH Lvl 5: 1.21
LLME Score: 0.25344
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
SJT 3.7B (Sakalti/SJT-3.7B)

SJT 3.7B Parameters and Internals

LLM NameSJT 3.7B
Repository 🤗https://huggingface.co/Sakalti/SJT-3.7B 
Base Model(s)  llm-jp/llm-jp-3-3.7b-instruct   llm-jp/llm-jp-3-3.7b-Instruct   llm-jp/llm-jp-3-3.7b-instruct   llm-jp/llm-jp-3-3.7b-Instruct
Merged ModelYes
Model Size3.7b
Required VRAM8.2 GB
Updated2025-03-12
MaintainerSakalti
Model Typellama
Instruction-BasedYes
Model Files  0.6 GB: 1-of-16   0.6 GB: 2-of-16   0.5 GB: 3-of-16   0.5 GB: 4-of-16   0.5 GB: 5-of-16   0.5 GB: 6-of-16   0.5 GB: 7-of-16   0.5 GB: 8-of-16   0.5 GB: 9-of-16   0.5 GB: 10-of-16   0.5 GB: 11-of-16   0.5 GB: 12-of-16   0.5 GB: 13-of-16   0.5 GB: 14-of-16   0.5 GB: 15-of-16   0.5 GB: 16-of-16
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Transformers Version4.46.3
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<PAD|LLM-jp>
Vocabulary Size99584
Torch Data Typefloat16

Best Alternatives to SJT 3.7B

Best Alternatives
Context / RAM
Downloads
Likes
Llm Jp 3 3.7B Instruct4K / 7.6 GB179911
....0 Computer Crime Act Instruct4K / 13.7 GB90
...3 3.7B Instruct EZO Humanities4K / 7.6 GB1765
Llm Jp 3 3.7B Instruct4K / 7.6 GB210

Rank the SJT 3.7B 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? 44887 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