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

SJT 8B by Sakalti

 »  All LLMs  »  Sakalti  »  SJT 8B   URL Share it on

  36   
  Merged Model   Autotrain compatible Base model:finetune:sakalti/mo...   Base model:sakalti/model-3   Conversational   Endpoints compatible   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Sakalti/SJT-8B 

SJT 8B Benchmarks

MMLU Pro: 36.29
GPQA: 10.63
MUSR: 8.46
BBH: 33.33
IFEval: 65.35 vs 88 (so35)-25.7%
MATH Lvl 5: 25.38
LLME Score: 0.34582
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
SJT 8B (Sakalti/SJT-8B)

SJT 8B Parameters and Internals

LLM NameSJT 8B
Repository 🤗https://huggingface.co/Sakalti/SJT-8B 
Base Model(s)  Model 3   Sakalti/model-3
Merged ModelYes
Model Size8b
Required VRAM17.8 GB
Updated2025-02-22
MaintainerSakalti
Model Typeqwen2
Model Files  1.1 GB: 1-of-34   1.1 GB: 2-of-34   0.5 GB: 3-of-34   0.5 GB: 4-of-34   0.4 GB: 5-of-34   0.5 GB: 6-of-34   0.4 GB: 7-of-34   0.5 GB: 8-of-34   0.4 GB: 9-of-34   0.5 GB: 10-of-34   0.4 GB: 11-of-34   0.5 GB: 12-of-34   0.5 GB: 13-of-34   0.5 GB: 14-of-34   0.5 GB: 15-of-34   0.5 GB: 16-of-34   0.5 GB: 17-of-34   0.5 GB: 18-of-34   0.5 GB: 19-of-34   0.5 GB: 20-of-34   0.5 GB: 21-of-34   0.5 GB: 22-of-34   0.5 GB: 23-of-34   0.5 GB: 24-of-34   0.5 GB: 25-of-34   0.5 GB: 26-of-34   0.5 GB: 27-of-34   0.5 GB: 28-of-34   0.5 GB: 29-of-34   0.5 GB: 30-of-34   0.5 GB: 31-of-34   0.5 GB: 32-of-34   0.5 GB: 33-of-34   0.5 GB: 34-of-34
Model ArchitectureQwen2ForCausalLM
Context Length131072
Model Max Length131072
Transformers Version4.46.3
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typefloat16
Errorsreplace

Best Alternatives to SJT 8B

Best Alternatives
Context / RAM
Downloads
Likes
Sailor2 8B Chat32K / 17.1 GB40516
SupaMATH128K / 5.6 GB50
Sailor2 8B Chat Uncensored32K / 17.1 GB412

Rank the SJT 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? 43508 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