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 V1.1 by Sakalti

 »  All LLMs  »  Sakalti  »  SJT 8B V1.1   URL Share it on

  9   
  Merged Model   Autotrain compatible Base model:finetune:sakalti/sj...   Base model:sakalti/sjt-7b-v1.1   Conversational   Endpoints compatible   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Sakalti/SJT-8B-V1.1 

SJT 8B V1.1 Benchmarks

MMLU Pro: 35.9
GPQA: 11.52
MUSR: 11.56
BBH: 31.32
IFEval: 46.21 vs 88 (so35)-47.5%
MATH Lvl 5: 20.69
LLME Score: 0.3189
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
SJT 8B V1.1 (Sakalti/SJT-8B-V1.1)

SJT 8B V1.1 Parameters and Internals

LLM NameSJT 8B V1.1
Repository 🤗https://huggingface.co/Sakalti/SJT-8B-V1.1 
Base Model(s)  Sakalti/SJT-7B-V1.1   Sakalti/SJT-7B-V1.1
Merged ModelYes
Model Size7b
Required VRAM17.8 GB
Updated2025-03-12
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 Length1010000
Model Max Length1010000
Transformers Version4.46.3
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151665
Torch Data Typefloat16
Errorsreplace

Best Alternatives to SJT 8B V1.1

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 7B Instruct 1M986K / 15.4 GB332966262
Hush Qwen2.5 7B RP V1.4 1M986K / 15.2 GB272
Qwen2.5 7B MixStock V0.1986K / 15.2 GB1653
Hush Qwen2.5 7B V1.1986K / 15.2 GB261
Hush Qwen2.5 7B V1.3986K / 15.2 GB192
Hush Qwen2.5 7B V1.4986K / 15.2 GB231
Hush Qwen2.5 7B V1.2986K / 15.2 GB211
Hush Qwen2.5 7B Preview986K / 15.2 GB840
Qwen2.5 7B Preview986K / 15.2 GB130
Qwen2.5 7B RRP 1M986K / 15.2 GB2086
Note: green Score (e.g. "73.2") means that the model is better than Sakalti/SJT-8B-V1.1.

Rank the SJT 8B V1.1 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