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

Saka 24B by Sakalti

 »  All LLMs  »  Sakalti  »  Saka 24B   URL Share it on

  252   
  Merged Model   Arxiv:2408.07990   Autotrain compatible Base model:alsamcur123/mistral... Base model:huihui-ai/mistral-s... Base model:trashpanda-org/ms-2...   Conversational   Endpoints compatible   Instruct   Mistral   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Sakalti/Saka-24B 

Saka 24B Benchmarks

MMLU Pro: 41.84
GPQA: 12.3
MUSR: 15.73
BBH: 43.31
IFEval: 38.19 vs 88 (so35)-56.6%
MATH Lvl 5: 18.05
LLME Score: 0.32296
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Saka 24B (Sakalti/Saka-24B)

Saka 24B Parameters and Internals

LLM NameSaka 24B
Repository 🤗https://huggingface.co/Sakalti/Saka-24B 
Base Model(s)  ... 24B Instruct 2501 Abliterated   MS 24B Instruct Mullein V0   ...all3 24B InstructContinuedFine   mergekit-community/24B-MS-PRO-V0.01   huihui-ai/Mistral-Small-24B-Instruct-2501-abliterated   trashpanda-org/MS-24B-Instruct-Mullein-v0   AlSamCur123/Mistral-Small3-24B-InstructContinuedFine   mergekit-community/24B-MS-PRO-V0.01
Merged ModelYes
Model Size24b
Required VRAM47.3 GB
Updated2025-02-12
MaintainerSakalti
Model Typemistral
Instruction-BasedYes
Model Files  4.9 GB: 1-of-10   4.8 GB: 2-of-10   4.8 GB: 3-of-10   4.9 GB: 4-of-10   4.8 GB: 5-of-10   4.8 GB: 6-of-10   4.9 GB: 7-of-10   4.8 GB: 8-of-10   4.8 GB: 9-of-10   3.8 GB: 10-of-10
Model ArchitectureMistralForCausalLM
Context Length32768
Model Max Length32768
Transformers Version4.48.2
Tokenizer ClassLlamaTokenizer
Vocabulary Size131072
Torch Data Typebfloat16

Best Alternatives to Saka 24B

Best Alternatives
Context / RAM
Downloads
Likes
...ral Nemo Instruct 24B Merge V11000K / 24.6 GB90
Harbinger 24B128K / 47.3 GB23051
Pantheon RP 1.8 24B Small 3.1128K / 47.3 GB162962
Zero Mistral 24B128K / 47.3 GB5825
...Small 3.1 24B Instruct 2503 HF128K / 47.3 GB157812
...Small 3.1 24B Instruct 2503 Hf128K / 47.3 GB9032
Eurydice 24B V3128K / 47.3 GB1836
... 24B Small Instruct Ties Merge128K / 47.3 GB1972
Eurydice 24B V2128K / 47.3 GB23513
...all 3.1 24B Instruct 2503 Text128K / 47.3 GB2250
Note: green Score (e.g. "73.2") means that the model is better than Sakalti/Saka-24B.

Rank the Saka 24B 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? 47770 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