Saka 3.8B by Sakalti

 ยป  All LLMs  ยป  Sakalti  ยป  Saka 3.8B   URL Share it on

  Merged Model   Arxiv:2306.01708   Autotrain compatible Base model:anakin87/phi-3.5-mi... Base model:axcxept/borea-phi-3...   Conversational   Custom code   Endpoints compatible   Instruct   Phi3   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF ๐Ÿค—: https://huggingface.co/Sakalti/Saka-3.8B 

Saka 3.8B Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
๐ŸŒŸ Advertise your project ๐Ÿš€

Saka 3.8B Parameters and Internals

LLM NameSaka 3.8B
Repository ๐Ÿค—https://huggingface.co/Sakalti/Saka-3.8B 
Base Model(s)  AXCXEPT/Borea-Phi-3.5-mini-Instruct-Common   microsoft/phi-3.5-mini-instruct   anakin87/Phi-3.5-mini-ITA   AXCXEPT/Borea-Phi-3.5-mini-Instruct-Common   microsoft/phi-3.5-mini-instruct   anakin87/Phi-3.5-mini-ITA
Merged ModelYes
Model Size3.8b
Required VRAM7.7 GB
Updated2025-06-09
MaintainerSakalti
Model Typephi3
Instruction-BasedYes
Model Files  1.0 GB: 1-of-9   1.0 GB: 2-of-9   1.0 GB: 3-of-9   0.9 GB: 4-of-9   0.9 GB: 5-of-9   0.9 GB: 6-of-9   0.9 GB: 7-of-9   0.9 GB: 8-of-9   0.2 GB: 9-of-9
Model ArchitecturePhi3ForCausalLM
Context Length131072
Model Max Length131072
Transformers Version4.46.3
Tokenizer ClassLlamaTokenizer
Padding Token<|endoftext|>
Vocabulary Size32064
Torch Data Typefloat16
Saka 3.8B (Sakalti/Saka-3.8B)

Best Alternatives to Saka 3.8B

Best Alternatives
Context / RAM
Downloads
Likes
Phi 4 Mini Instruct128K / 7.7 GB273273496
Phi 3.5 Mini Instruct128K / 7.7 GB309317873
Phi 3 Mini 128K Instruct128K / 7.7 GB3196781647
NuExtract V1.5128K / 7.7 GB10851189
NuExtract 1.5128K / 7.7 GB27686232
Phi 4 Mini Instruct128K / 7.7 GB360114
Phi 3.5 Mini TitanFusion 0.1128K / 7.7 GB230
Phi 4 Bifrost Sol 3.8B128K / 7.7 GB541
ECE EIFFEL 3Bv2128K / 7.7 GB50
Glider128K / 15.4 GB73940
Note: green Score (e.g. "73.2") means that the model is better than Sakalti/Saka-3.8B.

Rank the Saka 3.8B Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 48046 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124