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

Synthia 13B by migtissera

 »  All LLMs  »  migtissera  »  Synthia 13B   URL Share it on

  1847   
  Arxiv:2302.13971   Arxiv:2306.02707   Autotrain compatible   En   Endpoints compatible   Fp16   Llama   Pytorch   Quantized   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/migtissera/Synthia-13B 

Synthia 13B Benchmarks

ARC: 59.98 vs 96.7 (so35)-38%
HellaSwag: 81.86 vs 95.3 (gpt4)-14.1%
MMLU: 56.11 vs 88.3 (so35)-36.5%
TruthfulQA: 47.41 vs 59 (gpt4)-19.6%
WinoGrande: 76.09 vs 87.5 (gpt4)-13%
GSM8K: 10.99 vs 96.4 (so35)-88.6%
LLME Score: 0.14422
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Synthia 13B (migtissera/Synthia-13B)
🌟 Advertise your project 🚀

Synthia 13B Parameters and Internals

Model Type 
text-generation
Additional Notes 
This model is a LLama-2-13B model trained on Orca style datasets.
Supported Languages 
en (High proficiency)
Training Details 
Data Sources:
Orca style datasets
Methodology:
Fine-tuned for instruction following and long-form conversations
Input Output 
Input Format:
Prompt format includes system and user messages followed by assistant response
Accepted Modalities:
text
Output Format:
Text responses
LLM NameSynthia 13B
Repository 🤗https://huggingface.co/migtissera/Synthia-13B 
Model Size13b
Required VRAM26 GB
Updated2025-09-23
Maintainermigtissera
Model Typellama
Model Files  9.9 GB: 1-of-3   9.9 GB: 2-of-3   6.2 GB: 3-of-3
Supported Languagesen
Quantization Typefp16
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.32.0.dev0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Quantized Models of the Synthia 13B

Model
Likes
Downloads
VRAM
Synthia 13B GGUF41125 GB
Synthia 13B GPTQ3847 GB
Synthia 13B GGML265 GB

Best Alternatives to Synthia 13B

Best Alternatives
Context / RAM
Downloads
Likes
Llama13b 32K Illumeet Finetune32K / 26 GB90
...Maid V3 13B 32K 6.0bpw H6 EXL232K / 10 GB71
...Maid V3 13B 32K 8.0bpw H8 EXL232K / 13.2 GB71
WhiteRabbitNeo 13B V116K / 26 GB2649429
CodeLlama 13B Python Fp1616K / 26 GB283325
CodeLlama 13B Instruct Fp1616K / 26 GB284728
...Llama 13B Instruct Hf 4bit MLX16K / 7.8 GB11962
CodeLlama 13B Fp1616K / 26 GB766
Airophin 13B Pntk 16K Fp1616K / 26 GB17374
Codellama 13B Bnb 4bit16K / 7.2 GB205
Note: green Score (e.g. "73.2") means that the model is better than migtissera/Synthia-13B.

Rank the Synthia 13B 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? 51536 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 v20241124
  Support LLM Explorer