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

Synatra 7B V0.3 DPO EXL2 by IHaBiS

 »  All LLMs  »  IHaBiS  »  Synatra 7B V0.3 DPO EXL2   URL Share it on

  7   

Synatra 7B V0.3 DPO EXL2 is an open-source language model by IHaBiS. Features: 7b LLM, VRAM: 7.4GB, Context: 32K, License: cc-by-sa-4.0, Quantized, HF Score: 60.6, LLM Explorer Score: 0.12, Arc: 62.8, HellaSwag: 82.6, MMLU: 61.5, TruthfulQA: 56.5, WinoGrande: 76.2, GSM8K: 23.7.

  Conversational   Endpoints compatible   Exl2   Mistral   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/IHaBiS/Synatra-7B-v0.3-dpo-exl2 

Synatra 7B V0.3 DPO EXL2 Benchmarks

ARC: 62.8 vs 96.7 (so35)-35.1%
HellaSwag: 82.58 vs 95.3 (gpt4)-13.3%
MMLU: 61.46 vs 88.3 (so35)-30.4%
TruthfulQA: 56.46 vs 59 (gpt4)-4.3%
WinoGrande: 76.24 vs 87.5 (gpt4)-12.9%
GSM8K: 23.73 vs 96.4 (so35)-75.4%
LLME Score: 0.12251
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Synatra 7B V0.3 DPO EXL2 (IHaBiS/Synatra-7B-v0.3-dpo-exl2)
🌟 Advertise your project 🚀

Synatra 7B V0.3 DPO EXL2 Parameters and Internals

Training Details 
Methodology:
Uses ChatML format and Alpaca(No-Input) format
Hardware Used:
A100 80GB * 1
LLM NameSynatra 7B V0.3 DPO EXL2
Repository 🤗https://huggingface.co/IHaBiS/Synatra-7B-v0.3-dpo-exl2 
Base Model(s)  maywell/Synatra-7B-v0.3-dpo   maywell/Synatra-7B-v0.3-dpo
Model Size7b
Required VRAM7.4 GB
Updated2026-03-30
MaintainerIHaBiS
Model Typemistral
Model Files  7.4 GB
Quantization Typeexl2
Model ArchitectureMistralForCausalLM
Licensecc-by-sa-4.0
Context Length32768
Model Max Length32768
Transformers Version4.34.1
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32002
Torch Data Typebfloat16

Best Alternatives to Synatra 7B V0.3 DPO EXL2

Best Alternatives
Context / RAM
Downloads
Likes
...t 3.5 0106 128K 4.0bpw H6 EXL2128K / 3.9 GB11
...t 3.5 0106 128K 8.0bpw H8 EXL2128K / 7.4 GB11
Mistral 7B V0.3 Bnb 4bit32K / 4.1 GB35143322
Mistral 7B Instruct V0.2 Fp1632K / 14.4 GB260
Mistral 7B Instruct V0.2 4bit32K / 4.3 GB1331
...tral 7B Instruct V0.3 Bnb 4bit32K / 4.1 GB3043728
Mistral 7B Instruct V0.2 8bit32K / 7.6 GB41
...tral 7B Instruct V0.2 Bnb 4bit32K / 4.1 GB1256736
Mixtral V0.3 Full 16bit32K / 14.5 GB60
Mistral 7B Instruct V0.3 4bit32K / 4.1 GB250538
Note: green Score (e.g. "73.2") means that the model is better than IHaBiS/Synatra-7B-v0.3-dpo-exl2.

Rank the Synatra 7B V0.3 DPO EXL2 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? 52721 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.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer