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

Saiga 30B Lora by IlyaGusev

 »  All LLMs  »  IlyaGusev  »  Saiga 30B Lora   URL Share it on

  0   

Saiga 30B Lora is an open-source language model by IlyaGusev. Features: 30b LLM, VRAM: 0.2GB, License: cc-by-4.0, Instruction-Based, LLM Explorer Score: 0.07.

  Adapter   Conversational Dataset:ilyagusev/oasst1 ru ma... Dataset:ilyagusev/ru sharegpt ... Dataset:ilyagusev/ru turbo alp... Dataset:ilyagusev/ru turbo alp... Dataset:ilyagusev/ru turbo sai...   Dataset:lksy/ru instruct gpt4   Finetuned   Instruct   Lora   Region:us   Ru
Model Card on HF 🤗: https://huggingface.co/IlyaGusev/saiga_30b_lora 

Saiga 30b Lora Benchmarks

LLME Score: 0.07025
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Saiga 30B Lora (IlyaGusev/saiga_30b_lora)
🌟 Advertise your project 🚀

Saiga 30B Lora Parameters and Internals

Model Type 
conversational
Use Cases 
Areas:
research, conversational applications
Primary Use Cases:
answering questions, generating creative writing, problem-solving, language tasks
Additional Notes 
Uses four datasets in v1 and seven in v2 for training. Utilizes a conversational template for dialogue flow. Employs specific predefined roles for interaction: system, user, bot.
Supported Languages 
ru (full proficiency)
Training Details 
Data Sources:
IlyaGusev/ru_turbo_alpaca, IlyaGusev/ru_turbo_saiga, IlyaGusev/oasst1_ru_main_branch, IlyaGusev/ru_sharegpt_cleaned, IlyaGusev/ru_turbo_alpaca_evol_instruct, lksy/ru_instruct_gpt4
Methodology:
adapter-only version
Context Length:
2000
Model Architecture:
Customized adapter for LLaMA
Input Output 
Input Format:
{role}\n{content}
Accepted Modalities:
text
Output Format:
textual responses
Release Notes 
Version:
v1
Notes:
First version; used four datasets; Ru LLaMA conversational structure.
Version:
v2
Notes:
Refined with seven datasets; updated conversational structure.
LLM NameSaiga 30b Lora
Repository 🤗https://huggingface.co/IlyaGusev/saiga_30b_lora 
Model Size30b
Required VRAM0.2 GB
Updated2025-10-12
MaintainerIlyaGusev
Instruction-BasedYes
Model Files  0.2 GB
Supported Languagesru
Model ArchitectureAdapter
Licensecc-by-4.0
Model Max Length2048
Is Biasednone
Tokenizer ClassLlamaTokenizer
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesq_proj|v_proj|k_proj|o_proj
LoRA Alpha16
LoRA Dropout0.05
R Param16

Rank the Saiga 30B Lora 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? 52473 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