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

Gigasaiga Lora by IlyaGusev

 »  All LLMs  »  IlyaGusev  »  Gigasaiga Lora   URL Share it on

  0   

Gigasaiga Lora is an open-source language model by IlyaGusev. Features: LLM, License: cc-by-4.0, Instruction-Based, LLM Explorer Score: 0.09.

  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/gigasaiga_lora 

Gigasaiga Lora Benchmarks

LLME Score: 0.08547
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Gigasaiga Lora (IlyaGusev/gigasaiga_lora)
🌟 Advertise your project 🚀

Gigasaiga Lora Parameters and Internals

Model Type 
conversational, text generation
Additional Notes 
The model is implemented using peft and transformers libraries for conversational functionality in Russian.
Supported Languages 
ru (native)
Training Details 
Data Sources:
ru_turbo_alpaca, ru_turbo_saiga, ru_sharegpt_cleaned, oasst1_ru_main_branch, ru_turbo_alpaca_evol_instruct, lksy/ru_instruct_gpt4
Methodology:
Adapter-only version with datasets merging
Input Output 
Input Format:
~~{role} {content}~~
Accepted Modalities:
text
Output Format:
Textual output for chatbot interactions.
Release Notes 
Version:
v2
Notes:
- dataset code revision 9f4145bf954082bf110e084feff93f2d59b609ee - wandb link: https://wandb.ai/ilyagusev/rulm_self_instruct/runs/97uib9vp - 5 datasets: ru_turbo_saiga, ru_sharegpt_cleaned, oasst1_ru_main_branch, gpt_roleplay_realm, ru_instruct_gpt4 - gigasaiga_v2 vs gigasaiga: 96-8-72 - gigasaiga_v2 vs gpt-3.5-turbo: 57-1-118
Version:
v1
Notes:
- dataset code revision 7712a061d993f61c49b1e2d992e893c48acb3a87 - wandb link: https://wandb.ai/ilyagusev/rulm_self_instruct/runs/lwgw4a1w - 7 datasets: ru_turbo_alpaca, ru_turbo_saiga, ru_sharegpt_cleaned, oasst1_ru_main_branch, gpt_roleplay_realm, ru_turbo_alpaca_evol_instruct (iteration 1/2), ru_instruct_gpt4 - Datasets merging script: create_chat_set.py - saiga13b_v2 vs gigasaiga: 112-11-53
LLM NameGigasaiga Lora
Repository 🤗https://huggingface.co/IlyaGusev/gigasaiga_lora 
Required VRAM0 GB
Updated2025-09-23
MaintainerIlyaGusev
Instruction-BasedYes
Model Files  0.0 GB
Supported Languagesru
Model ArchitectureAdapter
Licensecc-by-4.0
Is Biasednone
Tokenizer ClassGPT2Tokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<|endoftext|>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesc_attn
LoRA Alpha16
LoRA Dropout0.1
R Param8
Errorsreplace

Best Alternatives to Gigasaiga Lora

Best Alternatives
Context / RAM
Downloads
Likes
Phi 3 Mini 4K Instruct Sa V0.10K / 0 GB50
...caaaf043da230d9a30d8e0ddcbe8790K / 0.4 GB110
...357cade9cc1096cecc35c34dba89920K / 1.3 GB100
...ini Instruct MedicalChat QLoRA0K / 0.1 GB02
...mall Physics Finetuned Adapter0K / 0.1 GB11
Mistral Small Dampf Qlora0K / 0.8 GB80
Mistral Small Fujin Qlora0K / 0.8 GB22
Test0K / 0 GB50
Vfgf0K / 0 GB50
Results0K / 0 GB50
Note: green Score (e.g. "73.2") means that the model is better than IlyaGusev/gigasaiga_lora.

Rank the Gigasaiga 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? 52394 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