RuGPT 3.5 13B GGML by evilfreelancer

 ยป  All LLMs  ยป  evilfreelancer  ยป  RuGPT 3.5 13B GGML   URL Share it on

  Conversational Dataset:ilyagusev/gpt roleplay... 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   En   Endpoints compatible   Ggml   Gpt2   Instruct   Lora   Q4   Quantized   Region:us   Ru   Rugpt

RuGPT 3.5 13B GGML Benchmarks

nn.n% โ€” How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Sponsored by Nebius

RuGPT 3.5 13B GGML Parameters and Internals

Model Type 
conversational
Additional Notes 
This model adapts the ruGPT-3.5-13B model using adapter-only techniques similar to GigaSaiga, with additional datasets for enhanced performance.
Supported Languages 
ru (high), en (medium)
Training Details 
Data Sources:
IlyaGusev/ru_turbo_alpaca, IlyaGusev/ru_turbo_alpaca_evol_instruct, IlyaGusev/ru_turbo_saiga, IlyaGusev/ru_sharegpt_cleaned, IlyaGusev/oasst1_ru_main_branch, IlyaGusev/gpt_roleplay_realm, lksy/ru_instruct_gpt4
Methodology:
Adapter-only training with a focus on conversational AI.
Input Output 
Input Format:
Role-based conversation prompts
Accepted Modalities:
text
Output Format:
Conversational text
LLM NameRuGPT 3.5 13B GGML
Repository ๐Ÿค—https://huggingface.co/evilfreelancer/ruGPT-3.5-13B-ggml 
Model Size13b
Required VRAM7.4โ€ฏGB
Updated2025-01-05
Maintainerevilfreelancer
Model Typegpt2
Instruction-BasedYes
Model Files  7.4 GB   8.2 GB   9.1 GB   9.9 GB   14.0 GB
Supported Languagesru en
GGML QuantizationYes
Quantization Typeggml|q4
Model ArchitectureAutoModel
Licensemit
LoRA ModelYes

Best Alternatives to RuGPT 3.5 13B GGML

Best Alternatives
Context / RAM
Downloads
Likes
Speechless Llama2 13B GGML0K / 5.5โ€‰GB152
CodeLlama 13B Instruct GGML0K / 5.7โ€‰GB1519
...lama2 13B Orca V2 8K 3166 GGML0K / 5.7โ€‰GB814
Vigogne 2 13B Instruct GGML0K / 5.5โ€‰GB146
...1.0 Uncensored Llama2 13B GGML0K / 5.5โ€‰GB1359
...aMa 3 Instruct Zeroed 13B GGUF0K / 5โ€‰GB281
Llama 3 13B Instruct V0.1 GGUF0K / 5.1โ€‰GB4165
Codellama 7B Instruct GGUF0K / 2.8โ€‰GB1410
Codellama 13B Instruct GGUF0K / 13.8โ€‰GB240
Law LLM 13B GGUF0K / 5.4โ€‰GB22887
Note: green Score (e.g. "73.2") means that the model is better than evilfreelancer/ruGPT-3.5-13B-ggml.

Rank the RuGPT 3.5 13B GGML 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  
โ—โ—โ—โ—
Factuality and Completeness of Knowledge  
โ—โ—โ—โ—
Censorship and Alignment  
โ—โ—โ—โ—
Data Analysis and Insight Generation  
โ—โ—โ—โ—
Text Generation  
โ—โ—โ—โ—
Text Summarization and Feature Extraction  
โ—โ—โ—โ—
Code Generation  
โ—โ—โ—โ—
Multi-Language Support and Translation  
โ—โ—โ—โ—

What open-source LLMs or SLMs are you in search of? 40868 in total.

Our Social Media โ†’  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227