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

Vikhr Llama3.1 8B Instruct R 21 09 24 by Vikhrmodels

 »  All LLMs  »  Vikhrmodels  »  Vikhr Llama3.1 8B Instruct R 21 09 24   URL Share it on

  1198   
Base model:finetune:meta-llama... Base model:meta-llama/llama-3.... Dataset:vikhrmodels/grandmaste... Dataset:vikhrmodels/grounded-r...   En   Instruct   Llama   Region:us   Ru   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Vikhrmodels/Vikhr-Llama3.1-8B-Instruct-R-21-09-24 

Vikhr Llama3.1 8B Instruct R 21 09 24 Benchmarks

MMLU Pro: 28.3
MUSR: 5.09
BBH: 32.67
IFEval: 64.31 vs 88 (so35)-26.9%
MATH Lvl 5: 21.75
LLME Score: 0.27116
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Vikhr Llama3.1 8B Instruct R 21 09 24 (Vikhrmodels/Vikhr-Llama3.1-8B-Instruct-R-21-09-24)
🌟 Advertise your project 🚀

Vikhr Llama3.1 8B Instruct R 21 09 24 Parameters and Internals

Model Type 
unimodal, LLM
Use Cases 
Areas:
research, industrial applications, coding, roleplay
Limitations:
model has a low level of safety in responses, not suited for character descriptions in system prompts
Considerations:
Use system prompts for styling; they must be in English.
Additional Notes 
The RAG mode requires a specific system prompt.
Supported Languages 
English (high-quality generation), Russian (high-quality generation), Other (some support)
Training Details 
Data Sources:
Vikhrmodels/GrandMaster-PRO-MAX, Vikhrmodels/Grounded-RAG-RU-v2
Data Volume:
150k instructions
Methodology:
SFT, SMPO, and alignment pipeline
Context Length:
128000
Safety Evaluation 
Ethical Considerations:
Model has a low level of safety in responses.
Input Output 
Accepted Modalities:
text
Performance Tips:
Better performance at lower temperatures and with beam search.
LLM NameVikhr Llama3.1 8B Instruct R 21 09 24
Repository 🤗https://huggingface.co/Vikhrmodels/Vikhr-Llama3.1-8B-Instruct-R-21-09-24 
Base Model(s)  meta-llama/Meta-Llama-3.1-8B-Instruct   meta-llama/Meta-Llama-3.1-8B-Instruct
Model Size8b
Required VRAM16.1 GB
Updated2025-09-23
MaintainerVikhrmodels
Model Typellama
Instruction-BasedYes
Model Files  5.0 GB: 1-of-4   5.0 GB: 2-of-4   4.9 GB: 3-of-4   1.2 GB: 4-of-4
Supported Languagesen ru
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version4.44.2
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|reserved_special_token_0|>
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to Vikhr Llama3.1 8B Instruct R 21 09 24

Best Alternatives
Context / RAM
Downloads
Likes
...otron 8B UltraLong 4M Instruct4192K / 32.1 GB1531120
...a 3.1 8B UltraLong 4M Instruct4192K / 32.1 GB17624
UltraLong Thinking4192K / 16.1 GB453
...otron 8B UltraLong 2M Instruct2096K / 32.1 GB114215
...a 3.1 8B UltraLong 2M Instruct2096K / 32.1 GB8759
...otron 8B UltraLong 1M Instruct1048K / 32.1 GB714252
...a 3.1 8B UltraLong 1M Instruct1048K / 32.1 GB138729
Zero Llama 3.1 8B Beta61048K / 16.1 GB21
...dger Nu Llama 3.1 8B UltraLong1048K / 16.2 GB53
....1 1million Ctx Dark Planet 8B1048K / 32.3 GB83

Rank the Vikhr Llama3.1 8B Instruct R 21 09 24 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? 51545 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