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

Vikhr Llama 3.2 1B Instruct by Vikhrmodels

 »  All LLMs  »  Vikhrmodels  »  Vikhr Llama 3.2 1B Instruct   URL Share it on

  5781   
  Arxiv:2405.13929   Autotrain compatible Base model:finetune:meta-llama... Base model:meta-llama/llama-3....   Conversational Dataset:vikhrmodels/grandmaste...   En   Endpoints compatible   Instruct   Llama   Region:us   Ru   Safetensors
Model Card on HF 🤗: https://huggingface.co/Vikhrmodels/Vikhr-Llama-3.2-1B-Instruct 

Vikhr Llama 3.2 1B Instruct Benchmarks

LLME Score: 0.31422
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Vikhr Llama 3.2 1B Instruct (Vikhrmodels/Vikhr-Llama-3.2-1B-Instruct)

Vikhr Llama 3.2 1B Instruct Parameters and Internals

Model Type 
language model, instructive model
Additional Notes 
Model efficiency is 5 times higher than the base model, perfect for low-power or mobile devices.
Supported Languages 
languages_supported (/- ru /- en)
Training Details 
Data Sources:
Vikhrmodels/GrandMaster-PRO-MAX
Data Volume:
150k instructions
Methodology:
Supervised Fine-Tuning (SFT)
Model Architecture:
Llama-3.2-1B-Instruct modified for Russian language
LLM NameVikhr Llama 3.2 1B Instruct
Repository 🤗https://huggingface.co/Vikhrmodels/Vikhr-Llama-3.2-1B-Instruct 
Model NameVikhr-Llama-3.2-1B-instruct
Base Model(s)  meta-llama/Llama-3.2-1B-Instruct   meta-llama/Llama-3.2-1B-Instruct
Model Size1b
Required VRAM2.5 GB
Updated2024-12-21
MaintainerVikhrmodels
Model Typellama
Instruction-BasedYes
Model Files  2.5 GB
Supported Languagesru en
Model ArchitectureLlamaForCausalLM
Licensellama3.2
Context Length131072
Model Max Length131072
Transformers Version4.44.2
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|reserved_special_token_0|>
Vocabulary Size128256
Torch Data Typefloat16

Best Alternatives to Vikhr Llama 3.2 1B Instruct

Best Alternatives
Context / RAM
Downloads
Likes
Llama 3.2 1B Instruct128K / 2.5 GB1873115654
Llama 3.2 1B Instruct128K / 2.5 GB7411645
FastLlama 3.2 1B Instruct128K / 4.9 GB10458
Llama 3.2 SUN HDIC 1B Instruct128K / 3 GB790
Explore Llama 3.2 1B Inst V1.1128K / 2.5 GB4420
FuseChat Llama 3.2 1B Instruct128K / 2.5 GB4244
Llama 3.2 SUN 2.5B Chat128K / 4.9 GB3861
... 1B Instruct Medmcqa Zh Linear128K / 4.9 GB4390
Llama 3.2 1B Spinquant Hf128K / 2.5 GB5260
...inetuned Billingual 3.0 Merged128K / 2.5 GB4270
Note: green Score (e.g. "73.2") means that the model is better than Vikhrmodels/Vikhr-Llama-3.2-1B-Instruct.

Rank the Vikhr Llama 3.2 1B Instruct 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? 40013 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 v20241217
  Support LLM Explorer