LLM EXPLORER 60,645 MODELS INDEXED

Mistral 7B Instruct Uz by behbudiy

By behbudiy · 59 downloads
HF Repo ↗ Copy URL

Mistral 7B Instruct Uz is an open-source language model by behbudiy. Features: 7b LLM, VRAM: 14.5GB, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.25, ELO: 1110.

Base model:finetune:mistralai/... Base model:mistralai/mistral-7...   Conversational   Dataset:allenai/c4 Dataset:behbudiy/alpaca-cleane... Dataset:behbudiy/translation-i... Dataset:mldatascientist/wikipe...   Dataset:tahrirchi/uz-crawl   Dataset:yahma/alpaca-cleaned   En   Endpoints compatible   Instruct   Mistral   Pytorch   Region:us   Sharded   Summarization   Translation   Uz
Model Card on HF 🤗: https://huggingface.co/behbudiy/Mistral-7B-Instruct-Uz 

Mistral 7B Instruct Uz Benchmarks

LMSys ELO 1110 vs 1272 (so35) -12.7%
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Mistral 7B Instruct Uz Parameters and Internals

Model Type 
text-generation, summarization, translation, question-answering
Use Cases 
Areas:
research, commercial applications
Applications:
machine translation, summarization, dialogue systems
Primary Use Cases:
Uzbek machine translation, Uzbek text summarization, Uzbek dialogue systems
Supported Languages 
uz (fluent), en (fluent)
Training Details 
Data Sources:
tahrirchi/uz-crawl, allenai/c4, MLDataScientist/Wikipedia-uzbek-2024-05-01, yahma/alpaca-cleaned, behbudiy/alpaca-cleaned-uz, behbudiy/translation-instruction
Methodology:
The model has been continually pre-trained and instruction-tuned using a mix of publicly available and syntheticly constructed Uzbek and English data.
Model Architecture:
Transformer architecture
Input Output 
Input Format:
Expected input format follows regular NLP conversational prompts.
Accepted Modalities:
text
Output Format:
Text output format.
LLM NameMistral 7B Instruct Uz
Repository 🤗https://huggingface.co/behbudiy/Mistral-7B-Instruct-Uz 
Base Model(s)  mistralai/Mistral-7B-Instruct-v0.3   mistralai/Mistral-7B-Instruct-v0.3
Model Size7b
Required VRAM14.5 GB
Updated2026-08-08
Maintainerbehbudiy
Instruction-BasedYes
Model Files  14.5 GB   5.0 GB: 1-of-3   5.0 GB: 2-of-3   4.5 GB: 3-of-3
Supported Languagesuz en
Model ArchitectureAutoModelForCausalLM
Licenseapache-2.0
Tokenizer ClassLlamaTokenizer
Vocabulary Size32768

Best Alternatives to Mistral 7B Instruct Uz

Best Alternatives
Context / RAM
Downloads
Likes
Mistral 7B Instruct V0.332K / 14.5 GB916
Mistral 7B Instruct V0.332K / 14.5 GB11223
...ralai Mistral 7B Instruct V0.332K / 14.5 GB63
Mistral 7B Instruct V0.332K / 14.5 GB60
Full V4 Astromistral Final32K / 4.5 GB61
Zyr3 V10K / 0.1 GB2061
Dekillnovelist V20K / 0.2 GB2030
Mistral 7B Manumit V10K / 14.5 GB1300
Qwen Medical 7B0K / 15.4 GB240
Acemath Convfinqa0K / 15.2 GB60
Note: green Score (e.g. "73.2") means that the model is better than behbudiy/Mistral-7B-Instruct-Uz.