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

Llama 3.1 8B Instuct Uz by behbudiy

 »  All LLMs  »  behbudiy  »  Llama 3.1 8B Instuct Uz   URL Share it on

  695   
  Autotrain compatible   Conversational Dataset:behbudiy/alpaca-cleane... Dataset:behbudiy/translation-i...   Dataset:yahma/alpaca-cleaned   En   Endpoints compatible   Instruct   Llama   Lora   Region:us   Safetensors   Sharded   Summarization   Tensorflow   Translation   Uz
Model Card on HF 🤗: https://huggingface.co/behbudiy/Llama-3.1-8B-Instuct-Uz 

Llama 3.1 8B Instuct Uz Benchmarks

LLME Score: 0.20809
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama 3.1 8B Instuct Uz (behbudiy/Llama-3.1-8B-Instuct-Uz)

Llama 3.1 8B Instuct 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 Sentiment Analysis, Uzbek News Classification, MMLU
Additional Notes 
This model has been optimized for Uzbek language processing tasks and can be used with `transformers` library.
Supported Languages 
uz (Advanced), en (Advanced)
Training Details 
Data Sources:
yahma/alpaca-cleaned, behbudiy/alpaca-cleaned-uz, behbudiy/translation-instruction
Methodology:
Instruction-tuning using a mix of publicly available and syntheticly constructed Uzbek and English data.
Input Output 
Input Format:
JSON
Accepted Modalities:
text
Output Format:
text
Performance Tips:
Using the transformers 'pipeline' for conversational inference or shift to the `generate()` function for more advanced usage.
LLM NameLlama 3.1 8B Instuct Uz
Repository 🤗https://huggingface.co/behbudiy/Llama-3.1-8B-Instuct-Uz 
Base Model(s)  models/Meta-Llama-3.1-8B-Instruct   models/Meta-Llama-3.1-8B-Instruct
Model Size8b
Required VRAM16.1 GB
Updated2025-05-15
Maintainerbehbudiy
Model Typellama
Instruction-BasedYes
Model Files  0.7 GB   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 Languagesuz en
Model ArchitectureAutoModelForCausalLM
Licensellama3.1
Context Length131072
Model Max Length131072
Transformers Version4.43.3
Is Biasednone
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|reserved_special_token_247|>
Vocabulary Size128256
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesdown_proj|up_proj|k_proj|v_proj|q_proj|gate_proj|o_proj
LoRA Alpha32
LoRA Dropout0
R Param64
Torch Data Typebfloat16

Best Alternatives to Llama 3.1 8B Instuct Uz

Best Alternatives
Context / RAM
Downloads
Likes
Autotrain Pvqlj Odah20K / 0.2 GB180
500tiao 100lun0K / 0.2 GB110
Codelica0K / 16.1 GB1110
ModeliCo 8B0K / 16.1 GB102
...3.1 8B Instruct Simplicity RAG0K / 48.2 GB90
Llama31 Eros0K / 16.1 GB31
Llama 3.1 8b Prop Logic Ft0K / 0.2 GB357
...Instruct Persian Finetuned Sft0K / 0 GB165
Meta Llama 3.1 8B Instruct OAS0K / 16.1 GB241
... 3 Instruct Bellman 8B Swedish0K / 0 GB1172
Note: green Score (e.g. "73.2") means that the model is better than behbudiy/Llama-3.1-8B-Instuct-Uz.

Rank the Llama 3.1 8B Instuct Uz 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? 47368 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 v20241227
  Support LLM Explorer