Dorna Llama3 8B Instruct AWQ by amir-ma71

 ยป  All LLMs  ยป  amir-ma71  ยป  Dorna Llama3 8B Instruct AWQ   URL Share it on

  4-bit   Autotrain compatible   Awq   En   Endpoints compatible   Fa   Instruct   Llama   Quantized   Region:us   Safetensors   Sharded   Tensorflow

Dorna Llama3 8B Instruct AWQ Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
๐ŸŒŸ Advertise your project ๐Ÿš€

Dorna Llama3 8B Instruct AWQ Parameters and Internals

Model Type 
text-generation
Use Cases 
Areas:
research, commercial applications
Applications:
Persian language text-generation
Primary Use Cases:
Persian assistant
Additional Notes 
Quantized version uses AWQ method for space efficiency with minimal accuracy loss.
Supported Languages 
en (supported), fa (supported)
Input Output 
Input Format:
messages in a JSON list with role and content fields
Accepted Modalities:
text
Output Format:
generated text
Performance Tips:
Use the quantized version for lower GPU memory use.
LLM NameDorna Llama3 8B Instruct AWQ
Repository ๐Ÿค—https://huggingface.co/amir-ma71/Dorna-Llama3-8B-Instruct-AWQ 
Model Size8b
Required VRAM5.8 GB
Updated2025-06-09
Maintaineramir-ma71
Model Typellama
Instruction-BasedYes
Model Files  4.7 GB: 1-of-2   1.1 GB: 2-of-2
Supported Languagesen fa
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureLlamaForCausalLM
Context Length8192
Model Max Length8192
Transformers Version4.41.2
Vocabulary Size128256
Torch Data Typebfloat16
Dorna Llama3 8B Instruct AWQ (amir-ma71/Dorna-Llama3-8B-Instruct-AWQ)

Best Alternatives to Dorna Llama3 8B Instruct AWQ

Best Alternatives
Context / RAM
Downloads
Likes
...8B Instruct Gradient 1048K AWQ1024K / 5.8 GB240
...radient 1048K AWQ 4bit Smashed1024K / 5.8 GB151
...Instruct 262K AWQ 4bit Smashed256K / 5.8 GB254
...ta Llama 3 8B Instruct 64K AWQ64K / 5.8 GB250
... Instruct 8B 32K V0.1 4bit AWQ64K / 5.8 GB210
Llama 3 8B Instruct AWQ8K / 5.8 GB2186424
Meta Llama 3 8B Instruct AWQ8K / 5.8 GB12055
...eta Llama 3 8B Instruct Hf AWQ8K / 5.8 GB12209
Meta Llama 3 8B Instruct AWQ8K / 5.8 GB230
Meta Llama 3 8B Instruct AWQ8K / 5.8 GB120
Note: green Score (e.g. "73.2") means that the model is better than amir-ma71/Dorna-Llama3-8B-Instruct-AWQ.

Rank the Dorna Llama3 8B Instruct AWQ 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  
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? 48023 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124