Lllyasviel Omost Llama 3 8B AWQ 4bit Smashed by PrunaAI

 ยป  All LLMs  ยป  PrunaAI  ยป  Lllyasviel Omost Llama 3 8B AWQ 4bit Smashed   URL Share it on

  4-bit   4bit   Autotrain compatible   Awq Base model:lllyasviel/omost-ll... Base model:quantized:lllyasvie...   Conversational   Endpoints compatible   Llama   Pruna-ai   Quantized   Region:us   Safetensors   Sharded   Tensorflow

Lllyasviel Omost Llama 3 8B AWQ 4bit Smashed Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Lllyasviel Omost Llama 3 8B AWQ 4bit Smashed (PrunaAI/lllyasviel-omost-llama-3-8b-AWQ-4bit-smashed)

Lllyasviel Omost Llama 3 8B AWQ 4bit Smashed Parameters and Internals

Model Type 
compressor
Additional Notes 
The smashed model is directly compared to the original base model under consistent conditions; however, results might vary based on different hardware settings.
Training Details 
Data Sources:
WikiText
Methodology:
The model is compressed with awq
Input Output 
Input Format:
Text based input using tokenized prompts
Accepted Modalities:
text
Output Format:
Generated text response
Performance Tips:
Test the efficiency gains directly in user's specific use cases to gauge actual benefit.
LLM NameLllyasviel Omost Llama 3 8B AWQ 4bit Smashed
Repository ๐Ÿค—https://huggingface.co/PrunaAI/lllyasviel-omost-llama-3-8b-AWQ-4bit-smashed 
Base Model(s)  Omost Llama 3 8B   lllyasviel/omost-llama-3-8b
Model Size8b
Required VRAM5.8 GB
Updated2025-01-20
MaintainerPrunaAI
Model Typellama
Model Files  4.7 GB: 1-of-2   1.1 GB: 2-of-2
AWQ QuantizationYes
Quantization Typeawq|4bit
Model ArchitectureLlamaForCausalLM
Context Length8192
Model Max Length8192
Transformers Version4.40.0
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|reserved_special_token_250|>
Vocabulary Size128256
Torch Data Typefloat16

Best Alternatives to Lllyasviel Omost Llama 3 8B AWQ 4bit Smashed

Best Alternatives
Context / RAM
Downloads
Likes
...8B Instruct Gradient 1048K AWQ1024K / 5.8 GB250
...radient 1048K AWQ 4bit Smashed1024K / 5.8 GB81
...Instruct 262K AWQ 4bit Smashed256K / 5.8 GB144
...ta Llama 3 8B Instruct 64K AWQ64K / 5.8 GB80
... Instruct 8B 32K V0.1 4bit AWQ64K / 5.8 GB270
Llama 3 ELYZA JP 8B AWQ8K / 5.8 GB21993
Llama 3 8B Instruct AWQ8K / 5.8 GB491522
Meta Llama 3 8B Instruct AWQ8K / 5.8 GB8945
...eta Llama 3 8B Instruct Hf AWQ8K / 5.8 GB5478
Meta Llama 3 8B Instruct AWQ8K / 5.8 GB190
Note: green Score (e.g. "73.2") means that the model is better than PrunaAI/lllyasviel-omost-llama-3-8b-AWQ-4bit-smashed.

Rank the Lllyasviel Omost Llama 3 8B AWQ 4bit Smashed 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? 41636 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227