Gradientai Llama 3 8B Instruct 262K AWQ 4bit Smashed by PrunaAI

 ยป  All LLMs  ยป  PrunaAI  ยป  Gradientai Llama 3 8B Instruct 262K AWQ 4bit Smashed   URL Share it on

  4-bit   4bit   Autotrain compatible   Awq Base model:prunaai/gradientai-... Base model:quantized:prunaai/g...   Conversational   Endpoints compatible   Instruct   Llama   Pruna-ai   Quantized   Region:us   Safetensors   Sharded   Tensorflow

Gradientai Llama 3 8B Instruct 262K 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").
Gradientai Llama 3 8B Instruct 262K AWQ 4bit Smashed (PrunaAI/gradientai-Llama-3-8B-Instruct-262k-AWQ-4bit-smashed)

Gradientai Llama 3 8B Instruct 262K AWQ 4bit Smashed Parameters and Internals

Model Type 
compression, efficiency
Additional Notes 
The model uses safetensors format and calibration data from WikiText for compression. Different metrics for efficiency evaluation include inference latency, memory, energy consumption, and CO2 emissions. Efficiency evaluation results might vary based on the hardware and settings used.
LLM NameGradientai Llama 3 8B Instruct 262K AWQ 4bit Smashed
Repository ๐Ÿค—https://huggingface.co/PrunaAI/gradientai-Llama-3-8B-Instruct-262k-AWQ-4bit-smashed 
Base Model(s)  ...Instruct 262K AWQ 4bit Smashed   PrunaAI/gradientai-Llama-3-8B-Instruct-262k-AWQ-4bit-smashed
Model Size8b
Required VRAM5.8 GB
Updated2024-12-21
MaintainerPrunaAI
Model Typellama
Instruction-BasedYes
Model Files  4.7 GB: 1-of-2   1.1 GB: 2-of-2
AWQ QuantizationYes
Quantization Typeawq|4bit
Model ArchitectureLlamaForCausalLM
Context Length262144
Model Max Length262144
Transformers Version4.40.0
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
Torch Data Typefloat16

Quantized Models of the Gradientai Llama 3 8B Instruct 262K AWQ 4bit Smashed

Model
Likes
Downloads
VRAM
...Instruct 262K AWQ 4bit Smashed4135 GB

Best Alternatives to Gradientai Llama 3 8B Instruct 262K AWQ 4bit Smashed

Best Alternatives
Context / RAM
Downloads
Likes
...8B Instruct Gradient 1048K AWQ1024K / 5.8 GB140
...radient 1048K AWQ 4bit Smashed1024K / 5.8 GB321
...ta Llama 3 8B Instruct 64K AWQ64K / 5.8 GB120
... Instruct 8B 32K V0.1 4bit AWQ64K / 5.8 GB130
Llama 3 8B Instruct AWQ8K / 5.8 GB7900620
Meta Llama 3 8B Instruct AWQ8K / 5.8 GB13944
Meta Llama 3 8B Instruct AWQ8K / 5.8 GB12720
Meta Llama 3 8B Instruct AWQ8K / 5.8 GB1120
...eta Llama 3 8B Instruct Hf AWQ8K / 5.8 GB4468
Meta Llama 3 8B Instruct AWQ8K / 5.8 GB80
Note: green Score (e.g. "73.2") means that the model is better than PrunaAI/gradientai-Llama-3-8B-Instruct-262k-AWQ-4bit-smashed.

Rank the Gradientai Llama 3 8B Instruct 262K 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? 40013 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217