Meta Llama 3 8B Int3 GPTQ Wikitext2 by Xu-Ouyang

 ยป  All LLMs  ยป  Xu-Ouyang  ยป  Meta Llama 3 8B Int3 GPTQ Wikitext2   URL Share it on

  Arxiv:1910.09700   3-bit   Autotrain compatible   Endpoints compatible   Gptq   Llama   Quantized   Region:us   Safetensors

Meta Llama 3 8B Int3 GPTQ Wikitext2 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Meta Llama 3 8B Int3 GPTQ Wikitext2 (Xu-Ouyang/Meta-Llama-3-8B-int3-GPTQ-wikitext2)

Meta Llama 3 8B Int3 GPTQ Wikitext2 Parameters and Internals

LLM NameMeta Llama 3 8B Int3 GPTQ Wikitext2
Repository ๐Ÿค—https://huggingface.co/Xu-Ouyang/Meta-Llama-3-8B-int3-GPTQ-wikitext2 
Model Size8b
Required VRAM4.9 GB
Updated2025-02-01
MaintainerXu-Ouyang
Model Typellama
Model Files  4.9 GB
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureLlamaForCausalLM
Context Length8192
Model Max Length8192
Transformers Version4.44.0
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
Torch Data Typefloat16

Best Alternatives to Meta Llama 3 8B Int3 GPTQ Wikitext2

Best Alternatives
Context / RAM
Downloads
Likes
...a 3 8B Instruct 262K 4bit GPTQ256K / 5.8 GB791
... 8B Instruct 262K 4bit GPTQ 02256K / 5.7 GB770
...lama 3.1 8B Instruct GPTQ INT4128K / 5.8 GB1563721
...Instruct 80K Qlora Merged GPTQ80K / 5.8 GB50
Llama3 German 8B 32K GPTQ64K / 5.7 GB100
...oLeo Instruct 8B 32K V0.1 GPTQ64K / 5.7 GB60
Tsukasa Llama 3 8B Qlora Gptq32K / 5.8 GB800
Llama 3 Soliloquy 8B V2 GPTQ24K / 5.7 GB101
Llama 3 Soliloquy 8B GPTQ16K / 5.7 GB105
Llama 3 8B Instruct GPTQ 4 Bit8K / 5.7 GB1055525
Note: green Score (e.g. "73.2") means that the model is better than Xu-Ouyang/Meta-Llama-3-8B-int3-GPTQ-wikitext2.

Rank the Meta Llama 3 8B Int3 GPTQ Wikitext2 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? 42577 in total.

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