NousResearch Meta Llama 3 8B HQQ 2bit Smashed by PrunaAI

 ยป  All LLMs  ยป  PrunaAI  ยป  NousResearch Meta Llama 3 8B HQQ 2bit Smashed   URL Share it on

  2bit   Autotrain compatible Base model:finetune:nousresear... Base model:nousresearch/meta-l...   Endpoints compatible   Llama   Pruna-ai   Quantized   Region:us

NousResearch Meta Llama 3 8B HQQ 2bit Smashed Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
NousResearch Meta Llama 3 8B HQQ 2bit Smashed (PrunaAI/NousResearch-Meta-Llama-3-8B-HQQ-2bit-smashed)

NousResearch Meta Llama 3 8B HQQ 2bit Smashed Parameters and Internals

Use Cases 
Primary Use Cases:
AI model compression
Additional Notes 
The model is compressed using the hqq method, and quality might vary compared to the base model. Different metrics like 'Sync' and 'Async' help evaluate efficiency gains.
Input Output 
Output Format:
Outputs are generated after decoding from tokens.
Performance Tips:
Efficiency results may vary in different settings; users are recommended to test in their use-case settings.
LLM NameNousResearch Meta Llama 3 8B HQQ 2bit Smashed
Repository ๐Ÿค—https://huggingface.co/PrunaAI/NousResearch-Meta-Llama-3-8B-HQQ-2bit-smashed 
Base Model(s)  Meta Llama 3 8B   NousResearch/Meta-Llama-3-8B
Model Size8b
Required VRAM4 GB
Updated2025-01-22
MaintainerPrunaAI
Model Typellama
Model Files  4.0 GB
Quantization Type2bit
Model ArchitectureLlamaForCausalLM
Context Length8192
Model Max Length8192
Transformers Version4.40.0
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
Torch Data Typefloat16

Best Alternatives to NousResearch Meta Llama 3 8B HQQ 2bit Smashed

Best Alternatives
Context / RAM
Downloads
Likes
...B Instruct Gradient 1048K 8bit1024K / 8.6 GB251
...B Instruct Gradient 1048K 4bit1024K / 4.5 GB222
...truct Gradient 1048K Bpw6 EXL21024K / 6.7 GB92
...truct Gradient 1048K Bpw5 EXL21024K / 5.8 GB80
Llama 3 8B Instruct 1048K 4bit1024K / 4.5 GB825
Llama 3 8B Instruct 1048K 8bit1024K / 8.6 GB2317
... Gradient 1048K 8.0bpw H8 EXL21024K / 8.6 GB83
...ct Gradient 1048K Bpw2.25 EXL21024K / 3.4 GB81
...B Instruct 262k V2 EXL2 8.0bpw256K / 8.4 GB300
Llama 3 8B Instruct 262K 2bit256K / 2.5 GB171
Note: green Score (e.g. "73.2") means that the model is better than PrunaAI/NousResearch-Meta-Llama-3-8B-HQQ-2bit-smashed.

Rank the NousResearch Meta Llama 3 8B HQQ 2bit 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? 41728 in total.

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