Meta Llama 3 70B Instruct AQLM 2Bit 1x16 by ISTA-DASLab

 ยป  All LLMs  ยป  ISTA-DASLab  ยป  Meta Llama 3 70B Instruct AQLM 2Bit 1x16   URL Share it on

  Arxiv:2401.06118   2bit   Autotrain compatible   Conversational   Endpoints compatible   Facebook   Instruct   Llama   Llama-3   Meta   Quantized   Region:us   Safetensors   Sharded   Tensorflow

Rank the Meta Llama 3 70B Instruct AQLM 2Bit 1x16 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  
Meta Llama 3 70B Instruct AQLM 2Bit 1x16 (ISTA-DASLab/Meta-Llama-3-70B-Instruct-AQLM-2Bit-1x16)

Best Alternatives to Meta Llama 3 70B Instruct AQLM 2Bit 1x16

Best Alternatives
HF Rank
Context/RAM
Downloads
Likes
...B Instruct Gradient 1048K 2bit1024K / 21.9 GB51
...B Instruct Gradient 1048K 4bit1024K / 39.7 GB153
...B Instruct Gradient 1048K 8bit1024K / 75 GB335
...0B Instruct Gradient 262K 2bit256K / 21.9 GB21
...0B Instruct Gradient 262K 4bit256K / 39.7 GB83
...0B Instruct Gradient 262K 8bit256K / 75 GB322
...B Instruct EXL2 4bpw Rpcal 32K32K / 37.2 GB280
...3 70B Instruct 2.25bpw H6 EXL28K / 22.2 GB356
...truct Abliterated Bpw2.25 EXL28K / 22.2 GB51
...ma 3 70B Instruct Bpw2.25 EXL28K / 22.2 GB60

Meta Llama 3 70B Instruct AQLM 2Bit 1x16 Parameters and Internals

LLM NameMeta Llama 3 70B Instruct AQLM 2Bit 1x16
RepositoryOpen on ๐Ÿค— 
Model Size70b
Required VRAM22 GB
Updated2024-05-20
MaintainerISTA-DASLab
Model Typellama
Instruction-BasedYes
Model Files  5.0 GB: 1-of-5   5.0 GB: 2-of-5   5.0 GB: 3-of-5   4.9 GB: 4-of-5   2.1 GB: 5-of-5
Quantization Type2bit
Model ArchitectureLlamaForCausalLM
Context Length8192
Model Max Length8192
Transformers Version4.40.0.dev0
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
Initializer Range0.02
Torch Data Typefloat16

What open-source LLMs or SLMs are you in search of? 34817 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024042801