LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Meta Llama 3.1 70B Instruct AQLM PV 2Bit 1x16 by ISTA-DASLab

 »  All LLMs  »  ISTA-DASLab  »  Meta Llama 3.1 70B Instruct AQLM PV 2Bit 1x16   URL Share it on

  226   
  Arxiv:2401.06118   Arxiv:2405.14852   2bit   Aqlm   Autotrain compatible Base model:meta-llama/llama-3.... Base model:quantized:meta-llam...   Conversational   Endpoints compatible   Facebook   Instruct   Llama   Llama-3   Meta   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/ISTA-DASLab/Meta-Llama-3.1-70B-Instruct-AQLM-PV-2Bit-1x16 

Meta Llama 3.1 70B Instruct AQLM PV 2Bit 1x16 Benchmarks

LLME Score: 0.26474
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Meta Llama 3.1 70B Instruct AQLM PV 2Bit 1x16 (ISTA-DASLab/Meta-Llama-3.1-70B-Instruct-AQLM-PV-2Bit-1x16)

Meta Llama 3.1 70B Instruct AQLM PV 2Bit 1x16 Parameters and Internals

Model Type 
conversational, text generation
Additional Notes 
Official AQLM quantization, finetuned with PV-Tuning. Used 1 codebook of 16 bits and groupsize of 8.
LLM NameMeta Llama 3.1 70B Instruct AQLM PV 2Bit 1x16
Repository 🤗https://huggingface.co/ISTA-DASLab/Meta-Llama-3.1-70B-Instruct-AQLM-PV-2Bit-1x16 
Base Model(s)  meta-llama/Meta-Llama-3.1-70B-Instruct   meta-llama/Meta-Llama-3.1-70B-Instruct
Model Size70b
Required VRAM22 GB
Updated2024-12-26
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
Licensemeta
Context Length8192
Model Max Length8192
Transformers Version4.40.0.dev0
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
Torch Data Typefloat16

Best Alternatives to Meta Llama 3.1 70B Instruct AQLM PV 2Bit 1x16

Best Alternatives
Context / RAM
Downloads
Likes
...B Instruct Gradient 1048K 8bit1024K / 75 GB155
...B Instruct Gradient 1048K 4bit1024K / 39.7 GB173
...B Instruct Gradient 1048K 2bit1024K / 21.9 GB122
...0B Instruct Gradient 262K 4bit256K / 39.7 GB163
...0B Instruct Gradient 262K 8bit256K / 75 GB82
...0B Instruct Gradient 262K 2bit256K / 21.9 GB161
...t Gradient 262K 4.0bpw H6 EXL2256K / 37.2 GB141
... Gradient 262K 2.25bpw H6 EXL2256K / 22.2 GB100
...t Gradient 262K 2.4bpw H6 EXL2256K / 23.5 GB140
...t Gradient 262K 3.5bpw H6 EXL2256K / 32.9 GB70

Rank the Meta Llama 3.1 70B Instruct AQLM PV 2Bit 1x16 Capabilities

🆘 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! 🌟

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? 40248 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217
  Support LLM Explorer