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

Llama 2 7B AQLM PV 1Bit 1x16 Hf by ISTA-DASLab

 »  All LLMs  »  ISTA-DASLab  »  Llama 2 7B AQLM PV 1Bit 1x16 Hf   URL Share it on

  166   
  Arxiv:2401.06118   Arxiv:2405.14852   1bit   Aqlm   Autotrain compatible   Conversational   Endpoints compatible   Facebook   Llama   Llama2   Meta   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/ISTA-DASLab/Llama-2-7b-AQLM-PV-1Bit-1x16-hf 

Llama 2 7B AQLM PV 1Bit 1x16 Hf Benchmarks

LLME Score: 0.19538
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama 2 7B AQLM PV 1Bit 1x16 Hf (ISTA-DASLab/Llama-2-7b-AQLM-PV-1Bit-1x16-hf)

Llama 2 7B AQLM PV 1Bit 1x16 Hf Parameters and Internals

Model Type 
conversational, text-generation-inference
Additional Notes 
Official quantization using PV-Tuning on AQLM, with 1x16g16 scheme resulting in 1.58 bits per weight.
LLM NameLlama 2 7B AQLM PV 1Bit 1x16 Hf
Repository 🤗https://huggingface.co/ISTA-DASLab/Llama-2-7b-AQLM-PV-1Bit-1x16-hf 
Model Size7b
Required VRAM1.8 GB
Updated2025-02-22
MaintainerISTA-DASLab
Model Typellama
Model Files  1.8 GB
Quantization Type1bit
Model ArchitectureLlamaForCausalLM
Context Length4096
Model Max Length4096
Transformers Version4.40.1
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Llama 2 7B AQLM PV 1Bit 1x16 Hf

Best Alternatives
Context / RAM
Downloads
Likes
Smaugv0.1 6.0bpw H6 EXL2195K / 26.4 GB94
Smaugv0.1 5.0bpw H6 EXL2195K / 22.3 GB63
Smaugv0.1 4.65bpw H6 EXL2195K / 20.8 GB71
Smaugv0.1 3.0bpw H6 EXL2195K / 13.9 GB51
Smaugv0.1 4.0bpw H6 EXL2195K / 18 GB41
Smaugv0.1 8.0bpw H8 EXL2195K / 34.9 GB41
Mistral 7B Openplatypus 1K32K / 29 GB18650
Mistral 7B OpenOrca 1K32K / 29 GB18663
Mistral 7B A U0.5 B2 Ver0.432K / 14.4 GB20150
Mistral 7B OP U1k Ver0.632K / 14.4 GB20120

Rank the Llama 2 7B AQLM PV 1Bit 1x16 Hf 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? 43470 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 v20241227
  Support LLM Explorer