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 13B AQLM PV 2Bit 1x16 Hf by ISTA-DASLab

 »  All LLMs  »  ISTA-DASLab  »  Llama 2 13B AQLM PV 2Bit 1x16 Hf   URL Share it on

  11   
  Arxiv:2401.06118   Arxiv:2405.14852   2bit   Aqlm   Autotrain compatible   Conversational   Endpoints compatible   Facebook   Llama   Llama2   Meta   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/ISTA-DASLab/Llama-2-13b-AQLM-PV-2Bit-1x16-hf 

Llama 2 13B AQLM PV 2Bit 1x16 Hf Benchmarks

LLME Score: 0.18867
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama 2 13B AQLM PV 2Bit 1x16 Hf (ISTA-DASLab/Llama-2-13b-AQLM-PV-2Bit-1x16-hf)

Llama 2 13B AQLM PV 2Bit 1x16 Hf Parameters and Internals

Model Type 
conversational, text-generation, inference
Additional Notes 
An official quantization using PV-Tuning on top of AQLM. Used 1 codebook of 16 bits for groups of 8 weights.
LLM NameLlama 2 13B AQLM PV 2Bit 1x16 Hf
Repository 🤗https://huggingface.co/ISTA-DASLab/Llama-2-13b-AQLM-PV-2Bit-1x16-hf 
Model Size13b
Required VRAM4.1 GB
Updated2025-02-22
MaintainerISTA-DASLab
Model Typellama
Model Files  4.1 GB
Quantization Type2bit
Model ArchitectureLlamaForCausalLM
Context Length4096
Model Max Length4096
Transformers Version4.39.3
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 13B AQLM PV 2Bit 1x16 Hf

Best Alternatives
Context / RAM
Downloads
Likes
Llama13b 32K Illumeet Finetune32K / 26 GB120
...Maid V3 13B 32K 8.0bpw H8 EXL232K / 13.2 GB121
...Maid V3 13B 32K 6.0bpw H6 EXL232K / 10 GB91
WhiteRabbitNeo 13B V116K / 26 GB3589411
CodeLlama 13B Python Fp1616K / 26 GB346725
CodeLlama 13B Instruct Fp1616K / 26 GB348428
CodeLlama 13B Fp1616K / 26 GB23766
Codellama 13B Bnb 4bit16K / 7.2 GB1092
...Llama 13B Instruct Hf 4bit MLX16K / 7.8 GB1002
Airophin 13B Pntk 16K Fp1616K / 26 GB17634
Note: green Score (e.g. "73.2") means that the model is better than ISTA-DASLab/Llama-2-13b-AQLM-PV-2Bit-1x16-hf.

Rank the Llama 2 13B AQLM PV 2Bit 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