Llama 2 70B Hf 2bit G16 S128 HQQ by mobiuslabsgmbh

 ยป  All LLMs  ยป  mobiuslabsgmbh  ยป  Llama 2 70B Hf 2bit G16 S128 HQQ   URL Share it on

  2bit   Autotrain compatible   Llama   Quantized   Region:us

Llama 2 70B Hf 2bit G16 S128 HQQ Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama 2 70B Hf 2bit G16 S128 HQQ (mobiuslabsgmbh/Llama-2-70b-hf-2bit_g16_s128-HQQ)

Llama 2 70B Hf 2bit G16 S128 HQQ Parameters and Internals

Model Type 
text-generation
Use Cases 
Limitations:
Only supports single GPU runtime., Not compatible with HuggingFace's PEFT.
LLM NameLlama 2 70B Hf 2bit G16 S128 HQQ
Repository ๐Ÿค—https://huggingface.co/mobiuslabsgmbh/Llama-2-70b-hf-2bit_g16_s128-HQQ 
Model Size70b
Required VRAM26.9 GB
Updated2025-02-16
Maintainermobiuslabsgmbh
Model Typellama
Model Files  26.9 GB
Quantization Type2bit
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.35.2
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 70B Hf 2bit G16 S128 HQQ

Best Alternatives
Context / RAM
Downloads
Likes
...B Instruct Gradient 1048K 8bit1024K / 75 GB95
...B Instruct Gradient 1048K 4bit1024K / 39.7 GB73
...B Instruct Gradient 1048K 2bit1024K / 21.9 GB102
...0B Instruct Gradient 262K 4bit256K / 39.7 GB123
...0B Instruct Gradient 262K 8bit256K / 75 GB102
...0B Instruct Gradient 262K 2bit256K / 21.9 GB61
... Gradient 262K 2.25bpw H6 EXL2256K / 22.2 GB70
...t Gradient 262K 4.0bpw H6 EXL2256K / 37.2 GB111
...t Gradient 262K 2.4bpw H6 EXL2256K / 23.5 GB90
...t Gradient 262K 3.5bpw H6 EXL2256K / 32.9 GB90
Note: green Score (e.g. "73.2") means that the model is better than mobiuslabsgmbh/Llama-2-70b-hf-2bit_g16_s128-HQQ.

Rank the Llama 2 70B Hf 2bit G16 S128 HQQ 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? 43187 in total.

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