LLM Explorer: A Curated Large Language Model Directory and Analytics  // 

Sheep Duck Llama 2 70B V1.1 GPTQ by TheBloke

What open-source LLMs or SLMs are you in search of? 18857 in total.

 ยป  All LLMs  ยป  TheBloke  ยป  Sheep Duck Llama 2 70B V1.1 GPTQ   URL Share it on

  4-bit   Autotrain compatible Base model:riiid/sheep-duck-ll...   Gptq   License:llama2   Llama   Quantized   Region:us   Safetensors

Sheep Duck Llama 2 70B V1.1 GPTQ Benchmarks

Rank the Sheep Duck Llama 2 70B V1.1 GPTQ 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  
Sheep Duck Llama 2 70B V1.1 GPTQ (TheBloke/sheep-duck-llama-2-70B-v1.1-GPTQ)

Best Alternatives to Sheep Duck Llama 2 70B V1.1 GPTQ

Best Alternatives
HF Rank
XuanYuan 70B79.558K / 138.3 GB84242
Tigerbot 70B Chat V277.924K / 139.2 GB3249
QuartetAnemoi 70B T0.000176.8631K / 137.8 GB50918
Miqu 70B Alpaca DPO76.631K / 138.7 GB6455
BoreanGale 70B76.4832K / 137.8 GB9074
Tigerbot 70B Chat V475.954K / 139.2 GB8361
OrcaHermes Mistral 70B Miqu75.5131K / 138 GB671
Senku 70B Full75.3631K / 138.7 GB1677111
Tulu 2 DPO 70B73.778K / 138 GB3817137
Aurora Nights 70B V1.073.774K / 137.8 GB181415
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/sheep-duck-llama-2-70B-v1.1-GPTQ.

Sheep Duck Llama 2 70B V1.1 GPTQ Parameters and Internals

LLM NameSheep Duck Llama 2 70B V1.1 GPTQ
RepositoryOpen on ๐Ÿค— 
Model NameSheep Duck Llama 2 70B v1.1
Model CreatorRiiid
Base Model(s)  Sheep Duck Llama 2 70B V1.1   Riiid/sheep-duck-llama-2-70b-v1.1
Model Size70b
Required VRAM35.3 GB
Model Typellama
Model Files  35.3 GB
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureLlamaForCausalLM
Context Length4096
Model Max Length4096
Transformers Version4.34.0.dev0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Initializer Range0.02
Torch Data Typefloat16
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024022003