Smaug Llama 3 70B Instruct GPTQ 8B by cortecs

 ยป  All LLMs  ยป  cortecs  ยป  Smaug Llama 3 70B Instruct GPTQ 8B   URL Share it on

  Arxiv:1910.09700   8-bit   8bit   Autotrain compatible   Conversational   Endpoints compatible   Gptq   Instruct   Llama   Quantized   Region:us

Rank the Smaug Llama 3 70B Instruct GPTQ 8B 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  
Smaug Llama 3 70B Instruct GPTQ 8B (cortecs/Smaug-Llama-3-70B-Instruct-GPTQ-8b)

Best Alternatives to Smaug Llama 3 70B Instruct GPTQ 8B

Best Alternatives
HF Rank
Llama3 TenyxChat 70B78.48K / 141.9 GB352161
Llama 3 70B Instruct DPO V0.178.118K / 141.9 GB5267
Dolphin 2.2 70B70.64K / 138 GB44649
SOLAR 0 70B 16bit70.114K / 138 GB3071253
Meta Llama 3 70B Instruct GPTQ68.38K / 39.8 GB615116
...oLLM Llama3 70B 2.4bpw H6 EXL268.38K / 23.5 GB80
...oLLM Llama3 70B 4.0bpw H6 EXL268.38K / 37.2 GB50
Llama3 70B Instruct 4bit68.38K / 39.7 GB6151
...LLM Llama3 70B 4.65bpw H6 EXL268.38K / 42.7 GB50
...oLLM Llama3 70B 6.0bpw H6 EXL268.38K / 54.4 GB150
Note: green Score (e.g. "73.2") means that the model is better than cortecs/Smaug-Llama-3-70B-Instruct-GPTQ-8b.

Smaug Llama 3 70B Instruct GPTQ 8B Parameters and Internals

LLM NameSmaug Llama 3 70B Instruct GPTQ 8B
RepositoryOpen on ๐Ÿค— 
Base Model(s)  Smaug Llama 3 70B Instruct   abacusai/Smaug-Llama-3-70B-Instruct
Model Size70b
Required VRAM5 GB
Model Typellama
Model Files  10.0 GB: 1-of-8   9.8 GB: 2-of-8   9.9 GB: 3-of-8   9.9 GB: 4-of-8   10.0 GB: 5-of-8   9.9 GB: 6-of-8   9.9 GB: 7-of-8   5.0 GB: 8-of-8
GPTQ QuantizationYes
Quantization Typegptq|8bit
Model ArchitectureLlamaForCausalLM
Context Length8192
Model Max Length8192
Transformers Version4.40.1
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|end_of_text|>
Vocabulary Size128256
Initializer Range0.02
Torch Data Typefloat16

What open-source LLMs or SLMs are you in search of? 34902 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024042801