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

Goliath120B EXL2 2 2.64bpw by LavaPlanet

What open-source LLMs or SLMs are you in search of? 18732 in total.

 ยป  All LLMs  ยป  LavaPlanet  ยป  Goliath120B EXL2 2 2.64bpw   URL Share it on

  Autotrain compatible   Endpoints compatible   Exl2   License:llama2   Llama   Quantized   Region:us   Safetensors   Sharded   Tensorflow

Rank the Goliath120B EXL2 2 2.64bpw 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  
Goliath120B EXL2 2 2.64bpw (LavaPlanet/Goliath120B-exl2_2-2.64bpw)

Best Alternatives to Goliath120B EXL2 2 2.64bpw

Best Alternatives
HF Rank
Context/RAM
Downloads
Likes
MegaDolphin 120B GPTQ60.44K / 61.1 GB323
MegaDolphin 120B AWQ60.44K / 63.3 GB161
Miquella 120B 3.0bpw H6 EXL231K / 44.8 GB128
Miquella 120B 4.0bpw H6 EXL231K / 59.4 GB42
Miquella 120B 4.5bpw H6 EXL231K / 66.9 GB60
Miquella 120B 5.0bpw H6 EXL231K / 74.1 GB70
Miquella 120B 8.0bpw H8 EXL231K / 118.1 GB22
Goliath 120B 2.18bpw H6 EXL24K / 33.2 GB26
Goliath 120B 2.4bpw H6 EXL24K / 36 GB11
Goliath120B EXL2 2.64bpw4K / 39.5 GB11
Note: green Score (e.g. "73.2") means that the model is better than LavaPlanet/Goliath120B-exl2_2-2.64bpw.

Goliath120B EXL2 2 2.64bpw Parameters and Internals

LLM NameGoliath120B EXL2 2 2.64bpw
RepositoryOpen on ๐Ÿค— 
Model Size120b
Required VRAM39.5 GB
Updated2024-02-21
MaintainerLavaPlanet
Model Typellama
Model Files  8.6 GB: 1-of-5   8.6 GB: 2-of-5   8.6 GB: 3-of-5   8.5 GB: 4-of-5   5.2 GB: 5-of-5
Quantization Typeexl2
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.35.0
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Initializer Range0.02
Torch Data Typefloat16
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024022003