huggyllama/llama-65b
Text Generation • 65B • Updated • 722 • 78
"True" Base Models
LLMs which have relatively flat distribution of tokens, see https://huggingface.co/blog/ChuckMcSneed/name-diversity-in-llms-experiment
-
-
meta-llama/Llama-2-70b-hf
Text Generation • 69B • Updated • 9.86k • 854 -
meta-llama/Meta-Llama-3-70B
Text Generation • 71B • Updated • 216k • 877 -
meta-llama/Llama-3.1-70B
Text Generation • 71B • Updated • 79.1k • 423 -
mistralai/Mixtral-8x22B-v0.1
141B • Updated • 5.28k • 239 -
mistralai/Mistral-Small-24B-Base-2501
24B • Updated • 4.34k • 262 -
deepseek-ai/DeepSeek-V2
Text Generation • 236B • Updated • 5.24k • 334 -
deepseek-ai/DeepSeek-V3-Base
685B • Updated • 6.36k • 1.7k -
deepseek-ai/DeepSeek-V3.1-Base
Text Generation • 685B • Updated • 9.35k • 1.01k -
tiiuae/falcon-180B
Text Generation • 180B • Updated • 120 • 1.15k -
xai-org/grok-1
Text Generation • Updated • 204 • 2.42k -
zai-org/GLM-4-32B-Base-0414
Text Generation • 33B • Updated • 94 • • 37 -
LLM360/K2
Text Generation • 65B • Updated • 185 • 99