huggyllama/llama-65b
Text Generation
•
65B
•
Updated
•
1.18k
•
77
"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 • 5.96k • • 853 -
meta-llama/Meta-Llama-3-70B
Text Generation • 71B • Updated • 492k • • 871 -
meta-llama/Llama-3.1-70B
Text Generation • 71B • Updated • 38.5k • 396 -
mistralai/Mixtral-8x22B-v0.1
141B • Updated • 2.63k • 234 -
mistralai/Mistral-Small-24B-Base-2501
24B • Updated • 2.89k • 259 -
deepseek-ai/DeepSeek-V2
Text Generation • 236B • Updated • 3.81k • 330 -
deepseek-ai/DeepSeek-V3-Base
685B • Updated • 19.9k • 1.68k -
deepseek-ai/DeepSeek-V3.1-Base
Text Generation • 685B • Updated • 13.4k • 1.01k -
tiiuae/falcon-180B
Text Generation • 180B • Updated • 306 • 1.15k -
xai-org/grok-1
Text Generation • Updated • 733 • 2.38k -
zai-org/GLM-4-32B-Base-0414
Text Generation • 33B • Updated • 1.35k • • 34 -
LLM360/K2
Text Generation • 65B • Updated • 576 • 97