CyberAgentLM2 is a decoder-only language model pre-trained on the 1.3T tokens of publicly available Japanese and English datasets.
7b
218 Pulls Updated 12 months ago
Updated 12 months ago
12 months ago
b2878b046a70 · 3.5GB
model
archllama
·
parameters7.01B
·
quantizationQ3_K_M
3.5GB
params
{"stop":["\u003c|endoftext|\u003e"]}
36B
Readme
cyberagent-calm2
CyberAgentLM2 is a decoder-only language model pre-trained on the 1.3T tokens of publicly available Japanese and English datasets.
CLI
Instruct:
ollama run cyberagent-calm2:7b-chat
Text completion:
ollama run cyberagent-calm2:7b