The TinyLlama project aims to pretrain a 1.1B Llama model on 3 trillion tokens. With some proper optimization, we can achieve this within a span of "just" 90 days using 16 A100-40G GPUs 🚀🚀. The training has started on 2023-09-01.
1M1.9K上下文 2K2.4GB
chageyun.aiDetail.tabOverview
下载
文件
chageyun.aiDetail.tabRankings
评论评分
相关文章
用途
text-generation→
chageyun.aiDetail.sectionCapabilities
chat
chageyun.aiDetail.sectionSpecs
chageyun.ai.deploymentPlatform
huggingface
chageyun.ai.hardwareType
nvidiaamdintelapple_mcpu
chageyun.ai.quantization
fp16bf16
API 站点比价
收录该模型的 AI API 站点定价(每 1M tokens),每组取前 5 家;「最低价」按输入价升序,「评分最高」按站点评分降序;不做汇率换算。