ModelsOfficial11月6日 10:04

百度开源 ERNIE-5.5-Flash-Base：280B 参数 MoE 基座模型

Baidu Open-Sources ERNIE-5.5-Flash-Base, a 280B MoE Base Model With 14B Active Parameters

官方一手pandaily@[email protected] (Pandaily)

Blog/Media

Read the original

Why we picked it

百度把 ERNIE-5.5-Flash-Base 的预训练检查点直接开源了，280B 参数只激活 14B，想自己微调基座模型的人可以去看看。

百度开源 ERNIE-5.5-Flash-Base，总参数量 280B，激活参数 14B 的 MoE 基座模型。该模型是未经后训练的原始预训练检查点，供开发者做继续训练。训练上下文为 128K，并可支持 100 万 token。

Original · pandaily

Baidu Open-Sources ERNIE-5.5-Flash-Base, a 280B MoE Base Model With 14B Active Parameters

Baidu released ERNIE-5.5-Flash-Base, a raw pretraining checkpoint with 280B total and 14B active parameters, 128K training context and 1M-token support, for further training.

#ERNIE #百度 #开源模型 #MoE

Keep reading

Recent stories with the same tag or section

Models US vs ChinaOfficial06:29

Chinese contentBaidu 发布 ERNIE 5.5 Flash Base：280B 参数 MoE 基座模型

百度把 280B 的 ERNIE 5.5 Flash 基座模型在还没做后训练前就放出来了，想自己微调、做后训练研究的开发者可以拿来玩。

#ERNIE #Baidu #MoE #开源模型

官方一手marktechpost@Michal SutterSource

Models US vs China02:25

Chinese content百度发布开源基座模型 ERNIE 5.5 Flash Base：2800 亿参数 MoE 架构

百度这次放了个 2800 亿参数的开源基座，没做微调就交给你，想怎么调就怎么调，搞微调的朋友可以上手试试。

#ERNIE #百度 #开源模型 #MoE

官方账号Decoder@Matthias BastianSource

Models US vs ChinaMulti-sourceSelected00:37

vLLM ships day-0 support for Baidu's ERNIE 5.5 Flash Base

The benchmark gap over DeepSeek-V4-Flash-Base in the same evaluation setup makes this one of the stronger open base weights released for coding workloads, and day-0 vLLM support means teams can deploy it without custom serving work. Practitioners running RL research or domain adaptation get open base weights plus serving recipes for expert parallelism, KV offload and prefill/decode disaggregation on GB200 and H100 hardware.

#ERNIE 5.5 Flash #Baidu #vLLM #open-source models

Event

官方账号vLLM@vllm_project11 sourcesSource

Models US vs ChinaSelected00:29

Baidu releases ERNIE 5.5 Flash Base with open weights

Releasing a pure pre-training checkpoint lets researchers and engineers run their own mid- and post-training experiments from the same starting point, making method comparisons reproducible. The 1M-token context and FP8 weights make it practical for long-document fine-tuning on a single cluster. Teams benchmarking open base models against Qwen or DeepSeek checkpoints now have a new Baidu entry to include.

#ERNIE #Baidu #open-source models #MoE

官方账号百度 AI Baidu@Baidu_IncSource

Models US vs China21:24

Chinese content百度 ERNIE 5.5 Flash Base 基准测试取得同尺寸 SOTA，超越 DeepSeek-V4-Flash

百度 ERNIE 5.5 Flash Base 评测出炉，同尺寸里跑赢了 DeepSeek-V4-Flash-Base 和 MiMo-V2.5-Base，覆盖数学、代码、长上下文六个维度。

#ERNIE #DeepSeek-V4 #MiMo #推理模型

Event

小互@imxiaohu2 sourcesSource

Models BuildersSelected21:23

Baidu open-sources ERNIE 5.5 Flash Base for continued training

The base-model-only release signals Baidu competing for the fine-tuning and localisation market rather than end users, letting teams inject industry knowledge or adapt regional languages on top of a large pretrained backbone. Developers evaluating against Qwen or DeepSeek open weights get a sparse 5%-activation design that keeps serving costs low at 1M-token contexts. Availability details and licence terms for ASEAN teams remain worth checking before adoption.

#ERNIE #Baidu #open-source models #fine-tuning

小互@imxiaohuSource