This is awesome. ERNIE seems more powerful than Qwen3.8-27B and Deepseek-v4-Flash, which AFAIK are currently the best base models... it'll be very interesting to experiment with when it hits OpenCode. Base models are also excellent for businesses who run models locally, as they can be trained in various house rules and house styles.
input_sh 30 minutes ago [-]
They're comparing it to Deepseek-v4-Flash, not 4.1 and not the 4.1 1017 update, so essentially two versions behind the latest version of Deepseek Flash.
irthomasthomas 29 minutes ago [-]
Qwen3.8-27B has no base model version in the wild that I can see?
speedping 51 minutes ago [-]
ERNIE feels old, like BERT. They either need a rebrand or fully embrace retro-dawn-of-ML vibes
josh-wrale 2 minutes ago [-]
[delayed]
lofties 13 minutes ago [-]
BERT models are still amazing for what they do. Even the latest JEV/KEV/SEV/BEV/REV/TREV models can't beat a well-trained BERT.
throwaw12 4 minutes ago [-]
do you have examples of open weight BERT models from hugging face which are trained for specific use cases?
NSUserDefaults 49 minutes ago [-]
I'd try DONALD for sure, if I wanted to kill a project.
locknitpicker 3 minutes ago [-]
> I'd try DONALD for sure, if I wanted to kill a project.
The current version is threatening to veto all my prompts.
yehoshuapw 25 minutes ago [-]
Make AI Great Again?
selectodude 23 minutes ago [-]
SI*
throwaw12 3 minutes ago [-]
Trump just realised that he can't use MAGA for Making SI Great Again, probably giving an executive order to reverse SI to AI again, to be able to claim Make AI Great Again
ahoka 31 minutes ago [-]
But they didn't give a DONALD.
roryirvine 43 minutes ago [-]
Am I the only one to feel sad that the name means "Enhanced Representation through kNowledge IntEgration", rather than being a homage to a very famous 1950s random number generator?
For me I see ERNIE as BERT's long time friend and room mate.
How do I look Ernie? ... with your eyes, Bert.
cubefox 10 minutes ago [-]
It's a homage to BERT (Bidirectional Encoder Representations from Transformers), Google's influential 2018 Transformer model that wasn't autoregressive. https://arxiv.org/abs/1810.04805v2
weijiejason119 1 hours ago [-]
anyone tried this? is it good?
spwa4 1 hours ago [-]
It's not instruction finetuned, so no, it's not good to use for anything like coding agents.
haunter 25 minutes ago [-]
OT
dropped is the worst word in this context because it can both
mean ‘released’ or ‘terminated/ended’
Baidu dropped ERNIE 5.5 Flash Base = Baidu released a new version of their software
Baidu dropped ERNIE 5.5 Flash Base = Baidu ended the support of their software
swiftcoder 20 minutes ago [-]
I think in contemporary parlance this sufficiently clear. Nobody thought massdrop was where you went to buy end-of-life products.
17 minutes ago [-]
spwa4 1 hours ago [-]
TLDR: Ernie 5.5 Flash base 280B params 14B active
A chunk better than Deepseek 1017, at half the parameter count, BUT it's only a base model, not finetuned to follow instructions.
Strange to release a model in this state. OpenAI is also "probably" releasing new models (sources within OpenAI talking about Sol 6.2 and the like). We must be getting really close to the Qwen4 releases.
cubefox 9 minutes ago [-]
> Strange to release a model in this state.
No, they explain why they do it.
v9v 53 minutes ago [-]
I believe they compare to DSv4, not DSv4.1 1017.
wolttam 32 minutes ago [-]
Specifically V4-Flash-Base from April.
Rendered at 11:07:08 GMT+0000 (Coordinated Universal Time) with Vercel.
The current version is threatening to veto all my prompts.
https://en.wikipedia.org/wiki/Premium_Bonds#ERNIE
How do I look Ernie? ... with your eyes, Bert.
dropped is the worst word in this context because it can both mean ‘released’ or ‘terminated/ended’
Baidu dropped ERNIE 5.5 Flash Base = Baidu released a new version of their software
Baidu dropped ERNIE 5.5 Flash Base = Baidu ended the support of their software
A chunk better than Deepseek 1017, at half the parameter count, BUT it's only a base model, not finetuned to follow instructions.
Strange to release a model in this state. OpenAI is also "probably" releasing new models (sources within OpenAI talking about Sol 6.2 and the like). We must be getting really close to the Qwen4 releases.
No, they explain why they do it.