Baidu released ERNIE 5.5 Flash Base (ernie.baidu.com)
54 points by pretext 2 hours ago
speedping 2 hours ago
ERNIE feels old, like BERT. They either need a rebrand or fully embrace retro-dawn-of-ML vibes
josh-wrale an hour ago
Bert and Ernie. Ring a bell? Sesame Steeet
lofties an hour 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 an hour ago
do you have examples of open weight BERT models from hugging face which are trained for specific use cases?
NSUserDefaults 2 hours ago
I'd try DONALD for sure, if I wanted to kill a project.
ahoka an hour ago
But they didn't give a DONALD.
yehoshuapw an hour ago
Make AI Great Again?
selectodude an hour ago
locknitpicker an hour ago
> I'd try DONALD for sure, if I wanted to kill a project.
The current version is threatening to veto all my prompts.
rob74 24 minutes ago
A_D_E_P_T 2 hours ago
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 an hour 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.
Tepix 30 minutes ago
DeepSeek 4.1 Flash is twice the size of this and difficult to run locally. Makes more sense to compare it to DS4F.
irthomasthomas an hour ago
Qwen3.8-27B has no base model version in the wild that I can see?
speedgoose 36 minutes ago
Isn’t the latest Qwen 3 public base model… Qwen 3?
Tepix 31 minutes ago
That's an interesting size, it will fit into 2x128GB at decent (≥4bpw) quantization.
roryirvine an hour 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?
jojogeo an hour ago
For me I see ERNIE as BERT's long time friend and room mate.
How do I look Ernie? ... with your eyes, Bert.
cubefox an hour 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 2 hours ago
anyone tried this? is it good?
spwa4 2 hours ago
It's not instruction finetuned, so no, it's not good to use for anything like coding agents.
haunter an hour 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 an hour ago
I think in contemporary parlance this sufficiently clear. Nobody thought massdrop was where you went to buy end-of-life products.
spwa4 2 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.
adrian_b 9 minutes ago
Many others, e.g. Google and NVIDIA, have also released such BASE models.
For those with the knowledge and resources needed to finalize the training, BASE models are much more useful than completely trained models.
BASE models are the next best thing after truly open-source LLMs, where you would have access to the complete dataset used for training. Besides the fact that nobody who had used a really big dataset wants to show it, due to possible legal problems, having access to the original dataset would not be helpful for most people, because they would not be able to use it to make an LLM, due to its huge size and due to the vast resources required for pre-training.
On the other hand, continuing training from a BASE model, which is greatly compressed in comparison with the original dataset, is feasible for many.
cubefox an hour ago
> Strange to release a model in this state.
No, they explain why they do it.
v9v 2 hours ago
I believe they compare to DSv4, not DSv4.1 1017.
wolttam an hour ago
Specifically V4-Flash-Base from April.