Post
123
Cheers for a year of sota AI on cpus 🥂 people actually liked my last model, here's another sota for you. This one should feel way different in terms of quality.
appvoid/palmer-005-core
appvoid/palmer-005-core
appvoid
appvoid
AI & ML interests
Working on symbolic models
Recent Activity
updated a dataset 2 days ago
appvoid/rewrite-dpo updated a model 2 days ago
appvoid/palmer-005-coreOrganizations
posted an update 2 days ago
replied to their post 4 days ago
Next release will be above most 1b models while being 1/3 the size
replied to their post 4 days ago
posted an update 5 days ago
Post
117
new model tomorrow, less than 100m params, 1b level on text editing tasks
🤖 palmer is coming back...
🤖 palmer is coming back...
- 1 reply
posted an update about 1 month ago
Post
158
Yesterday someone faked an anthropic account: https://huggingface.co/Anthropic-ai/claude
Be careful... all I'm saying.
Be careful... all I'm saying.
- 1 reply
replied to their post 2 months ago
I guess the reason is slow is because llama.cpp is not optimized...
replied to their post 3 months ago
Correct! It's causal modeling (for now) with a char level tokenizer with only 8 tokens.
The model learns by looking for relationships of sequences for a single token, so the only way it learns is literally nudging weights towards a generalized solution using pure sequences.
In short, it learns to learn.
Will the be any app to.. convert the dots to something meaningful?
Not yet, I'm focusing on getting the core right first. But once the model is general enough, I don't see why not. Though you might need to finetune it for your use case.
replied to their post 3 months ago
Correct! It's causal modeling (for now) with a char level tokenizer with only 8 tokens.
The model learns by looking for relationships of sequences for a single token, so the only way it learns is literally nudging weights towards a generalized solution using pure sequences.
In short, it learns to learn.
posted an update 3 months ago
Post
2519
Let's keep the momentum for small models. I just published dot. It's the first pretrained causal model that is trained on math/symbols rather than english. The goal is to get an agnostic fewshot meta learner that learns from reality itself instead of language.
It's already decent at some tasks, with next version coming in a few weeks.
appvoid/dot
It's already decent at some tasks, with next version coming in a few weeks.
appvoid/dot
- 5 replies
replied to their post 3 months ago
The first model proudly trained from scratch on "physical" reasoning instead of chunky language tokens was published.
posted an update 3 months ago
Post
245
Are you ready for some ●s? Tomorrow will be a good day.
- 4 replies
replied to their post 3 months ago
if you need raw power though slow, rwkv 0.4b has you covered, if you need something in between choose lfm2 350m
posted an update 3 months ago
Post
946
granite-4.0-350m, rwkv7-g1d-0.4b and LFM2-350M are currently the best sub 0.5b models currently for fewshot, simple language tasks
no one is saying this:
if you need the absolute speed + small size + quality, granite 350m is the current king
no one is saying this:
if you need the absolute speed + small size + quality, granite 350m is the current king
- 3 replies
replied to sourceoftruthdata's post 6 months ago
indeed 🤝
reacted to sourceoftruthdata's post with 🤝 6 months ago
Post
3464
What a fantastic community!
- 1 reply
posted an update 7 months ago
Post
331
What's the best model out there below 700m parameters that is good at few shot tasks? I want to test it against arco-3
posted an update 7 months ago
Post
280
Introducing arco-3
The first project, as far as I know, that focuses purely on few-shot prompting results rather than zero-shot like usually done with decoder-only transformer models. This model excels at few-shot tasks compared to most 0.6b and even bigger models. It also outperforms the base model on some popular language modeling benchmarks.
appvoid/arco-3
Try it yourself!
The first project, as far as I know, that focuses purely on few-shot prompting results rather than zero-shot like usually done with decoder-only transformer models. This model excels at few-shot tasks compared to most 0.6b and even bigger models. It also outperforms the base model on some popular language modeling benchmarks.
appvoid/arco-3
Try it yourself!
replied to their post 7 months ago
Do you have your raspberry pis and phones ready for this new model yet?
New model, new architecture, more power:
Since I'm unable to post for about 11 hours, I will post it here: https://huggingface.co/appvoid/arco-3
posted an update 7 months ago
Post
4121
today is going to be a great day for small models, are you ready?
- 3 replies