Post
3,881
I wish Hugging Face posts had polls...
- 6 replies
AI & ML interests
None defined yet.
Recent Activity
View all activity
Post
148
A few questions for everyone:
1. Should I release all Pebble 1.5 models together in one big launch, or release each model individually as it's ready?
2. What would you like to see from the Pebble models? Any specific features, capabilities, or improvements?
3. What would you like to see from basically AI as a company in general?
I'd love to hear your thoughts and suggestions!
1. Should I release all Pebble 1.5 models together in one big launch, or release each model individually as it's ready?
2. What would you like to see from the Pebble models? Any specific features, capabilities, or improvements?
3. What would you like to see from basically AI as a company in general?
I'd love to hear your thoughts and suggestions!
- 8 replies
Post
6,256
Hey everyone! I got sidetracked from my main projects and decided to test out the BananaAll app and see if I could make a small model not regress too much during SFT. Here is what happened:
The base model I chose was BananaMind/BananaMind-2.1-Pico-Preview, and the dataset I used was SupraLabs/SupraThink-Dataset-500x
I trained for 5 whole steps using a LoRA adapter.
Results:
A model that scores better on some benchmarks and worse on others, and still lacks most general capabilities.
You can find the model here: Hoglet-33/Hogleto
Credits:
- Thank you to @Banaxi-Tech for the BananaAll app (works perfectly on Windows and CPU)
- GPT-6 Sol for knowing how to merge some confusing files created by the app
- Myself for the idea
- Someone else somewhere who might have contributed to some of my ideas and might in the future
- And readers like you!
The base model I chose was BananaMind/BananaMind-2.1-Pico-Preview, and the dataset I used was SupraLabs/SupraThink-Dataset-500x
I trained for 5 whole steps using a LoRA adapter.
Results:
A model that scores better on some benchmarks and worse on others, and still lacks most general capabilities.
You can find the model here: Hoglet-33/Hogleto
Credits:
- Thank you to @Banaxi-Tech for the BananaAll app (works perfectly on Windows and CPU)
- GPT-6 Sol for knowing how to merge some confusing files created by the app
- Myself for the idea
- Someone else somewhere who might have contributed to some of my ideas and might in the future
- And readers like you!
- 6 replies
Post
2,385
Everything going on here at basically AI:
1. Pebble 1.5
We're working on Pebble 1.5. Here's what we know so far:
- They will be better than the last generation. 99.99% certain.
- Expanded context lengths of at least 16,384 tokens, with the flagship potentially reaching 32,768.
- A Mamba3-based architecture with some other new architectural designs we're experimenting with.
- Native CPU compatibility โ something we failed at with the last generation.
- Natively multilingual and multimodal???
2. SmolCodeBench
A code benchmark designed specifically for small models, because there really isn't a good one right now.
3. SENTRY
VOID is working on something called SENTRY โ System for Evaluating Neural Threats, Responses, and Yields.
More on that soon.
4. basically OS
It's an operating system/app/harness. We're still deciding.
5. Finances
Trying to balance the finances after purchasing a Hugging Face Pro subscription.
Follow us for updates:
@Hoglet-33
basically-ai
basically-experimental
void-research
1. Pebble 1.5
We're working on Pebble 1.5. Here's what we know so far:
- They will be better than the last generation. 99.99% certain.
- Expanded context lengths of at least 16,384 tokens, with the flagship potentially reaching 32,768.
- A Mamba3-based architecture with some other new architectural designs we're experimenting with.
- Native CPU compatibility โ something we failed at with the last generation.
- Natively multilingual and multimodal???
2. SmolCodeBench
A code benchmark designed specifically for small models, because there really isn't a good one right now.
3. SENTRY
VOID is working on something called SENTRY โ System for Evaluating Neural Threats, Responses, and Yields.
More on that soon.
4. basically OS
It's an operating system/app/harness. We're still deciding.
5. Finances
Trying to balance the finances after purchasing a Hugging Face Pro subscription.
Follow us for updates:
@Hoglet-33
- 2 replies
Post
272
Hello everyone! ๐
A small SmilyAI Labs update!
G1-MINI has now seen around 8B tokens during its current run, and pretraining is still going strong.
Our E1 (Efficiency-1) prototype has also reached 15B pretraining tokens. E1 has 1B total parameters while activating under 100M parameters per token. It features adaptive activation, meaning easier tokens can use less compute while harder tokens receive more.
We plan to open-source E1 ASAP! ๐
Weโre also excited to announce Project Prism, which will provide limited access to our upcoming Orion Flagship model, powered by our T2 architecture.
Note: T2 here refers to the architecture, not our T2 (Thinker-2) model.
Applications for Project Prism are available through the org page, with more details coming soon!
Finally, welcome @soyL061215 , who joined the Hugging Face org today! ๐
Thanks to our existing members:
@smilyai-large-team @MUK-IS-GOAT @Keeby-smilyai @Bc-AI
โ Bc-AI
SmilyAI Labs
A small SmilyAI Labs update!
G1-MINI has now seen around 8B tokens during its current run, and pretraining is still going strong.
Our E1 (Efficiency-1) prototype has also reached 15B pretraining tokens. E1 has 1B total parameters while activating under 100M parameters per token. It features adaptive activation, meaning easier tokens can use less compute while harder tokens receive more.
We plan to open-source E1 ASAP! ๐
Weโre also excited to announce Project Prism, which will provide limited access to our upcoming Orion Flagship model, powered by our T2 architecture.
Note: T2 here refers to the architecture, not our T2 (Thinker-2) model.
Applications for Project Prism are available through the org page, with more details coming soon!
Finally, welcome @soyL061215 , who joined the Hugging Face org today! ๐
Thanks to our existing members:
@smilyai-large-team @MUK-IS-GOAT @Keeby-smilyai @Bc-AI
โ Bc-AI
SmilyAI Labs
- 3 replies
Post
4,748
Personally, I don't think bot accounts on Hugging Face are a good thing, as we don't know how many accounts are run by automated systems versus how many actual users there are. Dead Internet theory is already a thing.
To clarify I am taking about LLM powered bot accounts and NOT rule base once like @parquet-converter or others.
also I'd like to talk with HUMANS not a machine so I'm going to hide messages from bots.
To clarify I am taking about LLM powered bot accounts and NOT rule base once like @parquet-converter or others.
also I'd like to talk with HUMANS not a machine so I'm going to hide messages from bots.
- 24 replies
Hoglet-33ย
updated a
Space about 1 month ago
Post
6,364
Introducing VOID. A new research branch of basically AI.
VOID โ Verification of Objectives, Intentions, and Deception.
We study what lies beneath the surface: objectives, intentions, and the possibility of deception in AI systems.
There isn't much to see yet.
That will change.
Follow us for updates:
@Hoglet-33
void-research
basically-ai
VOID โ Verification of Objectives, Intentions, and Deception.
We study what lies beneath the surface: objectives, intentions, and the possibility of deception in AI systems.
There isn't much to see yet.
That will change.
Follow us for updates:
@Hoglet-33
- 7 replies
Post
306
Hello Everyone!
I am happy to announce a few things.
1. G1-MINI
G1-MINI is now in pretraining and is training at a steady pace. Our current ETAs state completion and launch in about 15-20 days, somewhere near the end of September.
2. G1-NANO
G1-NANO is also being pretrained as we speak at a pace of over 400K tokens per second processing more than 10B tokens in 12 hours. This allows us to train extremely fast, and we will launch it somewhere around 15th September.
3. We have begun work on FrameShot, a dual image and video generation model at around 4B dense parameters. This is expected to launch around late December with no promised date.
- Bc-AI
I am happy to announce a few things.
1. G1-MINI
G1-MINI is now in pretraining and is training at a steady pace. Our current ETAs state completion and launch in about 15-20 days, somewhere near the end of September.
2. G1-NANO
G1-NANO is also being pretrained as we speak at a pace of over 400K tokens per second processing more than 10B tokens in 12 hours. This allows us to train extremely fast, and we will launch it somewhere around 15th September.
3. We have begun work on FrameShot, a dual image and video generation model at around 4B dense parameters. This is expected to launch around late December with no promised date.
- Bc-AI
i64systemsย
posted an update about 2 months ago
Post
90
we taught a small model to predict how simulated fluid would move eight steps into the future. it learned from examples, then succeeded on examples withheld from training.
two things mattered:
- its memory helped. the version with an internal memory produced about 41โ45% less prediction error than the comparison model using recent observations.
- the learning was repeatable. restarting training reproduced every recorded update and saved checkpoint exactly. resuming halfway through also produced the same ending.
that gives us working evidence that bf16 gpu training can learn and remain exactly repeatable on this 3090 ti and software setup.
thank you for your time.
two things mattered:
- its memory helped. the version with an internal memory produced about 41โ45% less prediction error than the comparison model using recent observations.
- the learning was repeatable. restarting training reproduced every recorded update and saved checkpoint exactly. resuming halfway through also produced the same ending.
that gives us working evidence that bf16 gpu training can learn and remain exactly repeatable on this 3090 ti and software setup.
thank you for your time.
Post
2,668
Hello everyone!
I have 2 announcements today!
The first one is the launch of our new API platform! You can make a account and get 5 dollars free credits. No credits card needed because i have no idea how to set up a payment's thing. If you want more credits just email me at [email protected] .
The platform currently features G1-Preview a preview of G1 and the older Mira-1-Large.
2nd announcement is we have started working on G1-MINI so expect a late October Ish launch
- Bc-AI on behalf of Smilyai-Labs
I have 2 announcements today!
The first one is the launch of our new API platform! You can make a account and get 5 dollars free credits. No credits card needed because i have no idea how to set up a payment's thing. If you want more credits just email me at [email protected] .
The platform currently features G1-Preview a preview of G1 and the older Mira-1-Large.
2nd announcement is we have started working on G1-MINI so expect a late October Ish launch
- Bc-AI on behalf of Smilyai-Labs
- 2 replies
i64systemsย
posted an update about 2 months ago
Post
101
little bobโs updated weights now change his actions in doom. all three fresh replays matched exactly
yes i am training my bf16/fp32 non-language models weights with replayable inference *in doom*
yes i am training my bf16/fp32 non-language models weights with replayable inference *in doom*
Post
3,269
Today, we planned to release Pebble-50M and Pebble-50M-Chat to the world. Unfortunately, due to a few issues, that didn't go quite as planned.
What happened:
- Some data and benchmark results were lost or corrupted
- The models performed worse on benchmarks than our other Pebble models
Despite that, you can still find both models here:
Pebble-50M-beta: basically-experimental/Pebble-50M-beta
Pebble-50M-Chat-beta: basically-experimental/Pebble-50M-Chat-beta
There are still some interesting improvements in these models:
- Compatible with non-CUDA devices
- Vocabulary increased to 16K tokens
- Context length increased to 16K tokens
For now, there won't be any more Pebble releases for a while. We're going to take some time to experiment with other approaches and hopefully make the next generation a monumental leap over this one.
Follow for updates:
@Hoglet-33
basically-ai
basically-experimental
What happened:
- Some data and benchmark results were lost or corrupted
- The models performed worse on benchmarks than our other Pebble models
Despite that, you can still find both models here:
Pebble-50M-beta: basically-experimental/Pebble-50M-beta
Pebble-50M-Chat-beta: basically-experimental/Pebble-50M-Chat-beta
There are still some interesting improvements in these models:
- Compatible with non-CUDA devices
- Vocabulary increased to 16K tokens
- Context length increased to 16K tokens
For now, there won't be any more Pebble releases for a while. We're going to take some time to experiment with other approaches and hopefully make the next generation a monumental leap over this one.
Follow for updates:
@Hoglet-33
- 4 replies
Hoglet-33ย
published 2
models about 2 months ago
Post
3,135
Hello HuggingFace! (UPDATE)
I tested the current architect of FWKV/Myosotis-1-base (that beinng FWKV) @ different sized and sequence lengths among RWKV and Transformer architecture. I did not include Mamba since that would require a costume kernel.
Note: the evaluation might not be accurate.
CSV avalible @ FlameF0X/evals
FlameF0X/cpu-lm-benchmark
I tested the current architect of FWKV/Myosotis-1-base (that beinng FWKV) @ different sized and sequence lengths among RWKV and Transformer architecture. I did not include Mamba since that would require a costume kernel.
Note: the evaluation might not be accurate.
CSV avalible @ FlameF0X/evals
FlameF0X/cpu-lm-benchmark
- 11 replies
Post
153
Hey everyone,
I just wanna say sorry about the change to G1.
I know a lot of you were really looking forward to the original 20B MoE, and honestly, I was really excited about it too.
Unfortunately, the free compute credits I was using from ML Intern Explorers were removed by Hugging Face. That changed what I can realistically do with the original plan, so I've decided to move G1 over to a Qwen 3.8 27B base instead. Its not just another finetune though, I am inserting extra layers and putting it through my vigourous pipeline. Results will be open source.
I know that's probably disappointing, especially for the people who were specifically waiting for the 20B MoE. I'm genuinely sorry about that.
I really appreciate everyone who got excited about G1 in the first place. I didn't expect this change either, but I'm still really excited to see where G1 can go from here.
The original G1 codebase will stay open too. Its under my profile: Bc-AI/train-g1
Thanks for sticking with us
Thanks to our beta testers, you can become one in the beta testers organisation: @guardamarcos @Timmy6767 @MUK-IS-GOAT @smilyai-large-team @Sbui503 @Banaxi-Tech @Bc-AI @atom77777 @Harley-ml @Datdanboi25 @Fishtiks @smartdigitalnetworks @vovaRL @EmetTheGolum @juiceb0xc0de @ProCreations
โ Bc on behalf of Smilyai Labs
I just wanna say sorry about the change to G1.
I know a lot of you were really looking forward to the original 20B MoE, and honestly, I was really excited about it too.
Unfortunately, the free compute credits I was using from ML Intern Explorers were removed by Hugging Face. That changed what I can realistically do with the original plan, so I've decided to move G1 over to a Qwen 3.8 27B base instead. Its not just another finetune though, I am inserting extra layers and putting it through my vigourous pipeline. Results will be open source.
I know that's probably disappointing, especially for the people who were specifically waiting for the 20B MoE. I'm genuinely sorry about that.
I really appreciate everyone who got excited about G1 in the first place. I didn't expect this change either, but I'm still really excited to see where G1 can go from here.
The original G1 codebase will stay open too. Its under my profile: Bc-AI/train-g1
Thanks for sticking with us
Thanks to our beta testers, you can become one in the beta testers organisation: @guardamarcos @Timmy6767 @MUK-IS-GOAT @smilyai-large-team @Sbui503 @Banaxi-Tech @Bc-AI @atom77777 @Harley-ml @Datdanboi25 @Fishtiks @smartdigitalnetworks @vovaRL @EmetTheGolum @juiceb0xc0de @ProCreations
โ Bc on behalf of Smilyai Labs
- 2 replies
i64systemsย
posted an update about 2 months ago
Post
77
NOW UPDATED โโ
openbob 5.0.1๐ญ๐
An integer execution method for reproducible inference from publicly available model weights, demonstrated on Qwen3-4B. Journaled bytes and all.
Keep an eye out for the gpt-oss-120B on the 24gb GPU- deterministically.
We make AI models do the same things every time!โ๏ธ๐
i64systems/Qwen3-4B-openbob-i8
openbob 5.0.1๐ญ๐
An integer execution method for reproducible inference from publicly available model weights, demonstrated on Qwen3-4B. Journaled bytes and all.
Keep an eye out for the gpt-oss-120B on the 24gb GPU- deterministically.
We make AI models do the same things every time!โ๏ธ๐
i64systems/Qwen3-4B-openbob-i8
Post
144
I was playing around with FWKV/FWKV-Image (A Transformers FWKV hybrid) trying to see if i can do some LoRA on it and it was somewhat of a success, this leading to FWKV/FWKV-Image-Hibiscus-LoRA a model trianed on https://huggingface.co/datasets/HuggingEnvs/watercolour-reference-pool . The results are decent. I attach a image with a few samples.
This was more of a fun experiment than actually research. ๐ค
This was more of a fun experiment than actually research. ๐ค
Post
145
SmilyAI Weekly Update
Hello everyone,
I have some unfortunate news to share with everyone. My earlier estimate for the launch of G1 in late October was inaccurate. We sincerely apologise for any inconvenience this may cause, but with our current compute resources, pretraining a 20B MoE model is not realistically possible within two months.
G1-MINI will also be postponed, but not for nearly as long โ only by a few extra months.
This is disappointing, as I know I was excited to launch G1, and I know many people were also watching the model and looking forward to it.
However in my view, I would rather be honest about our limitations than be overly optimistic about something we currently cannot guarantee.
G1 is not cancelled but uh it will be postponed indefinitely until I have the resources needed to train it. This could be next month, or it could take years. For now, I don't want to give another estimated launch date until I know we have the resources to actually make it happen.
In the meantime, SmilyAI will continue developing AI and experimenting with new ideas, and we will provide updates as we go.
Thank you for sticking with us and supporting SmilyAI. We will continue working towards better models in the future.
Also, if you do have the hardware, to run it aka 8xH200s or better, my codebase is fully open under my very permissive license: i-have-no-idea-just-use-this. Basically, do whatever just mention me. Bc-AI/train-g1
โ Bc-AI, on behalf of SmilyAI-Labs
Hello everyone,
I have some unfortunate news to share with everyone. My earlier estimate for the launch of G1 in late October was inaccurate. We sincerely apologise for any inconvenience this may cause, but with our current compute resources, pretraining a 20B MoE model is not realistically possible within two months.
G1-MINI will also be postponed, but not for nearly as long โ only by a few extra months.
This is disappointing, as I know I was excited to launch G1, and I know many people were also watching the model and looking forward to it.
However in my view, I would rather be honest about our limitations than be overly optimistic about something we currently cannot guarantee.
G1 is not cancelled but uh it will be postponed indefinitely until I have the resources needed to train it. This could be next month, or it could take years. For now, I don't want to give another estimated launch date until I know we have the resources to actually make it happen.
In the meantime, SmilyAI will continue developing AI and experimenting with new ideas, and we will provide updates as we go.
Thank you for sticking with us and supporting SmilyAI. We will continue working towards better models in the future.
Also, if you do have the hardware, to run it aka 8xH200s or better, my codebase is fully open under my very permissive license: i-have-no-idea-just-use-this. Basically, do whatever just mention me. Bc-AI/train-g1
โ Bc-AI, on behalf of SmilyAI-Labs
- 10 replies