Followed BananaMind @Banaxi-Tech . This will be awesome, can’t wait for it! The model I’m training maybe could be added, but again too early to tell since lot of work it needs to be done.
Eric PRO
Dorman11
AI & ML interests
Currently training Endeavor, a SLM model! Interests include: Agentic security, Machine Learning, Reinforcement Learning, PyTorch and all around web dev ninja! Level II Specialist working in Cyber Security field.
Recent Activity
repliedto Banaxi-Tech's post 5 minutes ago
We're exited to announce BananaMind OS, our OS specically for running BananaMind models!
Its able to run BananaMind 2 Nano at 4 bit on only 7-8MB of ram, the 2 bit on 6MB of ram and the 8 bit version on 14MB of RAM!
It runs on a 486 or newer!
Check out this video and image running BananaMind 2 Nano 4 Bit on 9
MB of RAM and a emulated 486 in QEMU at ~1TPS!
We asked it: "What is the first letter of the alphabet?"
The response is:
"The first letter of the alphabet is:
- A.
"
And if you're asking because of the video, yes I am a arch btw.
Comment and like this post for a GitHub link and comment for adding other models! updated a Space about 22 hours ago
Dorman11/endeavor-trainer published a Space about 22 hours ago
Dorman11/endeavor-trainerOrganizations
replied to Banaxi-Tech's post 5 minutes ago
replied to Banaxi-Tech's post 2 days ago
Wow that’s great news! Nice to see the continued development!
reacted to salma-remyx's post with 🚀 2 days ago
Post
1904
Auto mode for coding agents has improved over the last year.
Devs are relying more on them for code review, and less on manual line-by-line checks.
But this leaves coding agents vulnerable to indirect injection attacks.
IssueTrojanBench (arxiv 2607.20759) studies this in the context of malicious issue requests.
I also observed these prompt injection vulnerabilities in my own harness, testing on the issue: https://github.com/smellslikeml/curator/issues/3
But even red teaming your own repos with toy examples like this can trigger AI safeguards and corrupt your session.
Adopting popular mitigation techniques like 'spotlighting' and 'known answer detection' can help but the researchers show it's not enough.
So our latest updates to Outrider implement additional layers for greater defense-in-depth to ensure that by time a human has to review the code, we've filtered this kind noise.
Devs are relying more on them for code review, and less on manual line-by-line checks.
But this leaves coding agents vulnerable to indirect injection attacks.
IssueTrojanBench (arxiv 2607.20759) studies this in the context of malicious issue requests.
I also observed these prompt injection vulnerabilities in my own harness, testing on the issue: https://github.com/smellslikeml/curator/issues/3
But even red teaming your own repos with toy examples like this can trigger AI safeguards and corrupt your session.
Adopting popular mitigation techniques like 'spotlighting' and 'known answer detection' can help but the researchers show it's not enough.
So our latest updates to Outrider implement additional layers for greater defense-in-depth to ensure that by time a human has to review the code, we've filtered this kind noise.
- 2 replies
reacted to maglun's post with 🚀 4 days ago
Post
1157
I work on quantizing models to run efficiently on local hardware, and kept being curious how existing quants spend their "bit budget" during optimization and built a local tool to explore. Many quants apply one setting across all tensors, but some do more interesting things: the model in the screenshot holds attention K at 4.5 bits while Q/V/O get 8.5, and protects layer 0 MLP.
It turned out useful enough that I made it public: https://tensorlens.dev
Explore any HF model in the browser without downloading it. The anatomy map is read from the safetensors header via a range request, and only tensors you click ever stream. Large tensors are sampled rather than streamed in full.
Limitations: safetensors only (no GGUF yet), some exotic variants don't work yet, and gated repos aren't supported yet.
Feedback very welcome, especially models that break it.
It turned out useful enough that I made it public: https://tensorlens.dev
Explore any HF model in the browser without downloading it. The anatomy map is read from the safetensors header via a range request, and only tensors you click ever stream. Large tensors are sampled rather than streamed in full.
Limitations: safetensors only (no GGUF yet), some exotic variants don't work yet, and gated repos aren't supported yet.
Feedback very welcome, especially models that break it.
- 5 replies
This a great to use! I checked Kimi-K3 with it. Very nice man!
reacted to KlondikeDev's post with 🔥 4 days ago
Post
2138
Boris-2 coming soon!
The Models:
Boris-2-75M: Trained on 26B tokens -- estimated to start training on August 12th.
Boris-2-125M: Trained on 90B tokens -- Estimated to start training on August 20th.
Boris-2-250M: Trained on 60B tokens -- Estimated to start training on September 10th.
Why does 125M get more tokens than 250M?
Well, the straight answer is time. It saves time, while still allowing the 250M model to exceed the 125M model.
Furthermore, we are attempting a unique architecture and layering scheme to hopefully end up around the strength of SmolLM2-135M. Fingers crossed!
We hope to end up in the ballpark of AxiomicLabs/GPT-X2.5-135M or BananaMind/BananaMind-2-Pro-Preview
Following this, we will release the Pro, Instruct and Pro-Instruct variants. More info will be coming soon!
The Models:
Boris-2-75M: Trained on 26B tokens -- estimated to start training on August 12th.
Boris-2-125M: Trained on 90B tokens -- Estimated to start training on August 20th.
Boris-2-250M: Trained on 60B tokens -- Estimated to start training on September 10th.
Why does 125M get more tokens than 250M?
Well, the straight answer is time. It saves time, while still allowing the 250M model to exceed the 125M model.
Furthermore, we are attempting a unique architecture and layering scheme to hopefully end up around the strength of SmolLM2-135M. Fingers crossed!
We hope to end up in the ballpark of AxiomicLabs/GPT-X2.5-135M or BananaMind/BananaMind-2-Pro-Preview
Following this, we will release the Pro, Instruct and Pro-Instruct variants. More info will be coming soon!
- 4 replies
reacted to dddyym's post with 🔥 4 days ago
Post
1926
Released mlquantx 0.2.6: a reproducible PyTorch workflow for cross-sectional multi-factor research.
pip install --upgrade mlquantx
mlquant demo
The demo runs synthetic data → 213 factors → MLP → portfolio construction → cost-aware backtest. CI covers Python 3.9–3.11 with 96 tests.
Dataset: dddyym/ml-quant-trading-synthetic
Checkpoint: dddyym/ml-quant-trading-synthetic-mlp
GitHub: https://github.com/initial-d/ml-quant-trading
PyPI: https://pypi.org/project/mlquantx/
Research and teaching use only — not a live-trading system or a profitability claim.
pip install --upgrade mlquantx
mlquant demo
The demo runs synthetic data → 213 factors → MLP → portfolio construction → cost-aware backtest. CI covers Python 3.9–3.11 with 96 tests.
Dataset: dddyym/ml-quant-trading-synthetic
Checkpoint: dddyym/ml-quant-trading-synthetic-mlp
GitHub: https://github.com/initial-d/ml-quant-trading
PyPI: https://pypi.org/project/mlquantx/
Research and teaching use only — not a live-trading system or a profitability claim.
posted an update 4 days ago
Post
122
I've been thinking this for a long time, other than OpenMythos will we see similar type of open source models be released? The more and more top frontier models get good at finding zero day vulnerabilities and security weaknesses how will the open source model community respond. My take is we will see a open source model very soon be as good at finding security holes as the top models, at some point in the future. Is it just me or anyone seeing this?
replied to Banaxi-Tech's post 5 days ago
BananaOS I assume could run other small models aside from BananaMind models? I’m training a small model and was just curious…either way this is a really cool idea!
A simple text generation model. Would be cool to build a coding model, but that’s a challenge in and of itself.
Yeah and I’m new making models so happy to find a community! I can learn a lot here!
I've seen this wave as well and it's great to see!
reacted to appvoid's post with 🔥 5 days ago
Post
2363
I don't know if it was us or one of you guys or maybe all of us at once but lately we have seen a finetuning/pretraining explosion of models below 200m params and we can't be more happy about it keep coming tinkerers all of this is possible because of you!
- 8 replies
Sounds good! Thanks!
Yeah precisely. XD
reacted to Banaxi-Tech's post with 🔥 5 days ago
Post
1941
We're exited to announce BananaMind OS, our OS specically for running BananaMind models!
Its able to run BananaMind 2 Nano at 4 bit on only 7-8MB of ram, the 2 bit on 6MB of ram and the 8 bit version on 14MB of RAM!
It runs on a 486 or newer!
Check out this video and image running BananaMind 2 Nano 4 Bit on 9
MB of RAM and a emulated 486 in QEMU at ~1TPS!
We asked it: "What is the first letter of the alphabet?"
The response is:
"The first letter of the alphabet is:
- A.
"
And if you're asking because of the video, yes I am a arch btw.
Comment and like this post for a GitHub link and comment for adding other models!
Its able to run BananaMind 2 Nano at 4 bit on only 7-8MB of ram, the 2 bit on 6MB of ram and the 8 bit version on 14MB of RAM!
It runs on a 486 or newer!
Check out this video and image running BananaMind 2 Nano 4 Bit on 9
MB of RAM and a emulated 486 in QEMU at ~1TPS!
We asked it: "What is the first letter of the alphabet?"
The response is:
"The first letter of the alphabet is:
- A.
"
And if you're asking because of the video, yes I am a arch btw.
Comment and like this post for a GitHub link and comment for adding other models!
- 25 replies
Well I have added the dataset to a bucket so this will be fun to use! Super interesting dataset and yeah wonder which newer models I could choose to use.
Oh this is super interesting and a great idea! I voted on some of them! An open-weights GPTZero alternative would be really cool to see.
Hey guys, I'm new to HuggingFace at least when it comes to interacting with the communty. I really like when I see these independent models and some really cool small models, especially AxiomicLabs/GPT-S-5M.