nvidia/canary-1b-flash
Automatic Speech Recognition
•
0.8B
•
Updated
•
10.1k
•
246
Jaward Sesay
Jaward
AI & ML interests
Building Lectūra Labs | CS Grad Student @BIT | AI/ML Research: Autonomous Agents, LLMs | First Paper (AutoAgents: A Framework for Automatic Agent Generation) Accepted @ IJCAI 2024 | Role Model Karpathy
Recent Activity
liked
a model
3 days ago
nvidia/canary-1b-flash
liked
a model
3 days ago
patmodels/bpm
posted
an
update
6 days ago
It’s absolutely mind blowing - the work Dynamics Lab is doing!!
With just a single input image and in a few seconds, their new world engine model (Mirage 2) can generate a whole new interactive world that’s physics informed and fully explorable in real-time🤯
Try it yourself: https://demo.dynamicslab.ai/chaos
Organizations
liked
2
models
3 days ago
posted
an
update
6 days ago
Post
6878
It’s absolutely mind blowing - the work Dynamics Lab is doing!!
With just a single input image and in a few seconds, their new world engine model (Mirage 2) can generate a whole new interactive world that’s physics informed and fully explorable in real-time🤯
Try it yourself: https://demo.dynamicslab.ai/chaos
With just a single input image and in a few seconds, their new world engine model (Mirage 2) can generate a whole new interactive world that’s physics informed and fully explorable in real-time🤯
Try it yourself: https://demo.dynamicslab.ai/chaos
- 1 reply
upvoted
a
paper
11 days ago
liked
a
model
15 days ago
replied to
their
post
17 days ago
you're welcome, nice work.
upvoted
a
paper
17 days ago
posted
an
update
18 days ago
Post
4178
fascinating read!
staying bullish on search with rl might just help us get rid of hallucination entirely. I really like their approach:
1) <think>on prompt/context && what u know </think>
2) self <search>when u don’t know</search> (iteratively) with no external tool
3) <information>cite sources to support claim(s)</information>
4) <answer>final answer</answer>
their rl training was done cost efficiently too, see code: https://github.com/TsinghuaC3I/SSRL
staying bullish on search with rl might just help us get rid of hallucination entirely. I really like their approach:
1) <think>on prompt/context && what u know </think>
2) self <search>when u don’t know</search> (iteratively) with no external tool
3) <information>cite sources to support claim(s)</information>
4) <answer>final answer</answer>
their rl training was done cost efficiently too, see code: https://github.com/TsinghuaC3I/SSRL
-
- 2 replies
upvoted
2
papers
18 days ago
upvoted
a
paper
21 days ago
upvoted
a
paper
26 days ago
upvoted
a
paper
about 1 month ago
posted
an
update
about 2 months ago
Post
3253
Towards batch sizes too small to meter🎉 beautiful work! And my personal favorite so far - I adore peak performance at small/nano scale. Everyone deserves to run/train AGI locally:) our data, our god model!
They showed that:
- you can train LLMs (upto 1B params) with as low as batch_size=1. This is unconventional given small batch sizes can lead to unstable/spiky training runs.
- you can have a stable train run with just vanilla SGD(stochastic gradient descent), no momentum required🤯
- small batch sizes are more robust to hyperparameters (i.e no worries with initialization)
- smaller batch sizes outperforms (“better per-Flops performance”) larger batch sizes.
“We recommend that practitioners training large models in memory-constrained settings exploit the benefits of small batch sizes rather than trying to emulate the large batch size setting (e.g., through gradient accumulation) typically used in industry.”
I’ve been doing this for ages - my mantra: all my experiments must scale on my 8gb ram m2 before moving to gpu. IOW I love being gpu poor. Checkout my nanoAI algo repo: https://github.com/Jaykef/ai-algorithms, all notebooks run on memory as low as 8gb ram
They showed that:
- you can train LLMs (upto 1B params) with as low as batch_size=1. This is unconventional given small batch sizes can lead to unstable/spiky training runs.
- you can have a stable train run with just vanilla SGD(stochastic gradient descent), no momentum required🤯
- small batch sizes are more robust to hyperparameters (i.e no worries with initialization)
- smaller batch sizes outperforms (“better per-Flops performance”) larger batch sizes.
“We recommend that practitioners training large models in memory-constrained settings exploit the benefits of small batch sizes rather than trying to emulate the large batch size setting (e.g., through gradient accumulation) typically used in industry.”
I’ve been doing this for ages - my mantra: all my experiments must scale on my 8gb ram m2 before moving to gpu. IOW I love being gpu poor. Checkout my nanoAI algo repo: https://github.com/Jaykef/ai-algorithms, all notebooks run on memory as low as 8gb ram
liked
2
models
about 2 months ago
upvoted
a
paper
2 months ago
posted
an
update
2 months ago
Post
2054
I played around with the new RXTX paper (XX^T) and was able to train nanogpt with 4x4 RXTX matmuls in both attention layer and optimizer🤕
It just works (well I had to add some guardrails) but still saves 5% of memory usage:
The Patch:
- Computes attention scores with a 4x4 blockwise RXTX matmuls (no pytorch dot prod)
- Handles arbitrary sequence lengths by padding to the nearest multiple of 4.
- An RXTX variant of shampoo with params reshaped into 4x4 blocks during each optimizer step.
- Uses 5% less ops
Code: https://github.com/Jaykef/ai-algorithms/blob/main/nanogpt-rxtx.ipynb
Paper: https://arxiv.org/pdf/2505.09814
It just works (well I had to add some guardrails) but still saves 5% of memory usage:
The Patch:
- Computes attention scores with a 4x4 blockwise RXTX matmuls (no pytorch dot prod)
- Handles arbitrary sequence lengths by padding to the nearest multiple of 4.
- An RXTX variant of shampoo with params reshaped into 4x4 blocks during each optimizer step.
- Uses 5% less ops
Code: https://github.com/Jaykef/ai-algorithms/blob/main/nanogpt-rxtx.ipynb
Paper: https://arxiv.org/pdf/2505.09814
liked
a
model
2 months ago
posted
an
update
2 months ago
Post
2333
Mind2Web 2 is out - this time featuring eval and benchmark for deep research🔥
Paper: Mind2Web 2: Evaluating Agentic Search with Agent-as-a-Judge (2506.21506)
Project: https://osu-nlp-group.github.io/Mind2Web-2/
Paper: Mind2Web 2: Evaluating Agentic Search with Agent-as-a-Judge (2506.21506)
Project: https://osu-nlp-group.github.io/Mind2Web-2/