mistralai/Mistral-Small-24B-Base-2501
Text Generation
•
Updated
•
3.08k
•
189
Tim Bula
timrbula
AI & ML interests
LLMs for language and code
Recent Activity
liked
a model
5 days ago
mistralai/Mistral-Small-24B-Base-2501
reacted
to
singhsidhukuldeep's
post
with ❤️
8 days ago
It's not every day you see a research paper named "Alice's Adventures in a Differentiable Wonderland," and when you open it, it's a 281-page book!
I haven't completed it yet, but this amazing work, written by Simone Scardapane, is a fascinating introduction to deep neural networks and differentiable programming.
Some key technical highlights:
• Covers core concepts like automatic differentiation, stochastic optimization, and activation functions in depth
• Explains modern architectures like convolutional networks, transformers, and graph neural networks
• Provides mathematical foundations including linear algebra, gradients, and probability theory
• Discusses implementation details in PyTorch and JAX
• Explores advanced topics like Bayesian neural networks and neural scaling laws
The book takes a unique approach, framing neural networks as compositions of differentiable primitives rather than biological analogs. It provides both theoretical insights and practical coding examples.
I especially enjoyed the sections on:
• Vector-Jacobian products and reverse-mode autodiff
• Stochastic gradient descent and mini-batch optimization
• ReLU, GELU, and other modern activation functions
• Universal approximation capabilities of MLPs
Whether you're new to deep learning or an experienced practitioner, this book offers valuable insights into the fundamentals and latest developments. Highly recommended for anyone working with neural networks!
liked
a model
19 days ago
ibm-granite/granite-3.1-3b-a800m-base
Organizations
timrbula's activity
liked
a
model
5 days ago
reacted to
singhsidhukuldeep's
post with ❤️
8 days ago
Post
2199
It's not every day you see a research paper named "Alice's Adventures in a Differentiable Wonderland," and when you open it, it's a 281-page book!
I haven't completed it yet, but this amazing work, written by Simone Scardapane, is a fascinating introduction to deep neural networks and differentiable programming.
Some key technical highlights:
• Covers core concepts like automatic differentiation, stochastic optimization, and activation functions in depth
• Explains modern architectures like convolutional networks, transformers, and graph neural networks
• Provides mathematical foundations including linear algebra, gradients, and probability theory
• Discusses implementation details in PyTorch and JAX
• Explores advanced topics like Bayesian neural networks and neural scaling laws
The book takes a unique approach, framing neural networks as compositions of differentiable primitives rather than biological analogs. It provides both theoretical insights and practical coding examples.
I especially enjoyed the sections on:
• Vector-Jacobian products and reverse-mode autodiff
• Stochastic gradient descent and mini-batch optimization
• ReLU, GELU, and other modern activation functions
• Universal approximation capabilities of MLPs
Whether you're new to deep learning or an experienced practitioner, this book offers valuable insights into the fundamentals and latest developments. Highly recommended for anyone working with neural networks!
I haven't completed it yet, but this amazing work, written by Simone Scardapane, is a fascinating introduction to deep neural networks and differentiable programming.
Some key technical highlights:
• Covers core concepts like automatic differentiation, stochastic optimization, and activation functions in depth
• Explains modern architectures like convolutional networks, transformers, and graph neural networks
• Provides mathematical foundations including linear algebra, gradients, and probability theory
• Discusses implementation details in PyTorch and JAX
• Explores advanced topics like Bayesian neural networks and neural scaling laws
The book takes a unique approach, framing neural networks as compositions of differentiable primitives rather than biological analogs. It provides both theoretical insights and practical coding examples.
I especially enjoyed the sections on:
• Vector-Jacobian products and reverse-mode autodiff
• Stochastic gradient descent and mini-batch optimization
• ReLU, GELU, and other modern activation functions
• Universal approximation capabilities of MLPs
Whether you're new to deep learning or an experienced practitioner, this book offers valuable insights into the fundamentals and latest developments. Highly recommended for anyone working with neural networks!
liked
7
models
19 days ago
ibm-granite/granite-3.1-3b-a800m-base
Text Generation
•
Updated
•
4.87k
•
5
ibm-granite/granite-3.1-1b-a400m-instruct
Text Generation
•
Updated
•
6.27k
•
13
ibm-granite/granite-3.1-1b-a400m-base
Text Generation
•
Updated
•
3.71k
•
5
ibm-granite/granite-3.1-8b-base
Text Generation
•
Updated
•
7.27k
•
20
ibm-granite/granite-3.1-2b-instruct
Text Generation
•
Updated
•
17.9k
•
31
ibm-granite/granite-3.1-2b-base
Text Generation
•
Updated
•
7.33k
•
10
ibm-granite/granite-3.1-3b-a800m-instruct
Text Generation
•
Updated
•
21k
•
20
updated
a
model
26 days ago
reacted to
MoritzLaurer's
post with 🔥
27 days ago
Post
1708
The TRL v0.13 release is 🔥! My highlight are the new process reward trainer to train models similar to o1 and tool call support:
🧠 Process reward trainer: Enables training of Process-supervised Reward Models (PRMs), which reward the quality of intermediate steps, promoting structured reasoning. Perfect for tasks like stepwise reasoning.
🔀 Model merging: A new callback leverages mergekit to merge models during training, improving performance by blending reference and policy models - optionally pushing merged models to the Hugging Face Hub.
🛠️ Tool call support: TRL preprocessing now supports tool integration, laying the groundwork for agent fine-tuning with examples like dynamic temperature fetching in prompts.
⚖️ Mixture of judges: The new AllTrueJudge combines decisions from multiple binary judges for more nuanced evaluation.
Read the release notes and other resources here 👇
Release: https://github.com/huggingface/trl/releases/tag/v0.13.0
Mergekit: https://github.com/arcee-ai/mergekit
Mixture of judges paper: The Perfect Blend: Redefining RLHF with Mixture of Judges (2409.20370)
🧠 Process reward trainer: Enables training of Process-supervised Reward Models (PRMs), which reward the quality of intermediate steps, promoting structured reasoning. Perfect for tasks like stepwise reasoning.
🔀 Model merging: A new callback leverages mergekit to merge models during training, improving performance by blending reference and policy models - optionally pushing merged models to the Hugging Face Hub.
🛠️ Tool call support: TRL preprocessing now supports tool integration, laying the groundwork for agent fine-tuning with examples like dynamic temperature fetching in prompts.
⚖️ Mixture of judges: The new AllTrueJudge combines decisions from multiple binary judges for more nuanced evaluation.
Read the release notes and other resources here 👇
Release: https://github.com/huggingface/trl/releases/tag/v0.13.0
Mergekit: https://github.com/arcee-ai/mergekit
Mixture of judges paper: The Perfect Blend: Redefining RLHF with Mixture of Judges (2409.20370)
liked
a
model
27 days ago
liked
a
model
about 2 months ago
upvoted
a
collection
4 months ago
liked
6
models
4 months ago
ibm-granite/granite-3.0-3b-a800m-instruct
Text Generation
•
Updated
•
6.32k
•
17
ibm-granite/granite-3.0-3b-a800m-base
Text Generation
•
Updated
•
3.57k
•
5
ibm-granite/granite-3.0-1b-a400m-instruct
Text Generation
•
Updated
•
798
•
19
ibm-granite/granite-3.0-1b-a400m-base
Text Generation
•
Updated
•
3.65k
•
6
ibm-granite/granite-3.0-8b-instruct
Text Generation
•
Updated
•
34k
•
199
ibm-granite/granite-3.0-8b-base
Text Generation
•
Updated
•
6.58k
•
22