Tim Bula

timrbula's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

liked 7 models 10 days ago

ibm-granite/granite-3.1-3b-a800m-base

Text Generation • Updated Dec 19, 2024 • 4.55k • 5

ibm-granite/granite-3.1-1b-a400m-instruct

Text Generation • Updated Dec 19, 2024 • 6.22k • 13

ibm-granite/granite-3.1-1b-a400m-base

Text Generation • Updated Dec 19, 2024 • 3.52k • 5

ibm-granite/granite-3.1-8b-base

Text Generation • Updated Dec 19, 2024 • 5.83k • 18

ibm-granite/granite-3.1-2b-instruct

Text Generation • Updated Dec 19, 2024 • 15.5k • 27

ibm-granite/granite-3.1-2b-base

Text Generation • Updated Dec 19, 2024 • 6.35k • 8

ibm-granite/granite-3.1-3b-a800m-instruct

Text Generation • Updated Dec 19, 2024 • 5.53k • 20

updated a model 17 days ago

timrbula/SmolLM2-FT-SmolTalk

Text Generation • Updated 17 days ago • 12

reacted to MoritzLaurer's post with 🔥 17 days ago

view post

Post

1700

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)

See translation

• 
• 

🔥

7

7

❤️

1

1

+

Reply

liked a model 17 days ago

ibm/materials.smi-ted

Feature Extraction • Updated Nov 7, 2024 • 46.8k • 20

liked a model about 1 month ago

ibm-granite/granite-3.1-8b-instruct

Text Generation • Updated Dec 19, 2024 • 63.2k • 126

upvoted a collection 3 months ago

Granite 3.0 Language Models

Collection

A series of language models trained by IBM licensed under Apache 2.0 license. We release both the base pretrained and instruct models. • 8 items • Updated Dec 18, 2024 • 96

liked 8 models 3 months ago

ibm-granite/granite-3.0-3b-a800m-instruct

Text Generation • Updated Dec 19, 2024 • 6.19k • 17

ibm-granite/granite-3.0-3b-a800m-base

Text Generation • Updated Dec 19, 2024 • 2.88k • 5

ibm-granite/granite-3.0-1b-a400m-instruct

Text Generation • Updated Dec 19, 2024 • 716 • 19

ibm-granite/granite-3.0-1b-a400m-base

Text Generation • Updated Dec 19, 2024 • 3.47k • 6

ibm-granite/granite-3.0-8b-instruct

Text Generation • Updated Dec 19, 2024 • 35.5k • 198

ibm-granite/granite-3.0-8b-base

Text Generation • Updated Dec 19, 2024 • 6.31k • 22

ibm-granite/granite-3.0-2b-base

Text Generation • Updated Dec 19, 2024 • 6.24k • 19

ibm-granite/granite-3.0-2b-instruct

Text Generation • Updated Dec 19, 2024 • 16.4k • 47