Anthony Mikinka

anthonymikinka's activity

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

liked a Space 21 days ago

Running on CPU Upgrade

828

828

Computer Agent

🖥

Interact with an agent to perform web-based tasks

liked a model 27 days ago

nvidia/OpenCodeReasoning-Nemotron-32B

Text Generation • Updated 27 days ago • 1.67k • 67

liked a model about 2 months ago

microsoft/MAI-DS-R1

Text Generation • Updated 28 days ago • 1.01k • 271

liked 4 models 2 months ago

Locutusque/TinyMistral-248M

Text Generation • Updated May 9, 2024 • 1.24k • 48

deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B

Text Generation • Updated Feb 24 • 1.28M • • 1.21k

open-r1/OlympicCoder-7B

Text Generation • Updated Mar 17 • 816 • 172

anthonymikinka/gpt2_coreml_kv_cache_try1

Text Generation • Updated Dec 18, 2024 • 2

updated a model 2 months ago

anthonymikinka/DeepSeek-R1-Distill-Llama-8B-Stateful-CoreML

Text Generation • Updated Mar 24 • 5 • 3

liked a model 2 months ago

seba/qwen-2-coreml-ane

Text Generation • Updated Sep 10, 2024 • 2

upvoted an article 2 months ago

view article

Article

Open R1: Update #3

By and 9 others •

Mar 11

• 291

upvoted a collection 2 months ago

👩‍💻 OlympicCoder

Collection

Reasoning datasets and models for competitive coding • 4 items • Updated 21 days ago • 17

liked a model 2 months ago

anthonymikinka/DeepSeek-R1-Distill-Llama-8B-Stateful-CoreML

Text Generation • Updated Mar 24 • 5 • 3

upvoted an article 3 months ago

view article

Article

Introducing smolagents: simple agents that write actions in code.

By and 2 others •

Dec 31, 2024

• 1.06k

published a model 3 months ago

anthonymikinka/DeepSeek-R1-Distill-Llama-8B-Stateful-CoreML

Text Generation • Updated Mar 24 • 5 • 3

liked 2 models 3 months ago

deepseek-ai/DeepSeek-R1-Distill-Llama-8B

Text Generation • Updated Feb 24 • 1.29M • • 736

peakji/steiner-32b-preview

Updated Oct 21, 2024 • 7 • 92

reacted to Jaward's post with 🔥 3 months ago

view post

Post

2593

Lightweight (nanoGPT) implementation of hybrid norm - an intuitive normalization method that combines the strength of both pre-norm (i.e QKV-norm in MHA) and post-norm in the feed-forward network.
Code: https://github.com/Jaykef/ai-algorithms/blob/main/hybrid_normalization.ipynb

See translation

• 
• 

👀

5

5

🔥

3

3

+

Reply

liked a model 3 months ago

mlx-community/UI-TARS-72B-DPO-bf16

Image-Text-to-Text • Updated Mar 6 • 13 • 1

liked a Space 3 months ago

Running

83

83

Find a leaderboard

🔍

Explore and discover all leaderboards from the HF community

upvoted a collection 3 months ago

DiffRhythm

Collection

5 items • Updated 27 days ago • 15