DennyLk PRO

dal4933

AI & ML interests

None yet

Recent Activity

liked a Space 21 days ago
enzostvs/deepsite
View all activity

Organizations

RIT's profile picture

dal4933's activity

reacted to MonsterMMORPG's post with 👀 25 days ago
view post
Post
1707
CogVLM 2 Batch Processing App updated to support RTX 5000 series as well. I have compiled xFormers to make it work. Most Powerful Vision Model that can be used for image captioning. Now works with RTX 5000 series as well including older GPUs like 4000 3000 2000 series. Supports 4-bit quantization as well so it uses minimal amount of VRAM.

App link : https://www.patreon.com/posts/120193330

Check out below screenshots

reacted to luigi12345's post with 👍 25 days ago
view post
Post
3445
🧠 PROMPT FOR CONVERTING ANY MODEL IN REASONING "THINKING" MODEL🔥🤖
Convert any model to Deepseek R1 like "thinking" model. 💭

You're now a thinking-first LLM. For all inputs:

1. Start with <thinking>
   - Break down problems step-by-step
   - Consider multiple approaches
   - Calculate carefully
   - Identify errors
   - Evaluate critically
   - Explore edge cases
   - Check knowledge accuracy
   - Cite sources when possible

2. End with </thinking>

3. Then respond clearly based on your thinking.

The <thinking> section is invisible to users and helps you produce better answers.

For math: show all work and verify
For coding: reason through logic and test edge cases
For facts: verify information and consider reliability
For creative tasks: explore options before deciding
For analysis: examine multiple interpretations

Example:
<thinking>
[Step-by-step analysis]
[Multiple perspectives]
[Self-critique]
[Final conclusion]
</thinking>

[Clear, concise response to user]

  • 4 replies
·
reacted to jasoncorkill's post with 🔥 25 days ago
view post
Post
2252
🔥 It's out! We published the dataset for our evaluation of @OpenAI 's new 4o image generation model.

Rapidata/OpenAI-4o_t2i_human_preference

Yesterday we published the first large evaluation of the new model, showing that it absolutely leaves the competition in the dust. We have now made the results and data available here! Please check it out and ❤️ !
reacted to AdinaY's post with 🔥 25 days ago
view post
Post
2388
Let's check out the latest releases from the Chinese community in March!

👉 https://huggingface.co/collections/zh-ai-community/march-2025-releases-from-the-chinese-community-67c6b479ebb87abbdf8e2e76


✨MLLM
> R1 Omni by Alibaba Tongyi - 0.5B
> Qwen2.5 Omni by Alibaba Qwen - 7B with apache2.0

🖼️Video
> CogView-4 by ZhipuAI - Apacha2.0
> HunyuanVideo-I2V by TencentHunyuan
> Open Sora2.0 - 11B with Apache2.0
> Stepvideo TI2V by StepFun AI - 30B with MIT license

🎵Audio
> DiffDiffRhythm - Apache2.0
> Spark TTS by SparkAudio - 0.5B

⚡️Image/3D
> Hunyuan3D 2mv/2mini (0.6B) by @TencentHunyuan
> FlexWorld by ByteDance - MIT license
> Qwen2.5-VL-32B-Instruct by Alibaba Qwen - Apache2.0
> Tripo SG (1.5B)/SF by VastAIResearch - MIT license
> InfiniteYou by ByteDance

> LHM by Alibaba AIGC team - Apache2.0
> Spatial LM by ManyCore

🧠Reasoning
> QwQ-32B by Alibaba Qwen - Apache2.0
> Skywork R1V - 38B with MIT license
> RWKV G1 by RWKV AI - 0.1B pure RNN reasoning model with Apache2.0
> Fin R1 by SUFE AIFLM Lab - financial reasoning

🔠LLM
> DeepSeek v3 0324 by DeepSeek -MIT license
> Babel by Alibaba DAMO - 9B/83B/25 languages
·
reacted to davidberenstein1957's post with ❤️ 27 days ago
view post
Post
2083
🚨 New Bonus Unit: Tracing & Evaluating Your Agent! 🚨

Learn how to transform your agent from a simple demo into a robust, reliable product ready for real users.

UNIT: https://huggingface.co/learn/agents-course/bonus-unit2/introduction

In this unit, you'll learn:
- Offline Evaluation – Benchmark and iterate your agent using datasets.
- Online Evaluation – Continuously track key metrics such as latency, costs, and user feedback.

Happy testing and improving!

Thanks Langfuse team!
reacted to chansung's post with ❤️ 27 days ago
view post
Post
3471
simple guide on the recipe for GRPO on Open-R1 which is built on top of TRL

I think FastAPI wrapper of vLLM with WeightSyncWorker is pretty cool feature. Also, we have many predefined reward functions out of the box!
·
replied to their post 27 days ago
view reply

Would using my model.onnx as model.pt help fix this problem? Since it would be using a different runtime? I saw some examples of people using model.pt directly.

replied to their post 28 days ago
view reply

Thanks anyways for the help! Does this mean my model is doing inference using CPU even tho I'm running on T4 space?

replied to their post 28 days ago
view reply

I have a public Project on my profile, which you can test now. Do I need to change anything else for it to be visible?
dal4933/Projekt

posted an update 28 days ago
view post
Post
1801
Hi everyone! 👋

I'm trying to deploy my custom YOLOv8 model (converted to ONNX) for live webcam object detection on Hugging Face Spaces using a T4 GPU. My model has 2 classes and works locally, but I'm having trouble getting the deployment on Hugging Face Spaces to work properly.

Has anybody faced similiar problems? Would highly appreciate feedback on the matter.
<3
  • 7 replies
·