Local & GGUF
Collection
38 items
•
Updated
•
2
Uthman Bilal
Winnougan
AI & ML interests
None yet
Recent Activity
upvoted
a
collection
about 1 month ago
Local & GGUF
liked
a model
about 2 months ago
MBZUAI-Paris/Atlas-Chat-9B
liked
a model
about 2 months ago
QuantFactory/Atlas-Chat-9B-GGUF
Organizations
None yet
Winnougan's activity
upvoted
a
collection
about 1 month ago
liked
2
models
about 2 months ago
Reacted to
singhsidhukuldeep's
post with 🧠🤯😎👍
about 2 months ago
Post
3986
Researchers have developed a novel approach called Logic-of-Thought (LoT) that significantly enhances the logical reasoning capabilities of large language models (LLMs).
Here are the steps on how Logic-of-Thought (LoT) is implemented:
-- 1. Logic Extraction
1. Use Large Language Models (LLMs) to identify sentences containing conditional reasoning relationships from the input context.
2. Generate a collection of sentences with logical relationships.
3. Use LLMs to extract the set of propositional symbols and logical expressions from the collection.
4. Identify propositions with similar meanings and represent them using identical propositional symbols.
5. Analyze the logical relationships between propositions based on their natural language descriptions.
6. Add negation (¬) for propositions that express opposite meanings.
7. Use implication (→) to connect propositional symbols when a conditional relationship exists.
-- 2. Logic Extension
1. Apply logical reasoning laws to the collection of logical expressions from the Logic Extraction phase.
2. Use a Python program to implement logical deduction and expand the expressions.
3. Apply logical laws such as Double Negation, Contraposition, and Transitivity to derive new logical expressions.
-- 3. Logic Translation
1. Use LLMs to translate the newly generated logical expressions into natural language descriptions.
2. Combine the natural language descriptions of propositional symbols according to the extended logical expressions.
3. Incorporate the translated logical information as a new part of the original input prompt.
-- 4. Integration with Existing Prompting Methods
1. Combine the LoT-generated logical information with the original prompt.
2. Use this enhanced prompt with existing prompting methods like Chain-of-Thought (CoT), Self-Consistency (SC), or Tree-of-Thoughts (ToT).
3. Feed the augmented prompt to the LLM to generate the final answer.
What do you think about LoT?
Here are the steps on how Logic-of-Thought (LoT) is implemented:
-- 1. Logic Extraction
1. Use Large Language Models (LLMs) to identify sentences containing conditional reasoning relationships from the input context.
2. Generate a collection of sentences with logical relationships.
3. Use LLMs to extract the set of propositional symbols and logical expressions from the collection.
4. Identify propositions with similar meanings and represent them using identical propositional symbols.
5. Analyze the logical relationships between propositions based on their natural language descriptions.
6. Add negation (¬) for propositions that express opposite meanings.
7. Use implication (→) to connect propositional symbols when a conditional relationship exists.
-- 2. Logic Extension
1. Apply logical reasoning laws to the collection of logical expressions from the Logic Extraction phase.
2. Use a Python program to implement logical deduction and expand the expressions.
3. Apply logical laws such as Double Negation, Contraposition, and Transitivity to derive new logical expressions.
-- 3. Logic Translation
1. Use LLMs to translate the newly generated logical expressions into natural language descriptions.
2. Combine the natural language descriptions of propositional symbols according to the extended logical expressions.
3. Incorporate the translated logical information as a new part of the original input prompt.
-- 4. Integration with Existing Prompting Methods
1. Combine the LoT-generated logical information with the original prompt.
2. Use this enhanced prompt with existing prompting methods like Chain-of-Thought (CoT), Self-Consistency (SC), or Tree-of-Thoughts (ToT).
3. Feed the augmented prompt to the LLM to generate the final answer.
What do you think about LoT?
- 1 reply
liked
2
models
about 2 months ago
Reacted to
DmitryRyumin's
post with 😎
about 2 months ago
Post
1853
🔥🎭🌟 New Research Alert - ECCV 2024 (Avatars Collection)! 🌟🎭🔥
📄 Title: MeshAvatar: Learning High-quality Triangular Human Avatars from Multi-view Videos 🔝
📝 Description: MeshAvatar is a novel pipeline that generates high-quality triangular human avatars from multi-view videos, enabling realistic editing and rendering through a mesh-based approach with physics-based decomposition.
👥 Authors: Yushuo Chen, Zerong Zheng, Zhe Li, Chao Xu, and Yebin Liu
📅 Conference: ECCV, 29 Sep – 4 Oct, 2024 | Milano, Italy 🇮🇹
📄 Paper: MeshAvatar: Learning High-quality Triangular Human Avatars from Multi-view Videos (2407.08414)
🌐 Github Page: https://shad0wta9.github.io/meshavatar-page
📁 Repository: https://github.com/shad0wta9/meshavatar
📺 Video: https://www.youtube.com/watch?v=Kpbpujkh2iI
🚀 CVPR-2023-24-Papers: https://github.com/DmitryRyumin/CVPR-2023-24-Papers
🚀 WACV-2024-Papers: https://github.com/DmitryRyumin/WACV-2024-Papers
🚀 ICCV-2023-Papers: https://github.com/DmitryRyumin/ICCV-2023-Papers
📚 More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin
🚀 Added to the Avatars Collection: DmitryRyumin/avatars-65df37cdf81fec13d4dbac36
🔍 Keywords: #MeshAvatar #3DAvatars #MultiViewVideo #PhysicsBasedRendering #TriangularMesh #AvatarCreation #3DModeling #NeuralRendering #Relighting #AvatarEditing #MachineLearning #ComputerVision #ComputerGraphics #DeepLearning #AI #ECCV2024
📄 Title: MeshAvatar: Learning High-quality Triangular Human Avatars from Multi-view Videos 🔝
📝 Description: MeshAvatar is a novel pipeline that generates high-quality triangular human avatars from multi-view videos, enabling realistic editing and rendering through a mesh-based approach with physics-based decomposition.
👥 Authors: Yushuo Chen, Zerong Zheng, Zhe Li, Chao Xu, and Yebin Liu
📅 Conference: ECCV, 29 Sep – 4 Oct, 2024 | Milano, Italy 🇮🇹
📄 Paper: MeshAvatar: Learning High-quality Triangular Human Avatars from Multi-view Videos (2407.08414)
🌐 Github Page: https://shad0wta9.github.io/meshavatar-page
📁 Repository: https://github.com/shad0wta9/meshavatar
📺 Video: https://www.youtube.com/watch?v=Kpbpujkh2iI
🚀 CVPR-2023-24-Papers: https://github.com/DmitryRyumin/CVPR-2023-24-Papers
🚀 WACV-2024-Papers: https://github.com/DmitryRyumin/WACV-2024-Papers
🚀 ICCV-2023-Papers: https://github.com/DmitryRyumin/ICCV-2023-Papers
📚 More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin
🚀 Added to the Avatars Collection: DmitryRyumin/avatars-65df37cdf81fec13d4dbac36
🔍 Keywords: #MeshAvatar #3DAvatars #MultiViewVideo #PhysicsBasedRendering #TriangularMesh #AvatarCreation #3DModeling #NeuralRendering #Relighting #AvatarEditing #MachineLearning #ComputerVision #ComputerGraphics #DeepLearning #AI #ECCV2024
Reacted to
onekq's
post with 👍
about 2 months ago
Post
2550
Here is my latest study on OpenAI🍓o1🍓.
A Case Study of Web App Coding with OpenAI Reasoning Models (2409.13773)
I wrote an easy-to-read blogpost to explain finding.
https://huggingface.co/blog/onekq/daily-software-engineering-work-reasoning-models
INSTRUCTION FOLLOWING is the key.
100% instruction following + Reasoning = new SOTA
But if the model misses or misunderstands one instruction, it can perform far worse than non-reasoning models.
A Case Study of Web App Coding with OpenAI Reasoning Models (2409.13773)
I wrote an easy-to-read blogpost to explain finding.
https://huggingface.co/blog/onekq/daily-software-engineering-work-reasoning-models
INSTRUCTION FOLLOWING is the key.
100% instruction following + Reasoning = new SOTA
But if the model misses or misunderstands one instruction, it can perform far worse than non-reasoning models.
liked
a
model
2 months ago
Reacted to
m-ric's
post with 👍
3 months ago
Post
2130
🥳 𝗧𝗿𝗮𝗻𝘀𝗳𝗼𝗿𝗺𝗲𝗿𝘀 𝗔𝗴𝗲𝗻𝘁𝘀 𝗻𝗼𝘄 𝘀𝘂𝗽𝗽𝗼𝗿𝘁𝘀 𝗠𝘂𝗹𝘁𝗶-𝗮𝗴𝗲𝗻𝘁 𝘀𝘆𝘀𝘁𝗲𝗺𝘀!
Multi-agent systems have been introduced in Microsoft's framework Autogen. It simply means having several agents working together to solve your task instead of only one : this paradigm empirically yields better performance on most benchmarks. The reason for this better performance is conceptually simple: for many tasks, rather than using a do-it-all system, you would prefer to specialize units on sub-tasks. Here, having agents with separate tool sets and memories allows to achieve efficient specialization.
You can now easily build hierarchical multi-agent systems with transformers.agents (not released yet, use the dev version)
To do so, encapsulate the agent in a ManagedAgent object. This object needs arguments agent, name, and a description, which will then be embedded in the manager agent's system prompt to let it know how to call this managed agent, as we also do for tools.
Cf the example in the image! We'll keep building on this paradigm in the upcoming weeks 🚀
Read more in the doc 👉 https://github.com/huggingface/transformers/blob/main/docs/source/en/agents_advanced.md
Checkout an advanced multi-agent system that tops the GAIA leaderboard 👉 https://github.com/aymeric-roucher/GAIA/blob/main/gaia_multiagent.py
Multi-agent systems have been introduced in Microsoft's framework Autogen. It simply means having several agents working together to solve your task instead of only one : this paradigm empirically yields better performance on most benchmarks. The reason for this better performance is conceptually simple: for many tasks, rather than using a do-it-all system, you would prefer to specialize units on sub-tasks. Here, having agents with separate tool sets and memories allows to achieve efficient specialization.
You can now easily build hierarchical multi-agent systems with transformers.agents (not released yet, use the dev version)
To do so, encapsulate the agent in a ManagedAgent object. This object needs arguments agent, name, and a description, which will then be embedded in the manager agent's system prompt to let it know how to call this managed agent, as we also do for tools.
Cf the example in the image! We'll keep building on this paradigm in the upcoming weeks 🚀
Read more in the doc 👉 https://github.com/huggingface/transformers/blob/main/docs/source/en/agents_advanced.md
Checkout an advanced multi-agent system that tops the GAIA leaderboard 👉 https://github.com/aymeric-roucher/GAIA/blob/main/gaia_multiagent.py
Reacted to
xianbao's
post with 👍
3 months ago
Post
1627
With the open-weight release of CogVideoX-5B from THUDM, i.e. GLM team, the Video Generation Model (how about calling it VGM) field has officially became the next booming "LLM"
What does the landscape look like? What are other video generation models? This collection below is all your need.
xianbao/video-generation-models-66c350163c74f60f5c412af6
The above video is generated by @a-r-r-o-w with CogVideoX-5B, taken from a nice lookout for the field!
What does the landscape look like? What are other video generation models? This collection below is all your need.
xianbao/video-generation-models-66c350163c74f60f5c412af6
The above video is generated by @a-r-r-o-w with CogVideoX-5B, taken from a nice lookout for the field!
This model slaps hard!
2
#1 opened 3 months ago
by
Winnougan
Winnougan
Reacted to
davidberenstein1957's
post with 👍
3 months ago
Post
1767
📣 Introducing Dataset Viber: your chill repo for data collection, annotation and vibe checks! 🎉
I've cooked up Dataset Viber, a set of cool tools designed to make data preparation for AI models easier, more approachable and enjoyable for standalone AI engineers and enthusiasts.
🔧 What Dataset Viber offers:
- CollectorInterface: Lazily collect model interaction data without human annotation
- AnnotatorInterface: Annotate your data with models in the loop
- BulkInterface: Explore data distribution and annotate in bulk
- Embedder: Efficiently embed data with ONNX-optimized speeds
🎯 Key features:
- Supports various tasks for text, chat, and image modalities
- Runs in .ipynb notebooks
- Logs data to local CSV or directly to Hugging Face Hub
- Easy to install via pip:
It's not designed for team collaboration or production use, but rather as a fun and efficient toolkit for individual projects.
Want to give it a try? Check out the repository link https://github.com/davidberenstein1957/dataset-viber/.
I'm excited to hear your feedback and learn how you vibe with your data. Feel free to open an issue or reach out if you have any questions or suggestions!
Some shoutouts:
- Gradio for the amazing backbone
- Daniel van Strien for some initial presentations I did on vibe checks
- Emily Omier for the workshop on structuring GitHub repo READMEs
- Hamel Husain for keeping mentioning that people should look at their data.
- Philipp Schmid for his code for ONNX feature-extractors
- Ben Burtenshaw for the first PR
I've cooked up Dataset Viber, a set of cool tools designed to make data preparation for AI models easier, more approachable and enjoyable for standalone AI engineers and enthusiasts.
🔧 What Dataset Viber offers:
- CollectorInterface: Lazily collect model interaction data without human annotation
- AnnotatorInterface: Annotate your data with models in the loop
- BulkInterface: Explore data distribution and annotate in bulk
- Embedder: Efficiently embed data with ONNX-optimized speeds
🎯 Key features:
- Supports various tasks for text, chat, and image modalities
- Runs in .ipynb notebooks
- Logs data to local CSV or directly to Hugging Face Hub
- Easy to install via pip:
pip install dataset-viberIt's not designed for team collaboration or production use, but rather as a fun and efficient toolkit for individual projects.
Want to give it a try? Check out the repository link https://github.com/davidberenstein1957/dataset-viber/.
I'm excited to hear your feedback and learn how you vibe with your data. Feel free to open an issue or reach out if you have any questions or suggestions!
Some shoutouts:
- Gradio for the amazing backbone
- Daniel van Strien for some initial presentations I did on vibe checks
- Emily Omier for the workshop on structuring GitHub repo READMEs
- Hamel Husain for keeping mentioning that people should look at their data.
- Philipp Schmid for his code for ONNX feature-extractors
- Ben Burtenshaw for the first PR
- 1 reply
Reacted to
not-lain's
post with ❤️🔥
4 months ago
Post
6093
🔥 New state of the art model for background removal is out
🤗 You can try the model at ZhengPeng7/BiRefNet
📈 model shows impressive results outperforming briaai/RMBG-1.4
🚀 you can try out the model in: ZhengPeng7/BiRefNet_demo
📃paper: Bilateral Reference for High-Resolution Dichotomous Image Segmentation (2401.03407)
🤗 You can try the model at ZhengPeng7/BiRefNet
📈 model shows impressive results outperforming briaai/RMBG-1.4
🚀 you can try out the model in: ZhengPeng7/BiRefNet_demo
📃paper: Bilateral Reference for High-Resolution Dichotomous Image Segmentation (2401.03407)
- 1 reply
Reacted to
MonsterMMORPG's
post with ➕🤯
4 months ago
Post
3808
FLUX FP16 produces better quality than FP8 but requires 28 GB VRAM - Full comparisons - Also compared Dev vs Turbo model and 1024 vs 1536
check the file names in the below given imgsli to see all details
SwarmUI on L40S is used to compare - 1.82 it / second step speed for 1024x1024
imgsli link that compares all : https://imgsli.com/MjgzNzM1
SwarmUI full tutorial public post : https://www.patreon.com/posts/106135985
1-Click FLUX models downloader scripts for Windows, RunPod and Massed Compute are in below post
https://www.patreon.com/posts/109289967
free Kaggle account notebook that supports FLUX already : Download from here : https://www.patreon.com/posts/106650931
prompt :
(medium full shot) of (awe-inspiring snake) with muscular body, amber eyes, bronze brown armored scales, venomous fangs, coiling tail, gemstone-studded scales frills, set in a barren desert wasteland, with cracked earth and the remains of ancient structures, a place of mystery and danger, at dawn, ,Masterpiece,best quality, raw photo, realistic, very aesthetic, dark
CFG 1 - seed 1 - FLUX CFG is default : 3.5
Full public SwarmUI tutorial
Zero to Hero Stable Diffusion 3 Tutorial with Amazing SwarmUI SD Web UI that Utilizes ComfyUI
https://youtu.be/HKX8_F1Er_w
Full public Cloud SwarmUI tutorial
How to Use SwarmUI & Stable Diffusion 3 on Cloud Services Kaggle (free), Massed Compute & RunPod
https://youtu.be/XFUZof6Skkw
check the file names in the below given imgsli to see all details
SwarmUI on L40S is used to compare - 1.82 it / second step speed for 1024x1024
imgsli link that compares all : https://imgsli.com/MjgzNzM1
SwarmUI full tutorial public post : https://www.patreon.com/posts/106135985
1-Click FLUX models downloader scripts for Windows, RunPod and Massed Compute are in below post
https://www.patreon.com/posts/109289967
free Kaggle account notebook that supports FLUX already : Download from here : https://www.patreon.com/posts/106650931
prompt :
(medium full shot) of (awe-inspiring snake) with muscular body, amber eyes, bronze brown armored scales, venomous fangs, coiling tail, gemstone-studded scales frills, set in a barren desert wasteland, with cracked earth and the remains of ancient structures, a place of mystery and danger, at dawn, ,Masterpiece,best quality, raw photo, realistic, very aesthetic, dark
CFG 1 - seed 1 - FLUX CFG is default : 3.5
Full public SwarmUI tutorial
Zero to Hero Stable Diffusion 3 Tutorial with Amazing SwarmUI SD Web UI that Utilizes ComfyUI
https://youtu.be/HKX8_F1Er_w
Full public Cloud SwarmUI tutorial
How to Use SwarmUI & Stable Diffusion 3 on Cloud Services Kaggle (free), Massed Compute & RunPod
https://youtu.be/XFUZof6Skkw