Running
3
š
Grok Chatbot
Try XAI's Grok-vision model
Mert Erbak PRO
merterbak
AI & ML interests
Currently NLP and Image Processing
Recent Activity
liked
a Space
11 days ago
merterbak/grok
liked
a dataset
11 days ago
ylecun/mnist
Organizations
merterbak's activity
liked
a
Space
11 days ago
liked
a
dataset
11 days ago
reacted to
m-ric's
post with š
11 days ago
Post
2361
š„ šš¼š¼š“š¹š² šæš²š¹š²š®šš²š šš²šŗš¶š»š¶ š®.š¬, ššš®šæšš¶š»š“ šš¶ššµ š® šš¹š®ššµ šŗš¼š±š²š¹ ššµš®š ššš²š®šŗšæš¼š¹š¹š šš£š§-š°š¼ š®š»š± šš¹š®šš±š²-šÆ.š² š¦š¼š»š»š²š! And they start a huge effort on agentic capabilities.
š The performance improvements are crazy for such a fast model:
ā£ Gemini 2.0 Flash outperforms the previous 1.5 Pro model at twice the speed
ā£ Now supports both input AND output of images, video, audio and text
ā£ Can natively use tools like Google Search and execute code
ā”ļø If the price is on par with previous Flash iteration ($0.30 / M tokens, to compare with GPT-4o's $1.25) the competition will have a big problem with this 4x cheaper model that gets better benchmarks š¤Æ
š¤ What about the agentic capabilities?
ā£ Project Astra: A universal AI assistant that can use Google Search, Lens and Maps
ā£ Project Mariner: A Chrome extension that can complete complex web tasks (83.5% success rate on WebVoyager benchmark, this is really impressive!)
ā£ Jules: An AI coding agent that integrates with GitHub workflows
I'll be eagerly awaiting further news from Google!
Read their blogpost here š https://blog.google/technology/google-deepmind/google-gemini-ai-update-december-2024/
š The performance improvements are crazy for such a fast model:
ā£ Gemini 2.0 Flash outperforms the previous 1.5 Pro model at twice the speed
ā£ Now supports both input AND output of images, video, audio and text
ā£ Can natively use tools like Google Search and execute code
ā”ļø If the price is on par with previous Flash iteration ($0.30 / M tokens, to compare with GPT-4o's $1.25) the competition will have a big problem with this 4x cheaper model that gets better benchmarks š¤Æ
š¤ What about the agentic capabilities?
ā£ Project Astra: A universal AI assistant that can use Google Search, Lens and Maps
ā£ Project Mariner: A Chrome extension that can complete complex web tasks (83.5% success rate on WebVoyager benchmark, this is really impressive!)
ā£ Jules: An AI coding agent that integrates with GitHub workflows
I'll be eagerly awaiting further news from Google!
Read their blogpost here š https://blog.google/technology/google-deepmind/google-gemini-ai-update-december-2024/
liked
2
models
11 days ago
updated
a
Space
11 days ago
liked
a
Space
16 days ago
reacted to
samjulien's
post with š„
16 days ago
Post
1469
š„ RAG in just a few lines of code?!
Try out our Hacker News Listener with new built-in RAG capabilities and Palmyra X 004 from the team at Writer!
This Writer Framework app:
- Scrapes up to 500 HN stories and comments
- Uploads them to a Knowledge Graph
- Enables interactive chat with the content using graph-based RAG
- Provides source attribution with every response
The best part? Setting up RAG is now incredibly simple - just a few lines of code to connect your Knowledge Graph as a tool with Palmyra X 004.
š¤ Space: samjulien/hacker-news-listener
š» Code: https://github.com/writer/framework-tutorials/tree/main/hacker-news-social-listener
Try out our Hacker News Listener with new built-in RAG capabilities and Palmyra X 004 from the team at Writer!
This Writer Framework app:
- Scrapes up to 500 HN stories and comments
- Uploads them to a Knowledge Graph
- Enables interactive chat with the content using graph-based RAG
- Provides source attribution with every response
The best part? Setting up RAG is now incredibly simple - just a few lines of code to connect your Knowledge Graph as a tool with Palmyra X 004.
š¤ Space: samjulien/hacker-news-listener
š» Code: https://github.com/writer/framework-tutorials/tree/main/hacker-news-social-listener
liked
a
model
16 days ago
liked
a
model
23 days ago
upvoted
an
article
23 days ago
Article
Use Models from the Hugging Face Hub in LM Studio
By
ā¢
ā¢
127
liked
2
Spaces
26 days ago
reacted to
merve's
post with š„
26 days ago
Post
3842
Small yet mighty! š«
We are releasing SmolVLM: a new 2B small vision language made for on-device use, fine-tunable on consumer GPU, immensely memory efficient š¤
We release three checkpoints under Apache 2.0: SmolVLM-Instruct, SmolVLM-Synthetic and SmolVLM-Base HuggingFaceTB/smolvlm-6740bd584b2dcbf51ecb1f39
Learn more from our blog here: huggingface.co/blog/smolvlm
This release comes with a demo, fine-tuning code, MLX integration and TRL integration for DPO š
Try the demo: HuggingFaceTB/SmolVLM
Fine-tuning Recipe: https://github.com/huggingface/smollm/blob/main/finetuning/Smol_VLM_FT.ipynb
Also TRL integration for DPO š
We are releasing SmolVLM: a new 2B small vision language made for on-device use, fine-tunable on consumer GPU, immensely memory efficient š¤
We release three checkpoints under Apache 2.0: SmolVLM-Instruct, SmolVLM-Synthetic and SmolVLM-Base HuggingFaceTB/smolvlm-6740bd584b2dcbf51ecb1f39
Learn more from our blog here: huggingface.co/blog/smolvlm
This release comes with a demo, fine-tuning code, MLX integration and TRL integration for DPO š
Try the demo: HuggingFaceTB/SmolVLM
Fine-tuning Recipe: https://github.com/huggingface/smollm/blob/main/finetuning/Smol_VLM_FT.ipynb
Also TRL integration for DPO š
liked
a
model
26 days ago
liked
5
models
about 1 month ago
mistralai/Mistral-Large-Instruct-2411
Updated
ā¢
2.75M
ā¢
174
mistralai/Pixtral-Large-Instruct-2411
Image-Text-to-Text
ā¢
Updated
ā¢
371
meta-llama/Llama-3.2-3B-Instruct
Text Generation
ā¢
Updated
ā¢
2.13M
ā¢
ā¢
810
nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
Text Generation
ā¢
Updated
ā¢
157k
ā¢
1.93k
black-forest-labs/FLUX.1-dev
Text-to-Image
ā¢
Updated
ā¢
1.33M
ā¢
ā¢
7.43k