markov-ai/computer-use-large
Updated • 107k • 139
Nawed Ali
nawed
AI & ML interests
AI/ML, Blockchain
Recent Activity
liked a dataset 3 days ago
markov-ai/computer-use-large reacted to jbilcke-hf's post with 🚀 5 months ago
I made a code sniping agent to detect when new AI papers with code (and weights) are released, and then automatically create a Gradio demo on Hugging Face 🧙
Here are some examples generated 100% automatically:
https://huggingface.co/collections/jbilcke-hf/sniped
I call this agent CheatCode (https://github.com/jbilcke-hf/CheatCode) because it skips so many steps that it kinda feels like breaking the rules of the AI tech release game 😅
As with any experimental technology, there is still room for improvement 👩🏻🔬:
- Currently the demos are all generated in one go and not built or tested by the agent itself. A more robust version should loop over the deployed app to fix build/runtime issues.
- There is still a bit of human curation done to avoid making demos for things that can’t really be demonstrated on ZeroGPU (eg. tasks taking several minutes)
- Some papers can actually be showcased in a variety of ways, which isn’t really supported (see Demo 2)
liked a Space over 1 year ago
pratikskarnik/Indian-Food-RecognitionOrganizations
liked a
dataset 3 days ago
reactedto jbilcke-hf's post with 🚀 5 months ago
Post
5971
I made a code sniping agent to detect when new AI papers with code (and weights) are released, and then automatically create a Gradio demo on Hugging Face 🧙
Here are some examples generated 100% automatically:
https://huggingface.co/collections/jbilcke-hf/sniped
I call this agent CheatCode (https://github.com/jbilcke-hf/CheatCode) because it skips so many steps that it kinda feels like breaking the rules of the AI tech release game 😅
As with any experimental technology, there is still room for improvement 👩🏻🔬:
- Currently the demos are all generated in one go and not built or tested by the agent itself. A more robust version should loop over the deployed app to fix build/runtime issues.
- There is still a bit of human curation done to avoid making demos for things that can’t really be demonstrated on ZeroGPU (eg. tasks taking several minutes)
- Some papers can actually be showcased in a variety of ways, which isn’t really supported (see Demo 2)
Here are some examples generated 100% automatically:
https://huggingface.co/collections/jbilcke-hf/sniped
I call this agent CheatCode (https://github.com/jbilcke-hf/CheatCode) because it skips so many steps that it kinda feels like breaking the rules of the AI tech release game 😅
As with any experimental technology, there is still room for improvement 👩🏻🔬:
- Currently the demos are all generated in one go and not built or tested by the agent itself. A more robust version should loop over the deployed app to fix build/runtime issues.
- There is still a bit of human curation done to avoid making demos for things that can’t really be demonstrated on ZeroGPU (eg. tasks taking several minutes)
- Some papers can actually be showcased in a variety of ways, which isn’t really supported (see Demo 2)
liked a
Space over 1 year ago
liked a
model over 1 year ago
reactedto reach-vb's post with 🔥 over 1 year ago
Post
3451
What an eventful day in Open Source LLMs today:
Mistral released Codestral Mamba 🐍
> Beats DeepSeek QwenCode, best model < 10B, competitive with Codestral 22B
> Mamba 2 architecture - supports up to 256K context
> Apache 2.0 licensed, perfect for local code assistant
> Transformers & llama.cpp integration upcoming!
Model checkpoint: https://huggingface.co/mistralai/mamba-codestral-7B-v0.1
Hugging Face dropped SmolLM 🤏
> Beats MobileLLM, Qwen 0.5B, Phi 1.5B and more!
> 135M, 360M, and 1.7B param model checkpoints
> Trained on 600B high-quality synthetic + FineWeb Edu tokens
> Architecture: Llama + GQA + 2048 ctx length
> Ripe for fine-tuning and on-device deployments.
> Works out of the box with Transformers!
Model checkpoints: HuggingFaceTB/smollm-6695016cad7167254ce15966
Mistral released Mathstral 7B ∑
> 56.6% on MATH and 63.47% on MMLU
> Same architecture as Mistral 7B
> Works out of the box with Transformers & llama.cpp
> Released under Apache 2.0 license
Model checkpoint: https://huggingface.co/mistralai/mathstral-7B-v0.1
Pretty dope day for open source ML. Can't wait to see what the community builds with it and to support them further! 🤗
What's your favourite from the release today?
Mistral released Codestral Mamba 🐍
> Beats DeepSeek QwenCode, best model < 10B, competitive with Codestral 22B
> Mamba 2 architecture - supports up to 256K context
> Apache 2.0 licensed, perfect for local code assistant
> Transformers & llama.cpp integration upcoming!
Model checkpoint: https://huggingface.co/mistralai/mamba-codestral-7B-v0.1
Hugging Face dropped SmolLM 🤏
> Beats MobileLLM, Qwen 0.5B, Phi 1.5B and more!
> 135M, 360M, and 1.7B param model checkpoints
> Trained on 600B high-quality synthetic + FineWeb Edu tokens
> Architecture: Llama + GQA + 2048 ctx length
> Ripe for fine-tuning and on-device deployments.
> Works out of the box with Transformers!
Model checkpoints: HuggingFaceTB/smollm-6695016cad7167254ce15966
Mistral released Mathstral 7B ∑
> 56.6% on MATH and 63.47% on MMLU
> Same architecture as Mistral 7B
> Works out of the box with Transformers & llama.cpp
> Released under Apache 2.0 license
Model checkpoint: https://huggingface.co/mistralai/mathstral-7B-v0.1
Pretty dope day for open source ML. Can't wait to see what the community builds with it and to support them further! 🤗
What's your favourite from the release today?
- 1 reply
liked a
model over 1 year ago
upvoted a paper almost 2 years ago
liked a
Space about 2 years ago
liked a
model about 3 years ago