Загрузка видео...

Не удалось загрузить видео

Возникла проблема при загрузке этого видео. Это может быть связано с временными проблемами сети или видео может быть недоступно.

На главную

Just discovered OSX Automator: attach a keyboard shortcut to run a Python script on highlighted text, instantly swapping with LLM magic! Now proofing grammar on-demand with Mistral 8x7B via Hugging Face or Mistral 7B with ollama LocalLLM

Radamés Ajna

6,854 subscribers

84,121 просмотров • 2 лет назад •via X (Twitter)

Образование

Anya Rossi• Live Now

Private livecam show

Комментарии: 11

Фото профиля Radamés Ajna

Radamés Ajna2 лет назад

here is the code

Фото профиля xleven

xleven2 лет назад

@huggingface @ollama Nice work! There is an Ollama Extension in Raycast with same functions and smooth UX

Фото профиля Radamés Ajna

Radamés Ajna2 лет назад

@xlevenz @huggingface @ollama Cool! I need to check Raycast

Фото профиля Fred Bliss

Fred Bliss2 лет назад

@huggingface @ollama Just discovered this post after spending way too long trying to make Raycast extensions work for this same exact purpose. THANK YOU.

Фото профиля Radamés Ajna

Radamés Ajna2 лет назад

@huggingface @ollama 🤩 I haven't tried Raycast however, I turned to Automator because of its native access on the OSX. The only place it doesn't work as a keyboard shortcut is inside Gmail textbox. However, you can select the text, right-click -> services -> run automator

Фото профиля saurabh mehta

saurabh mehta2 лет назад

@huggingface @ollama Thanks a lot for sharing this automator. Can be much helpful in the flow of work. I followed the steps but when I trigger the shortcut, I get an error: error ‘response’ Any idea why this might be happening? Thanks a lot again.

Фото профиля Steven Natera

Steven Natera2 лет назад

@ollama @huggingface A word of caution. Automator is unreliable with some tasks.

Фото профиля IF

IF2 лет назад

@huggingface @ollama win version please :😭

Фото профиля Radamés Ajna

Radamés Ajna2 лет назад

@FramesImpact @huggingface @ollama maybe we could try using this ?

Фото профиля BLENDER SUSHI 🫶 X - 24/7 Blenderian

BLENDER SUSHI 🫶 X - 24/7 Blenderian2 лет назад

@huggingface @ollama I have been doing this with Pythonista keyboard and chatGPT! But good usage of Automator.p and Shortcuts.

Фото профиля Radamés Ajna

Radamés Ajna2 лет назад

@huggingface @ollama can you run the command from any app? Automator is nice

Похожие видео

Unmute turns a text LLM into a voice AI. At it’s Mistral AI's Mistral-Small-3.2-24B, making it fully open-source. Play a quiz game with a snarky host, catch up on tech news, or just hang out and talk. Or modify it to do anything you want!

Unmute turns a text LLM into a voice AI. At it’s Mistral AI's Mistral-Small-3.2-24B, making it fully open-source. Play a quiz game with a snarky host, catch up on tech news, or just hang out and talk. Or modify it to do anything you want!

kyutai

24,900 просмотров • 1 год назад

Build a local LLM app with RAG to chat with Google Drive data using Mistral or Llama-3 running locally on your computer without wiring a single line of Python Code (100% free and without internet):

Build a local LLM app with RAG to chat with Google Drive data using Mistral or Llama-3 running locally on your computer without wiring a single line of Python Code (100% free and without internet):

Shubham Saboo

189,778 просмотров • 2 лет назад

The video is a Llama v1 7B model implemented in MLX and running on an M2 Ultra. More here: * Train a Transformer LM or fine-tune with LoRA * Text generation with Mistral * Image generation with Stable Diffusion * Speech recognition with Whisper

The video is a Llama v1 7B model implemented in MLX and running on an M2 Ultra. More here: * Train a Transformer LM or fine-tune with LoRA * Text generation with Mistral * Image generation with Stable Diffusion * Speech recognition with Whisper

Awni Hannun

66,585 просмотров • 2 лет назад

100% Local LLM Coding with Bolt + Ollama + Qwen Qwen just dropped their qwen2.5-coder-30B and it's on ollama. Finally a model good enough to use instead of gpt-4o or claude. Now with Qwen, Bolt perfectly displays the app preview with Ollama. Run it with 1 click.

100% Local LLM Coding with Bolt + Ollama + Qwen Qwen just dropped their qwen2.5-coder-30B and it's on ollama. Finally a model good enough to use instead of gpt-4o or claude. Now with Qwen, Bolt perfectly displays the app preview with Ollama. Run it with 1 click.

cocktail peanut

52,630 просмотров • 1 год назад

New short course with Mistral AI ! Mistral's open-source Mixtral 8x7B model uses a "mixture of experts" (MoE) architecture. Unlike a standard transformer, an MoE model has multiple expert feed-forward networks (8 in this case), with a gating network selecting two experts at inference time. This enables MoE to match the performance of a large model but faster inference. Mixtral 8x7B has 46.7B parameters but activates only 12.9B at inference to predict the next token. In Getting Started with Mistral, you’ll learn from Mistral’s Sophia Yang, Ph.D. to: - Explore Mistral's open-source models (Mistral 7B, Mixtral 8x7B) and commercial models via API calls and Mistral AI's Le Chat website - Implement JSON mode to generate structured outputs to integrate directly into larger software systems. - Use function calling for Tool Use, such as calling custom Python code that queries tabular data - Ground your LLM's response with external knowledge sources using RAG - Build a Mistral-powered chat interface that can reference external documents This course will help deepen your prompt engineering skills. Please sign up here:

New short course with Mistral AI ! Mistral's open-source Mixtral 8x7B model uses a "mixture of experts" (MoE) architecture. Unlike a standard transformer, an MoE model has multiple expert feed-forward networks (8 in this case), with a gating network selecting two experts at inference time. This enables MoE to match the performance of a large model but faster inference. Mixtral 8x7B has 46.7B parameters but activates only 12.9B at inference to predict the next token. In Getting Started with Mistral, you’ll learn from Mistral’s Sophia Yang, Ph.D. to: - Explore Mistral's open-source models (Mistral 7B, Mixtral 8x7B) and commercial models via API calls and Mistral AI's Le Chat website - Implement JSON mode to generate structured outputs to integrate directly into larger software systems. - Use function calling for Tool Use, such as calling custom Python code that queries tabular data - Ground your LLM's response with external knowledge sources using RAG - Build a Mistral-powered chat interface that can reference external documents This course will help deepen your prompt engineering skills. Please sign up here:

Andrew Ng

387,172 просмотров • 2 лет назад

I made a site to chat with Mistral AI's new 8x7B instruct model! - free + open source - streams at ~40 tokens/s - beats GPT-3.5 on most benchmarks Try it at

I made a site to chat with Mistral AI's new 8x7B instruct model! - free + open source - streams at ~40 tokens/s - beats GPT-3.5 on most benchmarks Try it at

Charlie Holtz

100,813 просмотров • 2 лет назад

LiveCC just dropped on Hugging Face Learning Video LLM with Streaming Speech Transcription at Scale video LLM capable of real-time commentary, trained with a novel video-ASR streaming method, SOTA on both streaming and offline benchmarks.

LiveCC just dropped on Hugging Face Learning Video LLM with Streaming Speech Transcription at Scale video LLM capable of real-time commentary, trained with a novel video-ASR streaming method, SOTA on both streaming and offline benchmarks.

AK

45,967 просмотров • 1 год назад

Molmo by Ai2 - Open source SoTA Multimodal (Vision) Language model, beating Claude 3.5 Sonnet, GPT4V and comparable to GPT4o 🔥 They release four model checkpoints: 1. MolmoE-1B, a mixture of experts model with 1B (active) 7B (total) 2. Molmo-7B-O, most open 7B model 3. Molmo-7B-D, demo model 4. Molmo-72B, best model System Architecture > Input: Multi-scale, multi-crop images generated from the original image. > Vision Encoder: OpenAI's ViT-L/14 336px CLIP model, a powerful ViT, encodes images into vision tokens. > Connector: MLP projects tokens to LLM input space, followed by pooling for dimensionality reduction. > LLM: Decoder-only Transformer, various options (OLMo, OLMoE, Qwen2, Mistral, Gemma2, Phi) with diverse scales and openness. Model Variants > Vision Encoder: Consistent ViT-L/14 CLIP model across variants. > LLM: OLMo-7B-1024, OLMoE-1B-7B-0924, Qwen2 (7B, 72B), Mistral 7B, Gemma2 9B, Phi 3 Medium, offering different capacities and openness levels. Training Strategy > Stage 1: Multimodal pre-training for caption generation with new captioning data. > Stage 2: Supervised fine-tuning on a dataset mixture, updating all parameters. > No RLHF involved, Learning rates adjusted based on component types and pre-training status. > All the weights are available on Hugging Face Hub 🤗 > Compatible with Transformers (Remote Code) Kudos Ai2 for such a brilliant and open work! 🐐 Video credits: Allen AI YT Channel

Molmo by Ai2 - Open source SoTA Multimodal (Vision) Language model, beating Claude 3.5 Sonnet, GPT4V and comparable to GPT4o 🔥 They release four model checkpoints: 1. MolmoE-1B, a mixture of experts model with 1B (active) 7B (total) 2. Molmo-7B-O, most open 7B model 3. Molmo-7B-D, demo model 4. Molmo-72B, best model System Architecture > Input: Multi-scale, multi-crop images generated from the original image. > Vision Encoder: OpenAI's ViT-L/14 336px CLIP model, a powerful ViT, encodes images into vision tokens. > Connector: MLP projects tokens to LLM input space, followed by pooling for dimensionality reduction. > LLM: Decoder-only Transformer, various options (OLMo, OLMoE, Qwen2, Mistral, Gemma2, Phi) with diverse scales and openness. Model Variants > Vision Encoder: Consistent ViT-L/14 CLIP model across variants. > LLM: OLMo-7B-1024, OLMoE-1B-7B-0924, Qwen2 (7B, 72B), Mistral 7B, Gemma2 9B, Phi 3 Medium, offering different capacities and openness levels. Training Strategy > Stage 1: Multimodal pre-training for caption generation with new captioning data. > Stage 2: Supervised fine-tuning on a dataset mixture, updating all parameters. > No RLHF involved, Learning rates adjusted based on component types and pre-training status. > All the weights are available on Hugging Face Hub 🤗 > Compatible with Transformers (Remote Code) Kudos Ai2 for such a brilliant and open work! 🐐 Video credits: Allen AI YT Channel

Vaibhav (VB) Srivastav

80,474 просмотров • 1 год назад

#Leafmap v0.21.0 is out. It now supports Solara. Developing interactive web apps with pure Python with automatic deployment on Hugging Face. Try it out 👇 Web app: GitHub: Maarten A. Breddels #python #geospatial #dataviz

#Leafmap v0.21.0 is out. It now supports Solara. Developing interactive web apps with pure Python with automatic deployment on Hugging Face. Try it out 👇 Web app: GitHub: Maarten A. Breddels #python #geospatial #dataviz

Qiusheng Wu

73,914 просмотров • 3 лет назад

An open-weight alternative to ElevenLabs! Voxtral is a TTS model by Mistral with: - just 4B params - 70ms latency for voice agents - voice cloning from 3s of audio - 9 languages + cross-lingual transfer - 68.4% win rate over ElevenLabs Flash v2.5 Open weights on Hugging Face.

An open-weight alternative to ElevenLabs! Voxtral is a TTS model by Mistral with: - just 4B params - 70ms latency for voice agents - voice cloning from 3s of audio - 9 languages + cross-lingual transfer - 68.4% win rate over ElevenLabs Flash v2.5 Open weights on Hugging Face.

Avi Chawla

28,162 просмотров • 4 месяцев назад

Check out mistral.rs, our #Rust-based open source inference engine allowing for fast #LLM serving for a variety of architectures including X-LoRA mixture-of-expert (MoE) models, Llama-3, Mistral/Mixtral, Gemma & many others. Built on the Hugging Face #Candle framework for #Rust w/ custom CUDA kernels in the backend (as well as support for Metal, Apple Accelerate, and Intel MKL for CPU use), you can easily create a REST API OpenAI compatible server or run via Python bindings. Key features include: ✅Prefix caching, continuous batching ✅Flash Attention V2 ✅Device offloading ✅GGUF or Hugging Face models ✅2, 3, 4, 5, 6 and 8 bit quantization ✅X-LoRA MoE non-granular scalings for fast inference ✅Grammar support ✅Continuous batching ✅LoRA support with weight merging ✅LlamaIndex 🦙 integration ...and much more. Incorporation into our GraphReasoning multi-agent modeling framework & LlamaIndex 🦙 allows you to combine in-context learning with adversarial agentic strategies, to dive deep into complex scientific analyses, such as to predict material behaviors, generate hypotheses, analyze papers and data, develop new research concepts, and much more. Check out mistral.rs: Join our Discord here: Rust Trending Rust Language

Check out mistral.rs, our #Rust-based open source inference engine allowing for fast #LLM serving for a variety of architectures including X-LoRA mixture-of-expert (MoE) models, Llama-3, Mistral/Mixtral, Gemma & many others. Built on the Hugging Face #Candle framework for #Rust w/ custom CUDA kernels in the backend (as well as support for Metal, Apple Accelerate, and Intel MKL for CPU use), you can easily create a REST API OpenAI compatible server or run via Python bindings. Key features include: ✅Prefix caching, continuous batching ✅Flash Attention V2 ✅Device offloading ✅GGUF or Hugging Face models ✅2, 3, 4, 5, 6 and 8 bit quantization ✅X-LoRA MoE non-granular scalings for fast inference ✅Grammar support ✅Continuous batching ✅LoRA support with weight merging ✅LlamaIndex 🦙 integration ...and much more. Incorporation into our GraphReasoning multi-agent modeling framework & LlamaIndex 🦙 allows you to combine in-context learning with adversarial agentic strategies, to dive deep into complex scientific analyses, such as to predict material behaviors, generate hypotheses, analyze papers and data, develop new research concepts, and much more. Check out mistral.rs: Join our Discord here: Rust Trending Rust Language

Markus J. Buehler

73,581 просмотров • 2 лет назад

$Fuck it! You can now run *any* GGUF on the Hugging Face Hub directly with ollama 🔥 This has been a constant ask from the community, starting today you can point to any of the 45,000 GGUF repos on the Hub* *Without any changes whatsoever! ⚡ All you need to do is: ollama run hf. co/{username}/{reponame}:latest For example, to run the Llama 3.2 1B, you can run: ollama run hf. co/bartowski/Llama-3.2-1B-Instruct-GGUF:latest If you want to run a specific quant, all you need to do is specify the Quant type: ollama run hf. co/bartowski/Llama-3.2-1B-Instruct-GGUF:Q8_0 That's it! We'll work closely with Ollama to continue developing this further! ⚡$

Fuck it! You can now run any GGUF on the Hugging Face Hub directly with ollama 🔥 This has been a constant ask from the community, starting today you can point to any of the 45,000 GGUF repos on the Hub* *Without any changes whatsoever! ⚡ All you need to do is: ollama run hf. co/{username}/{reponame}:latest For example, to run the Llama 3.2 1B, you can run: ollama run hf. co/bartowski/Llama-3.2-1B-Instruct-GGUF:latest If you want to run a specific quant, all you need to do is specify the Quant type: ollama run hf. co/bartowski/Llama-3.2-1B-Instruct-GGUF:Q8_0 That's it! We'll work closely with Ollama to continue developing this further! ⚡

Vaibhav (VB) Srivastav

317,790 просмотров • 1 год назад

Claude Desktop can now run with free local models. This is a huge workflow shift. → Install Ollama. → Run local models on your machine. → Connect Ollama to Claude Code. → Launch Claude Desktop with Ollama. → Swap models depending on the task. Save this video, you’ll use Claude with way more freedom. Want the SOP? DM me. 💬

Claude Desktop can now run with free local models. This is a huge workflow shift. → Install Ollama. → Run local models on your machine. → Connect Ollama to Claude Code. → Launch Claude Desktop with Ollama. → Swap models depending on the task. Save this video, you’ll use Claude with way more freedom. Want the SOP? DM me. 💬

Julian Goldie SEO

11,444 просмотров • 3 месяцев назад

Transforming Invoice Data into JSON: Local LLM with LlamaIndex & Pydantic 🚀 Complete video: Code: I explain how to get structured JSON output with LlamaIndex and dynamic Pydantic class. This helps to implement the use case of data extraction from invoice documents. The solution runs on the local machine, thanks to Ollama. I'm using a MacBook Air M1 with 8GB RAM. LlamaIndex 🦙 Pydantic ollama #Python #LLM #RAG

Transforming Invoice Data into JSON: Local LLM with LlamaIndex & Pydantic 🚀 Complete video: Code: I explain how to get structured JSON output with LlamaIndex and dynamic Pydantic class. This helps to implement the use case of data extraction from invoice documents. The solution runs on the local machine, thanks to Ollama. I'm using a MacBook Air M1 with 8GB RAM. LlamaIndex 🦙 Pydantic ollama #Python #LLM #RAG

Andrej Baranovskij

147,949 просмотров • 2 лет назад

MiniMax Music 3 is just out on Hugging Face 🎶🎵 SoTA song generation, now open weights 🔊, a 8B LLM + 2.7B DiT that turn prompt + lyrics into full songs fits smol consumer GPUs with 🧨 diffusers or comfy model weights + app on Spaces, come play ▶️

MiniMax Music 3 is just out on Hugging Face 🎶🎵 SoTA song generation, now open weights 🔊, a 8B LLM + 2.7B DiT that turn prompt + lyrics into full songs fits smol consumer GPUs with 🧨 diffusers or comfy model weights + app on Spaces, come play ▶️

apolinario (poli)

63,108 просмотров • 19 дней назад

🚀 OpenLLM 0.6 is out providing fast inference speed! Check out our video comparing #OpenLLM and #Ollama handling concurrent requests on the Llama 3 8B model. Ollama is ideal for local LLM deployment, but it is not designed for high concurrency scenarios essential for deployments in the cloud, powering applications with a large number of users. OpenLLM enables you to run any open-source model as OpenAI-compatible endpoints with just a single command. It supports a broad array of models like Llama 3, Mistral, and Qwen 2, including those fine-tuned with proprietary datasets and quantized versions. Ready to speed up your AI deployments? See the OpenLLM repo #BentoML #OpenSource

🚀 OpenLLM 0.6 is out providing fast inference speed! Check out our video comparing #OpenLLM and #Ollama handling concurrent requests on the Llama 3 8B model. Ollama is ideal for local LLM deployment, but it is not designed for high concurrency scenarios essential for deployments in the cloud, powering applications with a large number of users. OpenLLM enables you to run any open-source model as OpenAI-compatible endpoints with just a single command. It supports a broad array of models like Llama 3, Mistral, and Qwen 2, including those fine-tuned with proprietary datasets and quantized versions. Ready to speed up your AI deployments? See the OpenLLM repo #BentoML #OpenSource

BentoML

18,798 просмотров • 2 лет назад

OpenClaw just got a free upgrade ⚡ With Nvidia Nemotron 3 Super now on Ollama, you can run OpenClaw completely free. Just run a simple command, connect it, and you’re good to go. No cost. No limits. Just powerful AI agents. 🚀

OpenClaw just got a free upgrade ⚡ With Nvidia Nemotron 3 Super now on Ollama, you can run OpenClaw completely free. Just run a simple command, connect it, and you’re good to go. No cost. No limits. Just powerful AI agents. 🚀

Julian Goldie SEO

38,830 просмотров • 5 месяцев назад

Hugging Face Spaces, the world's largest AI app directory, is now MCP-compatible 🤯 Here turning an entire website into Ghibli in one shot with Claude Code to demonstrate what's now possible: instantly access any A I tool right in your LLM client!

Hugging Face Spaces, the world's largest AI app directory, is now MCP-compatible 🤯 Here turning an entire website into Ghibli in one shot with Claude Code to demonstrate what's now possible: instantly access any A I tool right in your LLM client!

Victor M

82,196 просмотров • 1 год назад