Sensitive content

This media may contain sensitive content.

Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

The Invitation ❤️💛 Sue Storm model: TheMadCommander (Cummissions Open) Angela model: Digital Hell Angela/Sue VA: Missus🎙️🔞💋 | COMMS OPEN SFX editor: 🏹Tress 性 4k version and no WM avaible only for supporters. You can always support for more and better works.

doolbumz's profile picture

doolbum 🔞

47,355 subscribers

476,644 görüntüleme • 9 ay önce •via X (Twitter)

NSFW
LIVE

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

Jan v1 is now more reliable when handling searches. It's an open-source alternative to Perplexity Pro, and it now avoids infinite loops with Jan v1 2509. Performance updates: - Gains on reasoning & creativity benchmarks - Small drop on SimpleQA (91.1 -> 90.7), still competitive with Perplexity Pro The updated version is live on Jan Hub. You can run the model in Jan, llama.cpp, or vLLM. Use the model: - Model: - GGUF: Shoutout to the Qwen team for Qwen3-4B Thinking and Georgi Gerganov for llama.cpp.
0:36

Jan v1 is now more reliable when handling searches. It's an open-source alternative to Perplexity Pro, and it now avoids infinite loops with Jan v1 2509. Performance updates: - Gains on reasoning & creativity benchmarks - Small drop on SimpleQA (91.1 -> 90.7), still competitive with Perplexity Pro The updated version is live on Jan Hub. You can run the model in Jan, llama.cpp, or vLLM. Use the model: - Model: - GGUF: Shoutout to the Qwen team for Qwen3-4B Thinking and Georgi Gerganov for llama.cpp.

👋 Jan

17,759 görüntüleme • 10 ay önce

LETS GOO! Parler TTS 🔥 A fully open-source, Apache 2.0 licensed Text-to-speech model focused on providing maximum controllability. Through voice prompts, you can control the pitch, speed, gender, noise levels, emotion characteristics and more! > Trained on 10K hours of permissive data. > Offers control over the generations. > Training + Inference code released. > The processed dataset and tagging scripts were released for further research. > English only for now. Next, we're scaling the training to 50K hours and even better dataset processing! Want to help us out? DMs open! 🤗
0:39

LETS GOO! Parler TTS 🔥 A fully open-source, Apache 2.0 licensed Text-to-speech model focused on providing maximum controllability. Through voice prompts, you can control the pitch, speed, gender, noise levels, emotion characteristics and more! > Trained on 10K hours of permissive data. > Offers control over the generations. > Training + Inference code released. > The processed dataset and tagging scripts were released for further research. > English only for now. Next, we're scaling the training to 50K hours and even better dataset processing! Want to help us out? DMs open! 🤗

Vaibhav (VB) Srivastav

156,386 görüntüleme • 2 yıl önce

Smart Turn v2: open source, native audio turn detection in 14 languages. New checkpoint of the open source, open data, open training code, semantic VAD model on Hugging Face, fal, and Pipecat AI. - 3x faster inference (12ms on an L40) - 14 languages (13 more than v1, which was english-only) - New synthetic data set `chirp_3_all` with ~163k audio samples - 99% accuracy on held out `human_5_all` test data Good turn detection is critical for voice agents. This model "understands" both semantic and audio patterns, and mitigates the voice AI trade-off between unwanted turn latency vs the agent interrupting people before they are finished speaking. Training scripts for both Modal and local training are in the repo. We want to make it as easy as possible to contribute to or customize this model! Here's a demo running the smart-turn model with default settings, aimed at generally hitting 400ms total turn detection time. You can tune things to be faster, too. You can help by contributing data, doing architecture expermints, or cleaning open source data! Keep reading ...
2:12

Smart Turn v2: open source, native audio turn detection in 14 languages. New checkpoint of the open source, open data, open training code, semantic VAD model on Hugging Face, fal, and Pipecat AI. - 3x faster inference (12ms on an L40) - 14 languages (13 more than v1, which was english-only) - New synthetic data set `chirp_3_all` with ~163k audio samples - 99% accuracy on held out `human_5_all` test data Good turn detection is critical for voice agents. This model "understands" both semantic and audio patterns, and mitigates the voice AI trade-off between unwanted turn latency vs the agent interrupting people before they are finished speaking. Training scripts for both Modal and local training are in the repo. We want to make it as easy as possible to contribute to or customize this model! Here's a demo running the smart-turn model with default settings, aimed at generally hitting 400ms total turn detection time. You can tune things to be faster, too. You can help by contributing data, doing architecture expermints, or cleaning open source data! Keep reading ...

kwindla

42,246 görüntüleme • 1 yıl önce

🚨 FASHN VTON v1.5 is now open source. Released in early 2025 and still widely used, this virtual try-on model generates photorealistic images from a person image and a garment image. Key points: • Pixel-space RGB generation, no VAE • Maskless inference, no person segmentation needed • 972M parameters, ~5s on H100, runs on consumer GPUs • Apache 2.0 licensed, first commercially usable open-source VTON Why open source? While the industry moves toward massive generalist models, FASHN VTON v1.5 proves a focused alternative. This is a production-grade virtual try-on model you can train for $5–10k, own, study, and extend. Built for researchers, developers, and fashion tech teams who want more than black-box APIs. More info in the comments.
0:53

🚨 FASHN VTON v1.5 is now open source. Released in early 2025 and still widely used, this virtual try-on model generates photorealistic images from a person image and a garment image. Key points: • Pixel-space RGB generation, no VAE • Maskless inference, no person segmentation needed • 972M parameters, ~5s on H100, runs on consumer GPUs • Apache 2.0 licensed, first commercially usable open-source VTON Why open source? While the industry moves toward massive generalist models, FASHN VTON v1.5 proves a focused alternative. This is a production-grade virtual try-on model you can train for $5–10k, own, study, and extend. Built for researchers, developers, and fashion tech teams who want more than black-box APIs. More info in the comments.

FASHN AI

19,111 görüntüleme • 5 ay önce

Small Language Models (SML) are the future of AI. "Small" (SML) instead of "Large" (LLM). These small models are highly specialized models with superhuman abilities on specific tasks. Here are two techniques to build these models: • Spectrum • Model Merging I give you a short introduction in the attached video, but here is a quick summary: Spectrum helps us identify the most relevant layers to solve one specific task. We can ignore everything else and focus on fine-tuning these layers. Using Spectrum, we can fine-tune models in a heartbeat. Model Merging combines multiple models into a unique, much better model than any of the individual input models. You can also combine models specialized in different tasks and get a model with multiple abilities. This is the state of the art of productizing models. It's what Arcee.ai's platform does behind the scenes. Arcee collaborated with me on this post and is sponsoring it. There are three main steps to produce a model for your particular use case: 1. You create a dataset by uploading your data. 2. You train a model. At this step, Arcee uses Spectrum and Model Merging to produce a highly specialized model for your task. 3. You can deploy that model to any environment you want. Three important notes: • Training process is 2x faster and 2x cheaper than regular fine-tuning. • Resultant models are smaller and have higher accuracy. • They create these specialized models from open-source models. Check this site so you can fully appreciate how this works: If you want to fine-tune an open-source model, consider Arcee's platform. This is the state of the art.
2:52

Small Language Models (SML) are the future of AI. "Small" (SML) instead of "Large" (LLM). These small models are highly specialized models with superhuman abilities on specific tasks. Here are two techniques to build these models: • Spectrum • Model Merging I give you a short introduction in the attached video, but here is a quick summary: Spectrum helps us identify the most relevant layers to solve one specific task. We can ignore everything else and focus on fine-tuning these layers. Using Spectrum, we can fine-tune models in a heartbeat. Model Merging combines multiple models into a unique, much better model than any of the individual input models. You can also combine models specialized in different tasks and get a model with multiple abilities. This is the state of the art of productizing models. It's what Arcee.ai's platform does behind the scenes. Arcee collaborated with me on this post and is sponsoring it. There are three main steps to produce a model for your particular use case: 1. You create a dataset by uploading your data. 2. You train a model. At this step, Arcee uses Spectrum and Model Merging to produce a highly specialized model for your task. 3. You can deploy that model to any environment you want. Three important notes: • Training process is 2x faster and 2x cheaper than regular fine-tuning. • Resultant models are smaller and have higher accuracy. • They create these specialized models from open-source models. Check this site so you can fully appreciate how this works: If you want to fine-tune an open-source model, consider Arcee's platform. This is the state of the art.

Santiago

164,162 görüntüleme • 2 yıl önce

✨"Cubism Editor 5.4.00 alpha1" limited release until September 14, 2026✨ We are also releasing Cubism 5 SDK for Unity R7 alpha1, which supports these new features, at the same time. Check out the accompanying digest video to learn about the main new features. 🔥[New Features] ✏️ [Parameter Controller SDK Support] Parameter controllers (IK) are now supported in the SDK. You can configure them directly on the model and export them as runtime files. Additionally, a new "target-only" controller can be defined to allow the controller to follow a path. ✏️ [Model State Set] A new model state set feature has been added. You can register working states in a dedicated palette, enabling you to recall specific states of visibility, lock, and parameter values with a single click. This helps you work more efficiently by allowing you to switch between states tailored to different tasks. ✏️[Expanded Editing Support for External Application Integration API ] The external application integration API has been expanded to include object editing and more. You can now integrate an API to directly add and edit parts, deformers, and parameters on models in the editor. ✏️[Enhanced automatic layout for texture atlases] The automatic layout algorithm for texture atlas editing has been completely redesigned. This enables more efficient packing with less unused space. You can configure the layout settings individually for each texture, allowing for flexible layouts. [How to use Cubism 5.4 alpha] Please see the announcement page for details on downloading and feedback. ⚠Notes on using the alpha version - The alpha version is provided for the purpose of gathering feedback on the usability and performance of new features. - Usage Period: Until September 14, 2026. - Please be sure to create a backup, as there is a possibility of data corruption. - Alpha version data and SDK outputs are not guaranteed to function properly and we do not provide support for it. #Live2D #cubism54_alpha
2:04

✨"Cubism Editor 5.4.00 alpha1" limited release until September 14, 2026✨ We are also releasing Cubism 5 SDK for Unity R7 alpha1, which supports these new features, at the same time. Check out the accompanying digest video to learn about the main new features. 🔥[New Features] ✏️ [Parameter Controller SDK Support] Parameter controllers (IK) are now supported in the SDK. You can configure them directly on the model and export them as runtime files. Additionally, a new "target-only" controller can be defined to allow the controller to follow a path. ✏️ [Model State Set] A new model state set feature has been added. You can register working states in a dedicated palette, enabling you to recall specific states of visibility, lock, and parameter values with a single click. This helps you work more efficiently by allowing you to switch between states tailored to different tasks. ✏️[Expanded Editing Support for External Application Integration API ] The external application integration API has been expanded to include object editing and more. You can now integrate an API to directly add and edit parts, deformers, and parameters on models in the editor. ✏️[Enhanced automatic layout for texture atlases] The automatic layout algorithm for texture atlas editing has been completely redesigned. This enables more efficient packing with less unused space. You can configure the layout settings individually for each texture, allowing for flexible layouts. [How to use Cubism 5.4 alpha] Please see the announcement page for details on downloading and feedback. ⚠Notes on using the alpha version - The alpha version is provided for the purpose of gathering feedback on the usability and performance of new features. - Usage Period: Until September 14, 2026. - Please be sure to create a backup, as there is a possibility of data corruption. - Alpha version data and SDK outputs are not guaranteed to function properly and we do not provide support for it. #Live2D #cubism54_alpha

Live2D

96,707 görüntüleme • 10 gün önce

Today we are launching Openwork is now Accomplish, an open-source (MIT-licensed) computer-use agent that’s fast, cheap, and more secure. Openwork is now Accomplish is the result of a short two-day hackathon our team decided to hack, which brings together some of our favorite open source AI modules into one powerful agent, to allow you to: 1. Bring your own model/API key (any provider and model supported by OpenCode is supported by Openwork) 2. ~4x faster than Claude for Chrome/Cowork, and much more token-efficient, powered by dev-browser by Sawyer Hood (legend) 3. More secure - contrary to Claude for Chrom/Cowork, does not leverage the main browser instance where you are logged into all services already. You login only to the services you need. This significantly reduces the risk of data loss in case of prompt injections, to which computer-use agents are highly exposed. 4. Free and 100% open-source! You can download the DMG (macOS only for now) or fork the github repo via the link in bio (Openwork is now Accomplish). Let us know what you think (or better, send a pull request)!
1:23

Today we are launching Openwork is now Accomplish, an open-source (MIT-licensed) computer-use agent that’s fast, cheap, and more secure. Openwork is now Accomplish is the result of a short two-day hackathon our team decided to hack, which brings together some of our favorite open source AI modules into one powerful agent, to allow you to: 1. Bring your own model/API key (any provider and model supported by OpenCode is supported by Openwork) 2. ~4x faster than Claude for Chrome/Cowork, and much more token-efficient, powered by dev-browser by Sawyer Hood (legend) 3. More secure - contrary to Claude for Chrom/Cowork, does not leverage the main browser instance where you are logged into all services already. You login only to the services you need. This significantly reduces the risk of data loss in case of prompt injections, to which computer-use agents are highly exposed. 4. Free and 100% open-source! You can download the DMG (macOS only for now) or fork the github repo via the link in bio (Openwork is now Accomplish). Let us know what you think (or better, send a pull request)!

Or Hiltch

1,002,139 görüntüleme • 6 ay önce

𝗥𝘂𝗻 𝗚𝗼𝗼𝗴𝗹𝗲'𝘀 𝗚𝗲𝗺𝗺𝗮 𝟰 + 𝗢𝗽𝗲𝗻𝗖𝗹𝗮𝘄 𝗮𝘀 𝗮 𝗳𝗿𝗲𝗲 𝗽𝗿𝗶𝘃𝗮𝘁𝗲 𝗔𝗜 𝗮𝗴𝗲𝗻𝘁 𝗼𝗻 𝘆𝗼𝘂𝗿 𝗼𝘄𝗻 𝗺𝗮𝗰𝗵𝗶𝗻𝗲 𝗶𝗻 𝟯 𝘀𝘁𝗲𝗽𝘀. No API bills. No usage limits. No subscription. Nothing leaves your computer. Here's the full setup: → Step 1: Go to Download and install. Update to version 0.2.2.0 or higher. → Step 2: Open terminal. Type: ollama pull gemma4. Downloads the model. Done. → Step 3: Install OpenClaw. Select Ollama as your provider. Point it at port 11434. Pick Gemma 4. That's it. Your AI agent is now running locally. Message it through Telegram, Slack, Discord, or WhatsApp like a coworker. Read files. Write code. Remember context across every conversation. All on your own hardware. Gemma 4 ranked number 3 on the global open model leaderboard on launch day. It beat models with 20 times more parameters. The 26B version activates only 4B parameters at a time so you get near large-model quality at small-model speed. Every AI subscription you're paying for right now could be replaced with this.
7:36

𝗥𝘂𝗻 𝗚𝗼𝗼𝗴𝗹𝗲'𝘀 𝗚𝗲𝗺𝗺𝗮 𝟰 + 𝗢𝗽𝗲𝗻𝗖𝗹𝗮𝘄 𝗮𝘀 𝗮 𝗳𝗿𝗲𝗲 𝗽𝗿𝗶𝘃𝗮𝘁𝗲 𝗔𝗜 𝗮𝗴𝗲𝗻𝘁 𝗼𝗻 𝘆𝗼𝘂𝗿 𝗼𝘄𝗻 𝗺𝗮𝗰𝗵𝗶𝗻𝗲 𝗶𝗻 𝟯 𝘀𝘁𝗲𝗽𝘀. No API bills. No usage limits. No subscription. Nothing leaves your computer. Here's the full setup: → Step 1: Go to Download and install. Update to version 0.2.2.0 or higher. → Step 2: Open terminal. Type: ollama pull gemma4. Downloads the model. Done. → Step 3: Install OpenClaw. Select Ollama as your provider. Point it at port 11434. Pick Gemma 4. That's it. Your AI agent is now running locally. Message it through Telegram, Slack, Discord, or WhatsApp like a coworker. Read files. Write code. Remember context across every conversation. All on your own hardware. Gemma 4 ranked number 3 on the global open model leaderboard on launch day. It beat models with 20 times more parameters. The 26B version activates only 4B parameters at a time so you get near large-model quality at small-model speed. Every AI subscription you're paying for right now could be replaced with this.

Julian Goldie SEO

36,566 görüntüleme • 3 ay önce

We just raised $30M at a $500M valuation, bringing our total funding to $47M. Led by Craft Ventures , with Pace Capital , Chemistry , TruArrow, and others. But before anything else: this belongs to the community. ComfyUI started as one developer and one open-source repo. No roadmap. No company. Just creators who wanted real control over how they built with AI. That community is now: → 4 million users → 60,000+ community-built nodes → 150,000+ daily downloads Every number traces back to people who built in the open, for anyone to use. Here's where the funding goes: → Comfy Cloud: for teams and studios that need security and scale → Collaborative workflows: versioning and iteration built for how studios actually work → A better local experience: more seamless, more stable → Ecosystem reliability: making 60,000+ community nodes more dependable → Day-one model support: every major release, compatible at launch We are not building a walled garden. We are building open infrastructure, built to last. Thank you genuinely, The ComfyUI Team
2:32

We just raised $30M at a $500M valuation, bringing our total funding to $47M. Led by Craft Ventures , with Pace Capital , Chemistry , TruArrow, and others. But before anything else: this belongs to the community. ComfyUI started as one developer and one open-source repo. No roadmap. No company. Just creators who wanted real control over how they built with AI. That community is now: → 4 million users → 60,000+ community-built nodes → 150,000+ daily downloads Every number traces back to people who built in the open, for anyone to use. Here's where the funding goes: → Comfy Cloud: for teams and studios that need security and scale → Collaborative workflows: versioning and iteration built for how studios actually work → A better local experience: more seamless, more stable → Ecosystem reliability: making 60,000+ community nodes more dependable → Day-one model support: every major release, compatible at launch We are not building a walled garden. We are building open infrastructure, built to last. Thank you genuinely, The ComfyUI Team

ComfyUI

961,005 görüntüleme • 3 ay önce

How to use 50+ API keys (models) for FREE on OpenClaw API??? - go to - login or register your account - click on "more models" - click on "use case" and select what you need it for - choose the model and open it - click on "view code" → "Generate API key" many models don't allow direct deploy, so use the "view code" button to generate API access basically Nvidia NIM gives you the ability to test almost any model from their list for FREE some of them are not worse than GPT 5.2 or Claude Opus 4.6, some might even perform better depending on the task how to understand if a model is efficient and compare it with others??? - go to - type the model name in search - click on "benchmarks" - you’ll see performance tests and rankings this way you can easily compare free models with paid ones of course there are RPM limits, on many models it’s around ~40 requests per minute each model is different, after generating the API key, RPM limits are shown in the top-right corner nothing stops you from using them, many work perfectly fine, super solid option for first tests and for learning OpenClaw or any other system where you need an AI API model
1:54

How to use 50+ API keys (models) for FREE on OpenClaw API??? - go to - login or register your account - click on "more models" - click on "use case" and select what you need it for - choose the model and open it - click on "view code" → "Generate API key" many models don't allow direct deploy, so use the "view code" button to generate API access basically Nvidia NIM gives you the ability to test almost any model from their list for FREE some of them are not worse than GPT 5.2 or Claude Opus 4.6, some might even perform better depending on the task how to understand if a model is efficient and compare it with others??? - go to - type the model name in search - click on "benchmarks" - you’ll see performance tests and rankings this way you can easily compare free models with paid ones of course there are RPM limits, on many models it’s around ~40 requests per minute each model is different, after generating the API key, RPM limits are shown in the top-right corner nothing stops you from using them, many work perfectly fine, super solid option for first tests and for learning OpenClaw or any other system where you need an AI API model

Ronin

58,789 görüntüleme • 5 ay önce

50% of my consulting work right now is helping companies use open-source models at scale. Everyone knows how to use an open-source LLM on their computers, but it's really hard to do this at scale for thousands of users. Here is how this plays out: 1. A team builds a prototype using DeepSeek. 2. Everything looks good. It works! 3. They follow an online guide to deploy the model online. 4. They ask 10 users to try the app. 5. Latency spikes everywhere. 6. The entire system halts. 7. They blame DeepSeek and try again using a new model. The problem is always with scaling inference, not the model. Here is one recommendation I give companies: Check out Nebius Token Factory if you don't want to ever think about deploying an open-source model again. This is a managed inference platform for deploying open-source LLMs at scale. This is not for prototypes or research experiments. This is for when you have a real application with real users. Three important notes about Token Factory: • You have complete control over how inference runs. • You have predictable tail latency (P99, not averages). • No surprise costs when you scale up. You can preplan your budget. Check it out here: Here are two codes you can use to get 100 hours of GPU usage on me: ymJLFa2ARYSKEdqb AdckcZaYjm7KqYY7 Thanks to the Nebius team for their continuous partnership.
2:40

50% of my consulting work right now is helping companies use open-source models at scale. Everyone knows how to use an open-source LLM on their computers, but it's really hard to do this at scale for thousands of users. Here is how this plays out: 1. A team builds a prototype using DeepSeek. 2. Everything looks good. It works! 3. They follow an online guide to deploy the model online. 4. They ask 10 users to try the app. 5. Latency spikes everywhere. 6. The entire system halts. 7. They blame DeepSeek and try again using a new model. The problem is always with scaling inference, not the model. Here is one recommendation I give companies: Check out Nebius Token Factory if you don't want to ever think about deploying an open-source model again. This is a managed inference platform for deploying open-source LLMs at scale. This is not for prototypes or research experiments. This is for when you have a real application with real users. Three important notes about Token Factory: • You have complete control over how inference runs. • You have predictable tail latency (P99, not averages). • No surprise costs when you scale up. You can preplan your budget. Check it out here: Here are two codes you can use to get 100 hours of GPU usage on me: ymJLFa2ARYSKEdqb AdckcZaYjm7KqYY7 Thanks to the Nebius team for their continuous partnership.

Santiago

48,443 görüntüleme • 5 ay önce

We made a thing! Very happy to announce sqlcoder-pro and the Defog Alignment Platform. Available to use immediately without a wait-list, weights will be open-sourced very soon. The video does a quick show and tell comparison against ChatGPT (with gpt-4o). Read on for more details! TLDR 💪 equal (or better) performance on text-to-SQL as the most capable Claude-3.5 or GPT-4 models 🤝 You can use it today on a free plan/free trial, without a waitlist 🪽 self-hostable on a single RTX4090, with 2 second median generation times for SQL queries 🔁 exactly the same output every time, give the same prompt 👨🏻‍🏫 teachable and steerable: show the model what you want it to do 🛞 debuggable – you can understand WTF is going on inside the model, instead of treating it like a black box Let's dig into each of these one-by-one! Performance SQLCoder-8b-pro significantly exceeds the performance of our previous sqlcoder-8b model on Postgres text-to-SQL (from 88.2% to 90.2% accuracy - gpt-4o is at 87.6%, for reference). It is also better at following instructions. This was done via self-merges, hand crafted fine-tuning data, and adapting the training data to fit our tokenizer. Cost You can host this on the model on a single $3,500 RTX4090, and support ~5 requests/second via VLLM. If you're looking to host on the cloud instead, you can run it on a single L4 GPU that costs $300/mo on GCP Repeatability We have a dense 8b model with no MoE shenanigans. For the same prompt with temperature=0, you'll always get the same answer – which is critical in BI. Teachable In our alignment and feedback modes, you can give the model feedback on how it answered certain questions, and it will automatically adapt to the feedback. Debuggable You can use logprobs and attention scores to determine where, exactly is the model paying attention to inside a prompt + what it's getting confused by when generating outputs. Available today You can use Defog on the cloud today by going to docs[dot]defog[dot]ai, and getting an API key. Excited to hear what you think!
2:33

We made a thing! Very happy to announce sqlcoder-pro and the Defog Alignment Platform. Available to use immediately without a wait-list, weights will be open-sourced very soon. The video does a quick show and tell comparison against ChatGPT (with gpt-4o). Read on for more details! TLDR 💪 equal (or better) performance on text-to-SQL as the most capable Claude-3.5 or GPT-4 models 🤝 You can use it today on a free plan/free trial, without a waitlist 🪽 self-hostable on a single RTX4090, with 2 second median generation times for SQL queries 🔁 exactly the same output every time, give the same prompt 👨🏻‍🏫 teachable and steerable: show the model what you want it to do 🛞 debuggable – you can understand WTF is going on inside the model, instead of treating it like a black box Let's dig into each of these one-by-one! Performance SQLCoder-8b-pro significantly exceeds the performance of our previous sqlcoder-8b model on Postgres text-to-SQL (from 88.2% to 90.2% accuracy - gpt-4o is at 87.6%, for reference). It is also better at following instructions. This was done via self-merges, hand crafted fine-tuning data, and adapting the training data to fit our tokenizer. Cost You can host this on the model on a single $3,500 RTX4090, and support ~5 requests/second via VLLM. If you're looking to host on the cloud instead, you can run it on a single L4 GPU that costs $300/mo on GCP Repeatability We have a dense 8b model with no MoE shenanigans. For the same prompt with temperature=0, you'll always get the same answer – which is critical in BI. Teachable In our alignment and feedback modes, you can give the model feedback on how it answered certain questions, and it will automatically adapt to the feedback. Debuggable You can use logprobs and attention scores to determine where, exactly is the model paying attention to inside a prompt + what it's getting confused by when generating outputs. Available today You can use Defog on the cloud today by going to docs[dot]defog[dot]ai, and getting an API key. Excited to hear what you think!

Rishabh Srivastava

13,460 görüntüleme • 1 yıl önce

My agent is now paying for its own data. No API key. No account. No credit card. Check the video I recorded. This uses the x402 open protocol built by Coinbase, along with a simple skill. This is an open protocol governed by the Linux Foundation. To complete a goal, an agent can now search for an actor on the Apify Store, pay for it, and use it without any human intervention. The way it works is pretty simple: 1. Your agent finds an Actor it wants to use 2. It sends a request 3. The Actor sends back an HTTP 402 "Payment Required" response 4. Agent authorizes payment from a wallet in USDC on Base 5. The Actor runs 6. User receives the result The model is pay-as-you-go: the agent authorizes a spending ceiling, pays only for usage, and the remaining balance is automatically settled. This brings an entire marketplace of AI tools into the agentic economy. Here is the skill you need. Add it to your agent, and it will take care of everything for you: If you want to know how this works, including what you can do with $1, read this post: Thanks to the Apify team for partnering with me on this post.
5:56

My agent is now paying for its own data. No API key. No account. No credit card. Check the video I recorded. This uses the x402 open protocol built by Coinbase, along with a simple skill. This is an open protocol governed by the Linux Foundation. To complete a goal, an agent can now search for an actor on the Apify Store, pay for it, and use it without any human intervention. The way it works is pretty simple: 1. Your agent finds an Actor it wants to use 2. It sends a request 3. The Actor sends back an HTTP 402 "Payment Required" response 4. Agent authorizes payment from a wallet in USDC on Base 5. The Actor runs 6. User receives the result The model is pay-as-you-go: the agent authorizes a spending ceiling, pays only for usage, and the remaining balance is automatically settled. This brings an entire marketplace of AI tools into the agentic economy. Here is the skill you need. Add it to your agent, and it will take care of everything for you: If you want to know how this works, including what you can do with $1, read this post: Thanks to the Apify team for partnering with me on this post.

Santiago

26,589 görüntüleme • 22 gün önce

Here are some tips for those who want to practice face acting: ➡️U motion: Move your head in a "U" Shape so it's never stuck in the same place. This will help your movements look more interesting. ➡️Key points: When practicing with your model, learn to get to a "Key point." This is when you can automatically get to an expression without using toggles. I use surprised and angry expressions a lot, so I know exactly how to move my face to achieve that look, mainly for clips or comedic effect. I practiced enough so I know what it will look like on the model. ➡️Head tilts: If you struggle with face acting, a simple head tilt will go a long way. Overall, the movement and face acting of your model does matter. It can help it look more interesting, but also, it's okay if you can't face acting all the time. Using just key animations when you're gaming will work perfectly. Example: You died in a game, and you go to the key point of surprise. You know, making this face will make your model look shocked, so you will do a dramatic eye open and mouth agape to achieve this, to reflect onto your model. Lastly. The way your model moves is usually 30% rigging artist,20% tracking (webcam/iPhone), and 50% you. Your rigging artist can give you the tools, but only you can make your models' results reflect your emotions. As always, DO YOUR PARAMETERS AND SETTINGS IN VTUBE STUDIO. It will not be perfect to your face and camera settings unless you adjust the model, (This is an old video I did on parameters) Holy Yapfest.
0:36

Here are some tips for those who want to practice face acting: ➡️U motion: Move your head in a "U" Shape so it's never stuck in the same place. This will help your movements look more interesting. ➡️Key points: When practicing with your model, learn to get to a "Key point." This is when you can automatically get to an expression without using toggles. I use surprised and angry expressions a lot, so I know exactly how to move my face to achieve that look, mainly for clips or comedic effect. I practiced enough so I know what it will look like on the model. ➡️Head tilts: If you struggle with face acting, a simple head tilt will go a long way. Overall, the movement and face acting of your model does matter. It can help it look more interesting, but also, it's okay if you can't face acting all the time. Using just key animations when you're gaming will work perfectly. Example: You died in a game, and you go to the key point of surprise. You know, making this face will make your model look shocked, so you will do a dramatic eye open and mouth agape to achieve this, to reflect onto your model. Lastly. The way your model moves is usually 30% rigging artist,20% tracking (webcam/iPhone), and 50% you. Your rigging artist can give you the tools, but only you can make your models' results reflect your emotions. As always, DO YOUR PARAMETERS AND SETTINGS IN VTUBE STUDIO. It will not be perfect to your face and camera settings unless you adjust the model, (This is an old video I did on parameters) Holy Yapfest.

♥️Cutiepierin | L2D RIG ARTIST

93,206 görüntüleme • 9 ay önce

Dario Amodei was asked whether open source will eventually gut Anthropic's business. He didn't defend the moat. He didn't argue closed beats open. He said the whole question is a red herring. That is the reframe. And it flips how the industry keeps scoring this race. The conventional narrative is inherited from the last era of tech: open source wins because anyone can read the code, anyone improves it, contributions stack, and eventually the free thing catches the paid thing. Investors have a full lexicon for it. Commoditization. Which layer captures the value. Everyone repeats it. Amodei says the analogy breaks at the root. It's called open weights, not open source, for a reason: you can't see inside the model. So the thing that actually made open source powerful elsewhere, many people reading and additively improving shared code, never transfers. You just get a large file of numbers. Now here's where it gets interesting. The second engine isn't ideology. It's infrastructure. Free isn't free. Someone still has to host it. These are big models, and they're hard to run inference on. Someone has to make that fast. And the capabilities people assume only open weights unlock fine tuning, steering, inspecting activations labs are increasingly serving on their own clouds anyway. When DeepSeek shipped, he says he never asked whether it was open. He asked one thing: is it a good model, and is it better than us. That's the only axis he competes on. He even inverts the usual edge. Coming from outside that investor lexicon, he thinks knowing none of it lets him predict this better than the people fluent in it. He is not defending closed models. He is saying the scoreboard everyone is watching measures the wrong thing. The uncomfortable question if the free model still needs someone to run it, was the moat ever the weights, or always the machine underneath ?
4:01

Dario Amodei was asked whether open source will eventually gut Anthropic's business. He didn't defend the moat. He didn't argue closed beats open. He said the whole question is a red herring. That is the reframe. And it flips how the industry keeps scoring this race. The conventional narrative is inherited from the last era of tech: open source wins because anyone can read the code, anyone improves it, contributions stack, and eventually the free thing catches the paid thing. Investors have a full lexicon for it. Commoditization. Which layer captures the value. Everyone repeats it. Amodei says the analogy breaks at the root. It's called open weights, not open source, for a reason: you can't see inside the model. So the thing that actually made open source powerful elsewhere, many people reading and additively improving shared code, never transfers. You just get a large file of numbers. Now here's where it gets interesting. The second engine isn't ideology. It's infrastructure. Free isn't free. Someone still has to host it. These are big models, and they're hard to run inference on. Someone has to make that fast. And the capabilities people assume only open weights unlock fine tuning, steering, inspecting activations labs are increasingly serving on their own clouds anyway. When DeepSeek shipped, he says he never asked whether it was open. He asked one thing: is it a good model, and is it better than us. That's the only axis he competes on. He even inverts the usual edge. Coming from outside that investor lexicon, he thinks knowing none of it lets him predict this better than the people fluent in it. He is not defending closed models. He is saying the scoreboard everyone is watching measures the wrong thing. The uncomfortable question if the free model still needs someone to run it, was the moat ever the weights, or always the machine underneath ?

Vikram M

58,688 görüntüleme • 9 gün önce

FREE access to Claude Opus 4.8 just opened on Chorus. Max plan costs $200/month. You can get it for free. Chorus gives you every latest Claude model including Opus 4.8 on the Max plan. Here's the exact flow: → chorus(.)com - register an account → select a plan - hit "continue free trial" → once inside, go to Settings bottom left → Billing - two plans available, Pro and Max → select Max → add your card and confirm. You can delete the card later (I always set up a card with no money on it) Trial works with your own card too - tested it myself, went through without issues. $200/month plan. Free trial. Opus 4.8 available immediately. Window is open right now. This method works right away, I've tried it myself.
0:24

FREE access to Claude Opus 4.8 just opened on Chorus. Max plan costs $200/month. You can get it for free. Chorus gives you every latest Claude model including Opus 4.8 on the Max plan. Here's the exact flow: → chorus(.)com - register an account → select a plan - hit "continue free trial" → once inside, go to Settings bottom left → Billing - two plans available, Pro and Max → select Max → add your card and confirm. You can delete the card later (I always set up a card with no money on it) Trial works with your own card too - tested it myself, went through without issues. $200/month plan. Free trial. Opus 4.8 available immediately. Window is open right now. This method works right away, I've tried it myself.

Atenov int.

131,068 görüntüleme • 1 ay önce

Nothing beats open-source! We now have a fully open-source coding agent that can compete with any proprietary solution out there: • 500+ available models • It doesn't train on your code • It doesn't charge a penny for tokens • It's open. You can change if you want. Kilo Code is the #1 app on OpenRouter right now, and the community is releasing new features on GitHub at rocket speed (about 20 releases in the last 30 days). I installed it in Visual Studio Code, but you can install it in pretty much any IDE. I need to spend more time with it, but here is a very interesting design choice: Most coding agents support two modes: an "agentic" mode for writing code and an "ask" mode for talking to the model without making any changes. Kilo Code supports 5 different modes: 1. Architect mode - Research, design, and planning 2. Debug mode - Problem solving and troubleshooting 3. Code mode - To write code. 4. Ask mode - To talk to the model. 5. Orchestrator mode - Combine every agent to solve problems. On paper, I really like this. I'll need more time to try out the specialized agents and see whether niching becomes an advantage. Here is the link to the website: Thanks to the Kilo for partnering with me on this post.
6:17

Nothing beats open-source! We now have a fully open-source coding agent that can compete with any proprietary solution out there: • 500+ available models • It doesn't train on your code • It doesn't charge a penny for tokens • It's open. You can change if you want. Kilo Code is the #1 app on OpenRouter right now, and the community is releasing new features on GitHub at rocket speed (about 20 releases in the last 30 days). I installed it in Visual Studio Code, but you can install it in pretty much any IDE. I need to spend more time with it, but here is a very interesting design choice: Most coding agents support two modes: an "agentic" mode for writing code and an "ask" mode for talking to the model without making any changes. Kilo Code supports 5 different modes: 1. Architect mode - Research, design, and planning 2. Debug mode - Problem solving and troubleshooting 3. Code mode - To write code. 4. Ask mode - To talk to the model. 5. Orchestrator mode - Combine every agent to solve problems. On paper, I really like this. I'll need more time to try out the specialized agents and see whether niching becomes an advantage. Here is the link to the website: Thanks to the Kilo for partnering with me on this post.

Santiago

73,062 görüntüleme • 8 ay önce