正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

The introduction of Workflows, Model Fine-tuning, Apps for Advertising and more. Get caught up on what happened This Week with Runway.

Runway

261,307 subscribers

18,527 次观看 • 10 个月前 •via X (Twitter)

艺术科学技术

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

The launch of Apps, new models added to the Runway API and a community showcase featuring Sway Molina. Get caught up on what happened This Week with Runway.

The launch of Apps, new models added to the Runway API and a community showcase featuring Sway Molina. Get caught up on what happened This Week with Runway.

Runway

21,356 次观看 • 10 个月前

Audio nodes, new models and more new features and improvements in Workflows, a detailed custom Workflow walkthrough and a community spotlight. Get caught up on what happened This Week with Runway.

Audio nodes, new models and more new features and improvements in Workflows, a detailed custom Workflow walkthrough and a community spotlight. Get caught up on what happened This Week with Runway.

Runway

22,369 次观看 • 9 个月前

New updates and features for workflows, tips on creating seamless transitions when modifying video and a community showcase from our Discord. Get caught up on what happened This Week with Runway.

New updates and features for workflows, tips on creating seamless transitions when modifying video and a community showcase from our Discord. Get caught up on what happened This Week with Runway.

Runway

19,976 次观看 • 11 个月前

The general release of Runway Aleph on both web and via API. A community showcase. And our weekly Discord challenge. Get caught up on what happened This Week with Runway.

The general release of Runway Aleph on both web and via API. A community showcase. And our weekly Discord challenge. Get caught up on what happened This Week with Runway.

Runway

26,632 次观看 • 1 年前

The release of our next generation motion capture model, Act-Two. How to use it. And some great work from the community. Get caught up on what happened This Week with Runway.

The release of our next generation motion capture model, Act-Two. How to use it. And some great work from the community. Get caught up on what happened This Week with Runway.

Runway

27,030 次观看 • 1 年前

New Aleph features and mobile updates, Gen-4 Image Turbo comes to the API and another community showcase. Get caught up on what happened This Week with Runway.

New Aleph features and mobile updates, Gen-4 Image Turbo comes to the API and another community showcase. Get caught up on what happened This Week with Runway.

Runway

36,152 次观看 • 1 年前

Today we’re introducing the Apps for Advertising collection. A growing library of easy-to-use apps inside of Runway that allow you to get from idea to deliverable with less time, money and effort. From generating endless product shots for social and e-commerce to mocking up designs in real world placements, the Apps for Advertising collection is designed to help your teams get the most out of Runway without the need for complicated prompting or advanced workflows. Learn more below and get started today. 1/5

Today we’re introducing the Apps for Advertising collection. A growing library of easy-to-use apps inside of Runway that allow you to get from idea to deliverable with less time, money and effort. From generating endless product shots for social and e-commerce to mocking up designs in real world placements, the Apps for Advertising collection is designed to help your teams get the most out of Runway without the need for complicated prompting or advanced workflows. Learn more below and get started today. 1/5

Runway

35,664 次观看 • 10 个月前

Introducing Apps, an easier way to create anything with Runway. From reshooting your products to restyling images, Apps are an ever-growing collection of use case specific workflows that make it easier than ever to get to great outputs. Apps are now rolling out on web, with more releasing every week. Have an app idea you’d like to see? Let us know in the comments. Learn more about the launch collection below and start creating with Runway Apps today. (1/7)

Introducing Apps, an easier way to create anything with Runway. From reshooting your products to restyling images, Apps are an ever-growing collection of use case specific workflows that make it easier than ever to get to great outputs. Apps are now rolling out on web, with more releasing every week. Have an app idea you’d like to see? Let us know in the comments. Learn more about the launch collection below and start creating with Runway Apps today. (1/7)

Runway

136,066 次观看 • 10 个月前

Revolutionizing Move Programming with OpenLedger In this demo, we showcase how Move datasets contributed by data providers to OpenLedger’s datanets are used to fine-tune specialized models with LoRA fine-tuning. As seen in the video, we showcase an example on how builders can deploy a Move-specialized model that powers Co-pilot agents using our no-code model fine-tuning platform. This is the future of AI and Web3 innovation. Watch this space to see more specialised models and data feeds being built for next generation agents on top of OpenLedger #Move

Revolutionizing Move Programming with OpenLedger In this demo, we showcase how Move datasets contributed by data providers to OpenLedger’s datanets are used to fine-tune specialized models with LoRA fine-tuning. As seen in the video, we showcase an example on how builders can deploy a Move-specialized model that powers Co-pilot agents using our no-code model fine-tuning platform. This is the future of AI and Web3 innovation. Watch this space to see more specialised models and data feeds being built for next generation agents on top of OpenLedger #Move

OpenLedger

61,693 次观看 • 1 年前

This week's Hermes Agent masterclass is on subagents and delegation! In this clip, I set up a more expensive parent agent for orchestration with a cheaper model for the children subagents doing the research. See how you can get 5x cheaper workflows with this setup!

This week's Hermes Agent masterclass is on subagents and delegation! In this clip, I set up a more expensive parent agent for orchestration with a cheaper model for the children subagents doing the research. See how you can get 5x cheaper workflows with this setup!

tonbi

43,818 次观看 • 2 个月前

OpenAI engineer explained every form of fine-tuning in 1 hour 46 minutes - better than $3000 fine-tuning bootcamps. pick your task -> try prompting first -> drop to SFT for style -> run DPO for preference -> run RFT for verifiable rewards -> ship a model 10x cheaper than GPT-5. That loop is why teams that fine-tune beat teams that only prompt on cost and speed. Prompting + SFT + DPO + RFT + OpenAI fine-tuning API - that's the stack. Watch and save it, then pick the right fine-tune for your task this week.

OpenAI engineer explained every form of fine-tuning in 1 hour 46 minutes - better than $3000 fine-tuning bootcamps. pick your task -> try prompting first -> drop to SFT for style -> run DPO for preference -> run RFT for verifiable rewards -> ship a model 10x cheaper than GPT-5. That loop is why teams that fine-tune beat teams that only prompt on cost and speed. Prompting + SFT + DPO + RFT + OpenAI fine-tuning API - that's the stack. Watch and save it, then pick the right fine-tune for your task this week.

h100envy

41,245 次观看 • 1 个月前

I went up to Flux 2 Klein 9B param model with 2 steps This model is seriously under rated and will look forward to fine tuning one.

I went up to Flux 2 Klein 9B param model with 2 steps This model is seriously under rated and will look forward to fine tuning one.

Dev Ed

112,550 次观看 • 6 个月前

Remember reinforcement fine-tuning? We’ve been working away at it since last December, and it’s available today with OpenAI o4-mini! RFT uses chain-of-thought reasoning and task-specific grading to improve model performance—especially useful for complex domains. Take Accordance, which used RFT to fine-tune a model that’s SOTA for their tax and accounting purposes. And in supervised fine-tuning news: you can now fine-tune GPT-4.1 nano. Get even more from our fastest, cheapest model by training it specifically for your use-case.

Remember reinforcement fine-tuning? We’ve been working away at it since last December, and it’s available today with OpenAI o4-mini! RFT uses chain-of-thought reasoning and task-specific grading to improve model performance—especially useful for complex domains. Take Accordance, which used RFT to fine-tune a model that’s SOTA for their tax and accounting purposes. And in supervised fine-tuning news: you can now fine-tune GPT-4.1 nano. Get even more from our fastest, cheapest model by training it specifically for your use-case.

OpenAI Developers

666,346 次观看 • 1 年前

⚡ Ship AI apps faster with Genkit → Benefit from multi-model support, intuitive Dev UI for testing, and full observability of your AI workflows.

⚡ Ship AI apps faster with Genkit → Benefit from multi-model support, intuitive Dev UI for testing, and full observability of your AI workflows.

Google for Developers

13,893 次观看 • 9 个月前

$still experimenting with LoRA based on the Thinking Machines configuration and just implemented it in colab. In this notebook I set up a fine tune of Qwen/Qwen3-0.6B on the OpenR1-Math dataset with lora rank of 1. with this setup you can get the same reward accuracy as full fine-tuning, at a fraction of vram usage.$

still experimenting with LoRA based on the Thinking Machines configuration and just implemented it in colab. In this notebook I set up a fine tune of Qwen/Qwen3-0.6B on the OpenR1-Math dataset with lora rank of 1. with this setup you can get the same reward accuracy as full fine-tuning, at a fraction of vram usage.

Ben Burtenshaw

25,624 次观看 • 10 个月前

Ex-JPMorgan engineer who wrote the LLM Course explained everything about fine-tuning and merging in 18 minutes - better than $2500 fine-tuning bootcamps. pick the base -> LoRA or QLoRA -> then DPO or KTO for alignment -> merge two fine-tunes into one stronger model -> ship a model that beats the base on your task. That loop is why Labonne's merges sit at the top of the Hugging Face leaderboard. LoRA + QLoRA + DPO + KTO + mergekit - that's the stack. Watch and save it, then merge your first two fine-tunes this week.

Ex-JPMorgan engineer who wrote the LLM Course explained everything about fine-tuning and merging in 18 minutes - better than $2500 fine-tuning bootcamps. pick the base -> LoRA or QLoRA -> then DPO or KTO for alignment -> merge two fine-tunes into one stronger model -> ship a model that beats the base on your task. That loop is why Labonne's merges sit at the top of the Hugging Face leaderboard. LoRA + QLoRA + DPO + KTO + mergekit - that's the stack. Watch and save it, then merge your first two fine-tunes this week.

h100envy

13,856 次观看 • 1 个月前

Loading.......this week's updates…….⏳ Loading complete! Get caught up with This Week On XBOX:

Loading.......this week's updates…….⏳ Loading complete! Get caught up with This Week On XBOX:

XBOX

396,694 次观看 • 1 个月前