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。

MolmoAct2 runs zero-shot on an SO-ARM101, no training required 🦾 Ai2 open Action Reasoning Model is now in LeRobot with the full lifecycle covered: fine-tuning (full or LoRA), evaluation, and real-robot deployment. It pairs a Molmo2-ER vision-language backbone with a flow-matching action expert to turn images, language, and proprioceptive... show more

LeRobot

18,599 subscribers

22,200 次观看 • 2 个月前 •via X (Twitter)

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

$QVAC SDK will support in 0.9.0 (gonna be release in ~10 days) LoRA fine-tuning directly on-device, letting developers customize LLMs with their own data without sending anything to the cloud. You just load a base model, point it at your training dataset, and get a lightweight LoRA adapter back — all running locally. The fine-tuned model can then be used for inference immediately, with no extra setup. Why it matters: LoRA (Low-Rank Adaptation) fine-tuning lets you specialize a general-purpose language model for your specific use case — like matching a brand's tone, mastering domain terminology, or following a particular output format — using a fraction of the compute a full fine-tune would require. QVAC handles the entire workflow locally: dataset preparation, training with configurable hyperparameters, checkpoint saving, and seamless inference with the resulting adapter. Your data never leaves the device. The developer experience: Fine-tuning with QVAC is as simple as calling "sdk.finetune()" with your dataset and a few hyperparameters. Training runs entirely on your local hardware, produces a compact LoRA adapter file, and supports pause/resume so you can stop a job and pick it back up without losing progress. The result plugs straight into QVAC's inference pipeline — no model conversion, no deployment step, just immediate local completions with your fine-tuned model.$

QVAC SDK will support in 0.9.0 (gonna be release in ~10 days) LoRA fine-tuning directly on-device, letting developers customize LLMs with their own data without sending anything to the cloud. You just load a base model, point it at your training dataset, and get a lightweight LoRA adapter back — all running locally. The fine-tuned model can then be used for inference immediately, with no extra setup. Why it matters: LoRA (Low-Rank Adaptation) fine-tuning lets you specialize a general-purpose language model for your specific use case — like matching a brand's tone, mastering domain terminology, or following a particular output format — using a fraction of the compute a full fine-tune would require. QVAC handles the entire workflow locally: dataset preparation, training with configurable hyperparameters, checkpoint saving, and seamless inference with the resulting adapter. Your data never leaves the device. The developer experience: Fine-tuning with QVAC is as simple as calling "sdk.finetune()" with your dataset and a few hyperparameters. Training runs entirely on your local hardware, produces a compact LoRA adapter file, and supports pause/resume so you can stop a job and pick it back up without losing progress. The result plugs straight into QVAC's inference pipeline — no model conversion, no deployment step, just immediate local completions with your fine-tuned model.

Paolo Ardoino 🤖

42,413 次观看 • 4 个月前

HRM-Text 101 is here. This tutorial takes you from zero to one: from setup to fine-tuning to evaluation. Download the base checkpoint. Fine-tune it on a real task. Evaluate the results. End to end, on a single GPU. Watch the tutorial and start building with HRM-Text.

HRM-Text 101 is here. This tutorial takes you from zero to one: from setup to fine-tuning to evaluation. Download the base checkpoint. Fine-tune it on a real task. Evaluate the results. End to end, on a single GPU. Watch the tutorial and start building with HRM-Text.

Sapient Intelligence

188,398 次观看 • 3 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 • 11 个月前

Chinese robotics company Astribot released their latest World-Action Model (WAM), Lumo-2. Technical breakdown: - based on a frozen 🥶 Qwen-3.5 4B VLM - trained in 3 progressive stages: 1. Action is aligned with latent world dynamics (an abstract representation of action). Real-world actions are anchored to physical constraints, while the latent space is guided to focus on motion-relevant changes. This bidirectional relationship makes the model physically grounded -> critical for a world model. 2. Action is aligned with vision and language. Reusing the vision backbone and action encoder from the frozen VLM, the authors add a custom vocabulary (for new actions), a semantic module, an action decoder, and an action projector. This aligns the (new) action representations with the (existing) vision-language semantic space. Most importantly: it builds a direct mapping from natural-language instructions to motor execution. 3. End-to-end training on language, video, and robot data. Only the new modules (everything outside the frozen backbone) are trained end-to-end across temporal reasoning, physical understanding, long-horizon, and dexterous manipulation. At the end of the day, Lumo-2 is not the best on benchmarks, but that's not the point. What's genuinely new: - a way to combine latent world modeling and action generation through progressive alignment - a physically-grounded latent dynamics space - it lifts performance on unseen objects using un-annotated human egocentric video + Vision Pro captures, no special transfer algorithm needed Why it matters: - the whole model is thin trainable adapters (semantic module, action decoder/projector) on a frozen 4B backbone (cheap) - that scale is suited for real-time embedded inference (~2.71× decode speedup, no accuracy loss) - its real moat is long-horizon execution, where the added temporal memory pays off far more than on any other task As a result, this robot can now make your latte (5x sped up video):

Chinese robotics company Astribot released their latest World-Action Model (WAM), Lumo-2. Technical breakdown: - based on a frozen 🥶 Qwen-3.5 4B VLM - trained in 3 progressive stages: 1. Action is aligned with latent world dynamics (an abstract representation of action). Real-world actions are anchored to physical constraints, while the latent space is guided to focus on motion-relevant changes. This bidirectional relationship makes the model physically grounded -> critical for a world model. 2. Action is aligned with vision and language. Reusing the vision backbone and action encoder from the frozen VLM, the authors add a custom vocabulary (for new actions), a semantic module, an action decoder, and an action projector. This aligns the (new) action representations with the (existing) vision-language semantic space. Most importantly: it builds a direct mapping from natural-language instructions to motor execution. 3. End-to-end training on language, video, and robot data. Only the new modules (everything outside the frozen backbone) are trained end-to-end across temporal reasoning, physical understanding, long-horizon, and dexterous manipulation. At the end of the day, Lumo-2 is not the best on benchmarks, but that's not the point. What's genuinely new: - a way to combine latent world modeling and action generation through progressive alignment - a physically-grounded latent dynamics space - it lifts performance on unseen objects using un-annotated human egocentric video + Vision Pro captures, no special transfer algorithm needed Why it matters: - the whole model is thin trainable adapters (semantic module, action decoder/projector) on a frozen 4B backbone (cheap) - that scale is suited for real-time embedded inference (~2.71× decode speedup, no accuracy loss) - its real moat is long-horizon execution, where the added temporal memory pays off far more than on any other task As a result, this robot can now make your latte (5x sped up video):

Léo

32,331 次观看 • 1 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

Meet VLA-JEPA, the first world model policy in LeRobot 🌍 Most VLAs just learn observation → action. VLA-JEPA also learns action-relevant dynamics: during training, a JEPA world model has to predict upcoming frames in latent space from the model's own actions. Then, at inference, the world model disappears entirely, leaving a standard, fast VLA: Qwen backbone, action head, nothing extra. In our demo it was fine-tuned on just 13 examples and ran in real time on an NVIDIA DGX Spark. On a consumer RTX 3080, it hits 10Hz using under 6GB of VRAM. World-model supervision during training, zero extra cost at inference. That's the whole trick.

Meet VLA-JEPA, the first world model policy in LeRobot 🌍 Most VLAs just learn observation → action. VLA-JEPA also learns action-relevant dynamics: during training, a JEPA world model has to predict upcoming frames in latent space from the model's own actions. Then, at inference, the world model disappears entirely, leaving a standard, fast VLA: Qwen backbone, action head, nothing extra. In our demo it was fine-tuned on just 13 examples and ran in real time on an NVIDIA DGX Spark. On a consumer RTX 3080, it hits 10Hz using under 6GB of VRAM. World-model supervision during training, zero extra cost at inference. That's the whole trick.

LeRobot

42,389 次观看 • 2 个月前

Most robot datasets store one sentence per episode: the task. Real problems need more: a plan, a memory, room to answer questions and change course. We just shipped full language support in the LeRobot dataset format. Now lerobot-annotate points a vision-language model at each episode and writes the subtasks, plans, memory, and grounded Q&A itself - roughly $1.20 for 100 episodes. From there, recipes turn the annotated rows into policy-agnostic training messages, so the same dataset can teach planning, memory, tool calls, or low-level control, no dataset redesign required. Read how it all works on the blog:

Most robot datasets store one sentence per episode: the task. Real problems need more: a plan, a memory, room to answer questions and change course. We just shipped full language support in the LeRobot dataset format. Now lerobot-annotate points a vision-language model at each episode and writes the subtasks, plans, memory, and grounded Q&A itself - roughly $1.20 for 100 episodes. From there, recipes turn the annotated rows into policy-agnostic training messages, so the same dataset can teach planning, memory, tool calls, or low-level control, no dataset redesign required. Read how it all works on the blog:

LeRobot

13,214 次观看 • 1 个月前

GR00T 1.7 just landed in LeRobot 🟢 We upgraded our NVIDIA Robotics GR00T integration to 1.7, the newest open generation of NVIDIA's cross-embodiment foundation model. It swaps the previous VLM for Cosmos-Reason2-2B feeding a flow-matching action head, and we parity-tested it against NVIDIA's own Isaac GR00T implementation: same inputs, same outputs. Flash-attention is now optional too, so pip install 'lerobot[groot]' just works, and you can load NVIDIA's published checkpoints directly. Isaac Teleop is now in the ecosystem too, letting you drive an SO-101 with a VR controller over CloudXR/OpenXR.

GR00T 1.7 just landed in LeRobot 🟢 We upgraded our NVIDIA Robotics GR00T integration to 1.7, the newest open generation of NVIDIA's cross-embodiment foundation model. It swaps the previous VLM for Cosmos-Reason2-2B feeding a flow-matching action head, and we parity-tested it against NVIDIA's own Isaac GR00T implementation: same inputs, same outputs. Flash-attention is now optional too, so pip install 'lerobot[groot]' just works, and you can load NVIDIA's published checkpoints directly. Isaac Teleop is now in the ecosystem too, letting you drive an SO-101 with a VR controller over CloudXR/OpenXR.

LeRobot

19,572 次观看 • 2 个月前

Ex-NVIDIA engineer who built Unsloth explained RL, kernels, reasoning, quantization, and agents in 2 hours 42 minutes - better than $5000 fine-tuning bootcamps. pick the base model -> write triton kernels for 2x faster fine-tune -> quantize to 4-bit -> run GRPO/DPO -> ship a reasoning model on your single GPU. That loop is why Unsloth is the default way to fine-tune Llama, Qwen, Gemma, and Phi on hardware you already own. Unsloth + Triton kernels + 4-bit quantization + GRPO/DPO + single-GPU fine-tuning - that's the stack. Watch and save it, then fine-tune your first model tonight.

Ex-NVIDIA engineer who built Unsloth explained RL, kernels, reasoning, quantization, and agents in 2 hours 42 minutes - better than $5000 fine-tuning bootcamps. pick the base model -> write triton kernels for 2x faster fine-tune -> quantize to 4-bit -> run GRPO/DPO -> ship a reasoning model on your single GPU. That loop is why Unsloth is the default way to fine-tune Llama, Qwen, Gemma, and Phi on hardware you already own. Unsloth + Triton kernels + 4-bit quantization + GRPO/DPO + single-GPU fine-tuning - that's the stack. Watch and save it, then fine-tune your first model tonight.

h100envy

495,680 次观看 • 2 个月前

Introducing W&B Skills for coding agents! Watch us install the skill, point it at a live fine-tuning project with thousands of traces and RL training runs, then query it all from the terminal in seconds. Also works with W&B Weave to pull in your agent traces and spot failures.

Introducing W&B Skills for coding agents! Watch us install the skill, point it at a live fine-tuning project with thousands of traces and RL training runs, then query it all from the terminal in seconds. Also works with W&B Weave to pull in your agent traces and spot failures.

Weights & Biases

264,792 次观看 • 6 个月前

Picking up laundry with a 3D printed robot arm and LeRobot. It operates using SO-ARM101 arm mounted on a mobile base, relying on just a wrist and base camera. The base is controlled with an Xbox controller by a human operator. The arm is fully autonomous thanks to the ACT model. The robot can generalize to previously unseen environments. The technical stack: - Model: Action Chunking Transformer (ACT) with Temporal Ensemble - Data: Learned via teleoperation including negative examples and failure recoveries - Framework: Built and trained locally using LeRobot on a single consumer GPU in 3.5h This is a perfect example that real-world robotics isn't about perfect lab conditions - it's about messy living rooms, confusing shadows, and learning to recover from mistakes. And with open tools, anyone can tackle these edge cases right from their desk.

Picking up laundry with a 3D printed robot arm and LeRobot. It operates using SO-ARM101 arm mounted on a mobile base, relying on just a wrist and base camera. The base is controlled with an Xbox controller by a human operator. The arm is fully autonomous thanks to the ACT model. The robot can generalize to previously unseen environments. The technical stack: - Model: Action Chunking Transformer (ACT) with Temporal Ensemble - Data: Learned via teleoperation including negative examples and failure recoveries - Framework: Built and trained locally using LeRobot on a single consumer GPU in 3.5h This is a perfect example that real-world robotics isn't about perfect lab conditions - it's about messy living rooms, confusing shadows, and learning to recover from mistakes. And with open tools, anyone can tackle these edge cases right from their desk.

LeRobot

68,814 次观看 • 1 个月前

Filmmaker Öner S. Biberkökü shares his "screenshot strategy" for building a full narrative from a single starting point during this In the Flow interview. Thanks Oner for the partnership! "At the end of the shot, you can take a screenshot, give it again [to Flow], and you now have a new image of that character in a different situation... So I think, with one image, you can stay in the flow, and make a story." Watch his breakdown:

Filmmaker Öner S. Biberkökü shares his "screenshot strategy" for building a full narrative from a single starting point during this In the Flow interview. Thanks Oner for the partnership! "At the end of the shot, you can take a screenshot, give it again [to Flow], and you now have a new image of that character in a different situation... So I think, with one image, you can stay in the flow, and make a story." Watch his breakdown:

Google Flow

35,967 次观看 • 6 个月前

Large Language Diffusion with Masking (LLaDA) are here - and their generation looks so fucking dope! 🤯 True to Yann LeCun's vision, Ditch the auto-regressive bits and approximate the language distribution via Maximum Likelihood Estimation! So cool to watch the model denoise text from tokens in real time! - The team released their model checkpoints and there's a demo for you to play with it too! Try it out!🤗

Large Language Diffusion with Masking (LLaDA) are here - and their generation looks so fucking dope! 🤯 True to Yann LeCun's vision, Ditch the auto-regressive bits and approximate the language distribution via Maximum Likelihood Estimation! So cool to watch the model denoise text from tokens in real time! - The team released their model checkpoints and there's a demo for you to play with it too! Try it out!🤗

Vaibhav (VB) Srivastav

21,410 次观看 • 1 年前

you don’t need a robot to see physical ai in action, you just need a browser. this week I finally tried something I've wanted to do for a while: design an SO-101 scene in three.js, connect it to a real leader arm, collect teleoperation data, train an ACT model, then port it to run in the browser. the result is the first ever demo of ACT that runs locally on the web. try it yourself now at

you don’t need a robot to see physical ai in action, you just need a browser. this week I finally tried something I've wanted to do for a while: design an SO-101 scene in three.js, connect it to a real leader arm, collect teleoperation data, train an ACT model, then port it to run in the browser. the result is the first ever demo of ACT that runs locally on the web. try it yourself now at

Binh Pham

121,383 次观看 • 2 个月前

You can now fine-tune Llama 3 without writing a single line of code! We are moving at breakneck speed. I recorded a video to show you how to fine-tune any open-source model in a few minutes. I'm using a GPT capable of taking a problem and turning it into a fine-tuned model that will solve it. You don't have to write any code. You only need to explain to a GPT what problem you want to solve and tell it you want to use Llama 3. For example, "fine-tune Llama 3" or "deploy zephyr." It feels magic. The system will recommend a dataset and fine-tune the model for you. I'm using Monster API, a platform that specializes in making fine-tuning and deploying open-source models easy and fast. Their stack is well-optimized to maximize fine-tuning efficiency using techniques like Q-Lora and vLLM. They are behind the GPT. Here is what you need to do: 1. Create an account at 2. Load the GPT with the link below This is as simple as it gets. When you are done, you can click a button to deploy the model and start using it. I have 10,000 free credits for anyone using the code "SANTIAGO" in the dashboard. You can use these credits to access, fine-tune, and deploy these open-source models. You can also keep up with their latest updates, and get free credits and special offers on their Discord server:

You can now fine-tune Llama 3 without writing a single line of code! We are moving at breakneck speed. I recorded a video to show you how to fine-tune any open-source model in a few minutes. I'm using a GPT capable of taking a problem and turning it into a fine-tuned model that will solve it. You don't have to write any code. You only need to explain to a GPT what problem you want to solve and tell it you want to use Llama 3. For example, "fine-tune Llama 3" or "deploy zephyr." It feels magic. The system will recommend a dataset and fine-tune the model for you. I'm using Monster API, a platform that specializes in making fine-tuning and deploying open-source models easy and fast. Their stack is well-optimized to maximize fine-tuning efficiency using techniques like Q-Lora and vLLM. They are behind the GPT. Here is what you need to do: 1. Create an account at 2. Load the GPT with the link below This is as simple as it gets. When you are done, you can click a button to deploy the model and start using it. I have 10,000 free credits for anyone using the code "SANTIAGO" in the dashboard. You can use these credits to access, fine-tune, and deploy these open-source models. You can also keep up with their latest updates, and get free credits and special offers on their Discord server:

Santiago

324,621 次观看 • 2 年前

Vibe coding is cool. But have you tried vibe-tuning? Here’s Claude Code using the Lightning Rod Labs SDK to turn messy Fed PDFs into a small, specialized economic forecaster. The agent: - parses raw historical PDFs - builds a training set - fine-tunes a smaller model - evaluates it against GPT-5 Result: a fine-tuned model that beats GPT-5 and runs anywhere, on a single GPU. Try it in your coding agent of choice.

Vibe coding is cool. But have you tried vibe-tuning? Here’s Claude Code using the Lightning Rod Labs SDK to turn messy Fed PDFs into a small, specialized economic forecaster. The agent: - parses raw historical PDFs - builds a training set - fine-tunes a smaller model - evaluates it against GPT-5 Result: a fine-tuned model that beats GPT-5 and runs anywhere, on a single GPU. Try it in your coding agent of choice.

Ben Turtel

423,542 次观看 • 3 个月前

VLA-JEPA just dropped in LeRobot 🤖 What makes this model special is that it does not just learn what action to take from a given observation, it also leverages a JEPA world model to learn action-relevant dynamics. During training, the VLA leverages V-JEPA2 by conditioning its predictor. This clever trick adds a world modeling objective to the training, which also allows pretraining on human videos. At inference, the world model is dropped entirely, keeping only a standard VLA architecture: Qwen backbone and action head. The demo here was only fine-tuned on 13 examples, showing great pretraining capability and running in real time on NVIDIA Robotics DGX Spark! VLA-JEPA is the first world model to be ported to LeRobot, and I feel like it won't be the last 🚀 Thomas Wolf clem 🤗

VLA-JEPA just dropped in LeRobot 🤖 What makes this model special is that it does not just learn what action to take from a given observation, it also leverages a JEPA world model to learn action-relevant dynamics. During training, the VLA leverages V-JEPA2 by conditioning its predictor. This clever trick adds a world modeling objective to the training, which also allows pretraining on human videos. At inference, the world model is dropped entirely, keeping only a standard VLA architecture: Qwen backbone and action head. The demo here was only fine-tuned on 13 examples, showing great pretraining capability and running in real time on NVIDIA Robotics DGX Spark! VLA-JEPA is the first world model to be ported to LeRobot, and I feel like it won't be the last 🚀 Thomas Wolf clem 🤗

LeRobot

320,328 次观看 • 3 个月前

New short course on Fine-tuning LLMs! Many developers are moving beyond only prompting, to also fine-tuning LLMs - that is, taking a pre-trained model and training it further on your own data, which can deliver superior results inexpensively. In this course, Sharon Zhou, CEO of Lamini (disclosure: I’m a minor shareholder) shows you how to recognize when fine-tuning can be help, and how to train an open-source LLM on your own data. I hope you enjoy the course!

New short course on Fine-tuning LLMs! Many developers are moving beyond only prompting, to also fine-tuning LLMs - that is, taking a pre-trained model and training it further on your own data, which can deliver superior results inexpensively. In this course, Sharon Zhou, CEO of Lamini (disclosure: I’m a minor shareholder) shows you how to recognize when fine-tuning can be help, and how to train an open-source LLM on your own data. I hope you enjoy the course!

Andrew Ng

502,923 次观看 • 3 年前

How do you know your robot actually succeeded? In v0.6.0, you ask a VLM 🤖 LeRobot ships a new unified reward models API with two zero-shot additions. Robometer is a general-purpose reward model trained on 1M+ trajectories across 21 robot embodiments: point it at any LeRobot dataset and it scores task progress and success straight from video and a language instruction, no task-specific training needed. TOPReward goes even further: no reward weights at all. It wraps an off-the-shelf VLM and reads the log-probability of the token "True" given the video and the instruction. Both come with labeling scripts that write per-frame progress curves into your dataset, ready for reward-aware behavior cloning. More on how they work:

How do you know your robot actually succeeded? In v0.6.0, you ask a VLM 🤖 LeRobot ships a new unified reward models API with two zero-shot additions. Robometer is a general-purpose reward model trained on 1M+ trajectories across 21 robot embodiments: point it at any LeRobot dataset and it scores task progress and success straight from video and a language instruction, no task-specific training needed. TOPReward goes even further: no reward weights at all. It wraps an off-the-shelf VLM and reads the log-probability of the token "True" given the video and the instruction. Both come with labeling scripts that write per-frame progress curves into your dataset, ready for reward-aware behavior cloning. More on how they work:

LeRobot

22,358 次观看 • 1 个月前

The era of Stable Intelligence is here 🤖 Tether’s QVAC Fabric just released the world’s first cross-platform 1-bit LLM LoRA fine-tuning framework. QVAC Fabric extends Microsoft's ultra-efficient BitNet architecture, allowing fine-tuning and inference of LLMs directly on your smartphone—no NVIDIA GPU/CUDA lock-in or expensive server required. The Breakthrough: - Total Sovereignty: LoRA fine-tune ultra-efficient models locally on any smartphone, including iPhones, Pixel phones, Samsung Galaxy phones and any desktop/laptop operating systems using Vulkan and Metal backends. - Extreme Efficiency: 1-bit architecture uses up to 90% less memory and runs up to 11x faster than traditional models. - Universal Access: What used to require a data center now runs on the chip in your pocket. Own your intelligence. The era of stable, local AI is here. 📱🧠 Read the full details on Hugging Face and grab the binaries to build on your own hardware.

The era of Stable Intelligence is here 🤖 Tether’s QVAC Fabric just released the world’s first cross-platform 1-bit LLM LoRA fine-tuning framework. QVAC Fabric extends Microsoft's ultra-efficient BitNet architecture, allowing fine-tuning and inference of LLMs directly on your smartphone—no NVIDIA GPU/CUDA lock-in or expensive server required. The Breakthrough: - Total Sovereignty: LoRA fine-tune ultra-efficient models locally on any smartphone, including iPhones, Pixel phones, Samsung Galaxy phones and any desktop/laptop operating systems using Vulkan and Metal backends. - Extreme Efficiency: 1-bit architecture uses up to 90% less memory and runs up to 11x faster than traditional models. - Universal Access: What used to require a data center now runs on the chip in your pocket. Own your intelligence. The era of stable, local AI is here. 📱🧠 Read the full details on Hugging Face and grab the binaries to build on your own hardware.

QVAC

108,835 次观看 • 5 个月前