Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

MLX Swift example can also QLoRA fine-tune Llama 3.2. Here's the 1B fine-tuning on my iPhone 15 Pro at > 150 toks/sec. A this rate only takes a few minutes to learn some decent adapters fully on-device.

Awni Hannun

44,863 subscribers

91,961 views • 2 years ago •via X (Twitter)

Education Health & Wellness Science & Technology

Anya Rossi• Live Now

Private livecam show

10 Comments

Awni Hannun2 years ago

Example is also open-source here (under MIT license):

GPT.Biz2 years ago

This looks amazing! It’s incredible to see fine-tuning done so quickly on a phone

⚡️Dylan White2 years ago

Whoa, that's impressive! Fine-tuning Llama 3.2 on your iPhone 15 Pro is no joke!

involuntarily incelibate2 years ago

If only iOS would expose more substantial endpoints, you could fine tune “Siri”!

Janaka2 years ago

Impressive

Andres Gomez Sarmiento2 years ago

really cool

Kalin Ovtcharov2 years ago

Ability to run llms locally on-device and fine tune them is an extremely important yet relatively under-appreciated/ignored capability today. I expect that will change as new applications emerge that leverage SLMs. I expect some governments may even ban them in the near future.

Josep M. Ganyet2 years ago

@Scobleizer @xaviviro

Sorayesh Semo2 years ago

Awesome

samuel abraham gomez villafuerte2 years ago

Para andriod cuando

Related Videos

Next level: QLoRA fine-tuning 4-bit Llama 3 8B on iPhone 15 pro. Incoming (Q)LoRA MLX Swift example by David Koski: works with lot's of models (Mistral, Gemma, Phi-2, etc)

Next level: QLoRA fine-tuning 4-bit Llama 3 8B on iPhone 15 pro. Incoming (Q)LoRA MLX Swift example by David Koski: works with lot's of models (Mistral, Gemma, Phi-2, etc)

Awni Hannun

581,777 views • 2 years ago

Demo of Tether's QVAC running local inference on a mobile device at incredible speed, via llama.cpp + LLAMA 3.2 1B parameters. QVAC is a generalized inference and fine-tuning runtime able to adapt to any device, from smartphones, to laptops and servers. Lots of models being supported already. More to come. No limits. Infinite intelligence. Coming soon

Demo of Tether's QVAC running local inference on a mobile device at incredible speed, via llama.cpp + LLAMA 3.2 1B parameters. QVAC is a generalized inference and fine-tuning runtime able to adapt to any device, from smartphones, to laptops and servers. Lots of models being supported already. More to come. No limits. Infinite intelligence. Coming soon

Paolo Ardoino 🤖

42,122 views • 1 year ago

$I just added the new Llama 3.2 1B and 3B models to LitGPT, the open-source LLM library I help develop (focused on efficiency and code readability). LitGPT allows you to fine-tune and use these models on the cloud or a laptop. So, if you are looking for something to play with this weekend: # 1) Finetune the model litgpt finetune_lora meta-llama/Llama-3.2-1B \ --data JSON \ --data.json_path my_custom_dataset.json \ --train.epochs 1 \ --out_dir out/llama-3.2-finetuned \ --precision bf16-true # 2) Chat with the model litgpt chat out/llama-3.2-finetuned/final # 3) Serve the model via an API endpoint litgpt serve out/llama-3.2-finetuned/final$

I just added the new Llama 3.2 1B and 3B models to LitGPT, the open-source LLM library I help develop (focused on efficiency and code readability). LitGPT allows you to fine-tune and use these models on the cloud or a laptop. So, if you are looking for something to play with this weekend: # 1) Finetune the model litgpt finetune_lora meta-llama/Llama-3.2-1B \ --data JSON \ --data.json_path my_custom_dataset.json \ --train.epochs 1 \ --out_dir out/llama-3.2-finetuned \ --precision bf16-true # 2) Chat with the model litgpt chat out/llama-3.2-finetuned/final # 3) Serve the model via an API endpoint litgpt serve out/llama-3.2-finetuned/final

Sebastian Raschka

65,529 views • 2 years ago

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 views • 2 years ago

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 views • 2 months ago

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

188,651 views • 4 months ago

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

496,831 views • 2 months ago

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 views • 2 months ago

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

502,962 views • 3 years ago

QVAC first demo (android mobile) of its local on-device fine-tuning generalized framework, which aims to bring LORA fine-tuning to any device, scaling from the smallest embedded device to any smartphone, laptop, server, operating system. In combination with WIP multi-node features, we expect QVAC to become the standard for local on-device single/multi node inference and fine-tuning. Imagine a horde of AI agents being able to learn from your emails, notes and messages, maintaining 100℅ privacy, leveraging only your own devices. A P2P private intelligence network at your fingertips. That's how QVAC personal assistant will look like. Future of Intelligence won't be centralized. Infinite Ingelligence vibes.

QVAC first demo (android mobile) of its local on-device fine-tuning generalized framework, which aims to bring LORA fine-tuning to any device, scaling from the smallest embedded device to any smartphone, laptop, server, operating system. In combination with WIP multi-node features, we expect QVAC to become the standard for local on-device single/multi node inference and fine-tuning. Imagine a horde of AI agents being able to learn from your emails, notes and messages, maintaining 100℅ privacy, leveraging only your own devices. A P2P private intelligence network at your fingertips. That's how QVAC personal assistant will look like. Future of Intelligence won't be centralized. Infinite Ingelligence vibes.

Paolo Ardoino 🤖

142,888 views • 10 months ago

Google engineer explained how to fine-tune a tiny LLM from 46% to 90% accuracy on your phone in 21 minutes - better than $1500 on-device AI bootcamps. pick Gemma 270M -> generate synthetic task data -> fine-tune with LoRA -> quantize to int4 -> deploy to Pixel and hit 2000 tokens per second. That loop is how a 270M model beats a 70B one on your task, running fully offline in your pocket. Gemma 270M + synthetic data + LoRA + int4 quantization + on-device runtime - that's the stack. Watch and save it, then fine-tune your own tiny agent tonight.

Google engineer explained how to fine-tune a tiny LLM from 46% to 90% accuracy on your phone in 21 minutes - better than $1500 on-device AI bootcamps. pick Gemma 270M -> generate synthetic task data -> fine-tune with LoRA -> quantize to int4 -> deploy to Pixel and hit 2000 tokens per second. That loop is how a 270M model beats a 70B one on your task, running fully offline in your pocket. Gemma 270M + synthetic data + LoRA + int4 quantization + on-device runtime - that's the stack. Watch and save it, then fine-tune your own tiny agent tonight.

h100envy

709,544 views • 2 months ago

Before Claude Fable 5 got banned, I turned all my fine-tuning research and experiments into a product: (A CLI for data generation to fine-tune AI models). Finetuner uses Codex 5.5 or Opus 4.8 as the orchestrator and Chinese models (DeepSeek v4 Pro, Kimi K2.7, MiMo v2.5, etc.) to generate dataset rows. This system is unique because these are not Python-script-paraphrased datasets. Each and every row is handcrafted by Chinese models based on the orchestrator model's instructions. Now anyone can generate datasets to fine-tune small language models (1B to 30B models). I achieved 10x lower costs and 5x better dataset quality. Releasing the product in a few days. (I'll open-source the skills.)

Before Claude Fable 5 got banned, I turned all my fine-tuning research and experiments into a product: (A CLI for data generation to fine-tune AI models). Finetuner uses Codex 5.5 or Opus 4.8 as the orchestrator and Chinese models (DeepSeek v4 Pro, Kimi K2.7, MiMo v2.5, etc.) to generate dataset rows. This system is unique because these are not Python-script-paraphrased datasets. Each and every row is handcrafted by Chinese models based on the orchestrator model's instructions. Now anyone can generate datasets to fine-tune small language models (1B to 30B models). I achieved 10x lower costs and 5x better dataset quality. Releasing the product in a few days. (I'll open-source the skills.)

CJ Zafir

40,211 views • 3 months ago

You can now vibecode your own WisprFlow or Monologue alternative that runs completely locally on Apple Silicon using MLX-Audio-Swift 🔥 Check out this live transcription of Dwarkesh Patel interview with Andrej Karpathy using Qwen3-ASR-0.6B quantized to 4bit on a M3 Max. It also runs in realtime on a iPhone 15 Pro and iPad Pro M1. No cloud. No API keys.

You can now vibecode your own WisprFlow or Monologue alternative that runs completely locally on Apple Silicon using MLX-Audio-Swift 🔥 Check out this live transcription of Dwarkesh Patel interview with Andrej Karpathy using Qwen3-ASR-0.6B quantized to 4bit on a M3 Max. It also runs in realtime on a iPhone 15 Pro and iPad Pro M1. No cloud. No API keys.

Prince Canuma

60,974 views • 7 months ago

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

61,697 views • 1 year ago

Holy sh*t, developers are going to lose their minds over this. Someone open sourced a repo that lets you fine-tune 100+ LLMs and VLMs without building the training pipeline yourself. Llama. Qwen. DeepSeek. Gemma. Mistral. And more. It's called LLaMA-Factory and here's why it changes everything: → 100+ open-source LLMs + VLMs → LoRA + QLoRA → SFT + DPO + PPO → multimodal fine-tuning → experiment tracking → Web UI You don't need to train the next frontier model. You can take a much smaller model and make it extremely good at one specific job. most people haven't done that yet. full guide in the article below

Holy sh*t, developers are going to lose their minds over this. Someone open sourced a repo that lets you fine-tune 100+ LLMs and VLMs without building the training pipeline yourself. Llama. Qwen. DeepSeek. Gemma. Mistral. And more. It's called LLaMA-Factory and here's why it changes everything: → 100+ open-source LLMs + VLMs → LoRA + QLoRA → SFT + DPO + PPO → multimodal fine-tuning → experiment tracking → Web UI You don't need to train the next frontier model. You can take a much smaller model and make it extremely good at one specific job. most people haven't done that yet. full guide in the article below

Rahul

34,785 views • 11 days ago

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

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 views • 1 year ago

"Introducing Multimodal Llama 3.2": As promised two weeks ago, here's the short course on Meta's latest open model! This short course is created with Meta and taught by Amit Sangani, Director of AI Partner Engineering at Meta. Meta’s Llama family of models is leading the way in open models, allowing anyone to download, customize, fine-tune, or build new applications on top of them. Learn about the vision capabilities of the Llama 3.2, and use it for image classification, prompting, tokenization, tool-calling. You'll also learn about the open-source Llama stack, which gives building blocks for many different stages of the LLM application life cycle. In detail, you’ll: - Learn what are the features of Meta's four newest models, and when to use which Llama model. - Learn best practices for multimodal prompting, with applications to advanced image reasoning, illustrated by many examples: Understanding errors on a car dashboard, adding up the total of photographed restaurant receipts, grading written math homework. - Use different roles—system, user, assistant, ipython—in the Llama 3.1 and 3.2 models and the prompt format that identifies those roles. - Understand how Llama uses the tiktoken tokenizer, and how it has expanded to a 128k vocabulary size that improves encoding efficiency and multilingual support. - Learn how to prompt Llama to call built-in and custom tools (functions) with examples for web search and solving math equations. - Learn about Llama Stack, a standardized interface for common toolchain components like fine-tuning or synthetic data generation, useful for building agentic applications. By the end of this course, you’ll be equipped to build out new applications with the new Llama 3.2. Thank you to Ahmad Al-Dahle, Amit Sangani, and the whole AI at Meta team AI at Meta for all the hard work on Llama 3.2 — we’re excited to make these open models even more accessible to more developers with this new course! Please sign up here!

"Introducing Multimodal Llama 3.2": As promised two weeks ago, here's the short course on Meta's latest open model! This short course is created with Meta and taught by Amit Sangani, Director of AI Partner Engineering at Meta. Meta’s Llama family of models is leading the way in open models, allowing anyone to download, customize, fine-tune, or build new applications on top of them. Learn about the vision capabilities of the Llama 3.2, and use it for image classification, prompting, tokenization, tool-calling. You'll also learn about the open-source Llama stack, which gives building blocks for many different stages of the LLM application life cycle. In detail, you’ll: - Learn what are the features of Meta's four newest models, and when to use which Llama model. - Learn best practices for multimodal prompting, with applications to advanced image reasoning, illustrated by many examples: Understanding errors on a car dashboard, adding up the total of photographed restaurant receipts, grading written math homework. - Use different roles—system, user, assistant, ipython—in the Llama 3.1 and 3.2 models and the prompt format that identifies those roles. - Understand how Llama uses the tiktoken tokenizer, and how it has expanded to a 128k vocabulary size that improves encoding efficiency and multilingual support. - Learn how to prompt Llama to call built-in and custom tools (functions) with examples for web search and solving math equations. - Learn about Llama Stack, a standardized interface for common toolchain components like fine-tuning or synthetic data generation, useful for building agentic applications. By the end of this course, you’ll be equipped to build out new applications with the new Llama 3.2. Thank you to Ahmad Al-Dahle, Amit Sangani, and the whole AI at Meta team AI at Meta for all the hard work on Llama 3.2 — we’re excited to make these open models even more accessible to more developers with this new course! Please sign up here!

Andrew Ng

131,846 views • 2 years ago