Pavan singer reddy

Road to Success - Work under Progress 😁😁😼

[Pavan singer reddy @k_pavansinger]

@onepluscareIN Hey @onepluscareIN, you're just repeating service center notes instead of solving my motherboard replacement issue. I DM'd full details—please check and actually fix this instead of going back and forth. @oneplus @OnePlus_IN @OnePlus_Support

[Pavan singer reddy @k_pavansinger]

Hey @oneplus @OnePlus_IN, my OnePlus Nord 5 screen suddenly went completely black and won't restart, even with the power button. Customer care says service centers are closed today even though it is tuesday(weekday)What can I do to fix this ASAP? Please help #OnePlusSupport

[Pavan singer reddy @k_pavansinger]

@kamlesh9mishra @oneplus @OnePlus_IN You can also do the same if you have any issues with your one plus even if they don't replace the motherboard we can file a complaint in e-dakil
I have proper proof of similar issue happening to most of the users after the recent oneplus software update just after their warrenty.

[Pavan singer reddy @k_pavansinger]

@onepluscareIN Hi @onepluscareIN replied to the dm could you please check and resolve my issue
#OnePlus #OnePlusCare #OnePlusService #NeverSettle

[Pavan singer reddy @k_pavansinger]

@onepluscareIN Hi @onepluscareIN, no response to my DM. Visited your service center today—told my motherboard needs replacement just 1 year after purchase (bought last Sept). Phone has zero scratches/drops. Dying right after warranty feels like a scam. Please help!
@oneplus @OnePlus_IN

[Pavan singer reddy @k_pavansinger]

@realmeIndia he realme team I want to unlock the bootloader of my realme 5 pro but your deep test app is not working and when I try to apply through it it is getting closed is there any other way to unlock the bootloader of my device or will the indepth test app works ?

[Itamar Golan 🤓 @ItakGol]

I can't believe I've just fine-tuned a 33B-parameter LLM on Google Colab in a few hours.😱

Insane announcement for any of you using open-source LLMs on normal GPUs! 🤯

A new paper has been released, QLoRA, which is nothing short of game-changing for the ability to train and fine-tune LLMs on consumers' GPUs.

In a few words:

QLoRA reduces the memory usage of LLM fine-tuning without any performance tradeoffs compared to standard 16-bit model fine-tuning.

This method enables 33B model fine-tuning on a single 24GB GPU and 65B model fine-tuning on a single 46GB GPU. This is incredible! 😍

More specifically, QLoRA uses 4-bit quantization to compress a pre-trained language model. The LM parameters are then frozen, and a relatively small number of trainable parameters are added to the model in the form of Low-Rank Adapters.

During finetuning, QLoRA backpropagates gradients through the frozen 4-bit quantized pretrained language model into the Low-Rank Adapters. The LoRA layers are the only parameters being updated during training. Read more about LoRA in the original LoRA paper (https://t.co/54Lsb4DBFi). 🤓

QLoRA has one storage data type (usually 4-bit NormalFloat) for the base model weights and a computation data type (16-bit BrainFloat) used to perform computations. QLoRA dequantizes weights from the storage data type to the computation data type to perform the forward and backward passes, but only computes weight gradients for the LoRA parameters, which use 16-bit bfloat. The weights are decompressed only when they are needed, therefore the memory usage stays low during training and inference. Beautiful!😱

QLoRA tuning is shown to match 16-bit finetuning methods in a wide range of experiments. In addition, the Guanaco models, which use QLoRA finetuning for LLaMA models on the OpenAssistant dataset (OASST1), are state-of-the-art chatbot systems and are close to ChatGPT on the Vicuna benchmark. This is an additional demonstration of the power of QLoRA tuning.

Their Guanaco models are reaching 99.3% of the performance level of ChatGPT while only requiring 24 hours of fine-tuning on a single GPU. You can actually do it in Google Colab.

📚 Links-

QLoRA Paper - https://t.co/srUrDq4PS6
Colab for inference - https://t.co/iBtmLleCLf
Colab for fine-tuning - https://t.co/8eZQLxKozM
GitHub Repository- https://t.co/Jo50Ltn1Xw
Use it with HuggingFace - https://t.co/TWT0xPfr2g

[How Things Are Manufactured @fastworkers6]

How to make the best paper airplane  https://t.co/xnRbbp1Nkv

[Pavan singer reddy @k_pavansinger]

@AzureSupport Hey @AzureSupport team I have sent you a private message as you have requested please check the problem thanks in advance

[Nikhil Chawla @nikhilchawla]

People: Let’s complain about RedMi K20 Pro (SD855) pricing. Why? Because someone thought it should be 25K and is now devastated 😭

Me: You guys are ridiculous. Even if it was priced 20k you’d have complained🤦🏻‍♂️

Samsung: Hold my beer 🍺 Launches A80 with SD730 for ₹47,990/-

[Pavan singer reddy @k_pavansinger]

@chunkynerd Who will buy k20 pro when we have one plus 7 oxygen os is more refreshed and close to stock Android with added features but miui has adds which is annoying who wants to buy a phone which has adds when they are paying 28000 Rupees

[Pavan singer reddy @k_pavansinger]

@manukumarjain @Google Iam really tired of your flash sales I want to buy Redmi note 7 pro from flash sales but within milliseconds it shows the product is out of stock now I will go with real me 3 pro even though they are small company they are providing good time to buy a smart phone in flash sales