StackOverflow Questions for Tag: fine-tuning

Ruoxi

Reputation: 253

Why does LLM supervised fine tuning only need small amounts of data?

large-language-modelfine-tuning

Score: 0

Answers: 0

Abdullah Algumar

Reputation: 1

How to Optimize Costs for Real-Time High-Volume GPT API Usage (2M+ Requests Daily)?

artificial-intelligenceopenai-apifine-tuninggpt-4

Score: -2

Answers: 0

itachi0510

Reputation: 1

Using `bitsandbytes` 4-bit quantization requires the latest version of bitsandbytes: `pip install -U bitsandbytes`

pythonmachine-learninghuggingface-transformerslarge-language-modelfine-tuning

Score: 0

Answers: 1

zenitsu Agastuma

Reputation: 1

How to approach performance testing and memory leak analysis for a .NET application

.netmemory-leaksperformance-testingload-testingfine-tuning

Score: 0

Answers: 2

Ron Libman

Reputation: 31

Cuda out of memory while training

nlptokenizelarge-language-modelfine-tuning

Score: 0

Answers: 0

Olga Nikitina

Reputation: 41

Loss stays constant at ~1.0 during training DPO

large-language-modelfine-tuning

Score: 4

Answers: 0

AYUSH NATH TIWARI

Reputation: 1

Context Length Limitation When Fine-Tuning Llama 3.1 in Colab

machine-learningdeep-learningartificial-intelligencellamafine-tuning

Score: 0

Answers: 1

Rishi Garg

Reputation: 1

Is it possible to Fine-Tune TinyBERT on Mac (M1 chip)?

deep-learningnlphuggingface-transformerstext-classificationfine-tuning

Score: -1

Answers: 1

Kartik Bali

Reputation: 31

Llama 3: Getting a CUDA unknown error while fine tuning Llama 3 on wikitext

pythonpytorchlarge-language-modelllamafine-tuning

Score: 0

Answers: 0

New

Reputation: 3

TrOCR fine tuning in Mac M4 chip (MPS)

pythonmacospytorchocrfine-tuning

Score: 0

Answers: 1

Bruno

Reputation: 1459

HuggingFace Pretrained Model for Fine-Tuning has 100% Trainable Parameters

huggingface-transformersfine-tuning

Score: 2

Answers: 0

Pulkit Pareek

Reputation: 1

ValueError: Could not interpret optimizer identifier: <keras.src.optimizers.adam.Adam object at 0x336f637d0>

python-3.xtensorflowkerashuggingface-transformersfine-tuning

Score: 0

Answers: 0

John

Reputation: 327

Multiple gpu fine-tuning does not accelerate?

torchlarge-language-modelmulti-gpufine-tuning

Score: 0

Answers: 0

Anay

Reputation: 579

Fine-Tuning Large Language Model on PDFs containing Text and Images

machine-learningextractopenai-apilarge-language-modelfine-tuning

Score: 0

Answers: 1

Silvia A

Reputation: 1

RuntimeError: Internal Triton PTX codegen error while trying to train model Llama-3

runtime-errorgoogle-colaboratoryllamafine-tuningtriton

Score: 0

Answers: 1

Mael Fosso

Reputation: 400

SVM tuning process: Caused by error in `vectbl_recycle_rhs_rows()`:

rmachine-learningsvmtidymodelsfine-tuning

Score: 0

Answers: 0

Anika Sharma

Reputation: 7

Issues during LoRA Fine-Tuning: Got unexpected arguments: {'num_items_in_batch': 8192}

pythonfine-tuning

Score: -1

Answers: 1

youtube

Reputation: 404

Huggingface trainer is not showing any progress for finetuning

pythonhuggingface-transformershuggingface-tokenizersfine-tuninghuggingface-trainer

Score: 0

Answers: 0

user62939

Reputation: 11

Finetuning with 8.1B Llama with LORA but responses are just repetitions of the inputs on inference

pytorchlarge-language-modelllamafine-tuning

Score: 1

Answers: 0

Infomagier

Reputation: 329

Fine Tune Huggingface model via Trainer API without labels?

huggingface-transformerslarge-language-modelhuggingfacefine-tuninghuggingface-trainer

Score: 0

Answers: 1

PreviousPage 1Next

StackOverflow Questions for Tag: fine-tuning

Why does LLM supervised fine tuning only need small amounts of data?

How to Optimize Costs for Real-Time High-Volume GPT API Usage (2M+ Requests Daily)?

Using `bitsandbytes` 4-bit quantization requires the latest version of bitsandbytes: `pip install -U bitsandbytes`

How to approach performance testing and memory leak analysis for a .NET application

Cuda out of memory while training

Loss stays constant at ~1.0 during training DPO

Context Length Limitation When Fine-Tuning Llama 3.1 in Colab

Is it possible to Fine-Tune TinyBERT on Mac (M1 chip)?

Llama 3: Getting a CUDA unknown error while fine tuning Llama 3 on wikitext

TrOCR fine tuning in Mac M4 chip (MPS)

HuggingFace Pretrained Model for Fine-Tuning has 100% Trainable Parameters

ValueError: Could not interpret optimizer identifier: &lt;keras.src.optimizers.adam.Adam object at 0x336f637d0&gt;

Multiple gpu fine-tuning does not accelerate?

Fine-Tuning Large Language Model on PDFs containing Text and Images

RuntimeError: Internal Triton PTX codegen error while trying to train model Llama-3

SVM tuning process: Caused by error in `vectbl_recycle_rhs_rows()`:

Issues during LoRA Fine-Tuning: Got unexpected arguments: {&#39;num_items_in_batch&#39;: 8192}

Huggingface trainer is not showing any progress for finetuning

Finetuning with 8.1B Llama with LORA but responses are just repetitions of the inputs on inference

Fine Tune Huggingface model via Trainer API without labels?

ValueError: Could not interpret optimizer identifier: <keras.src.optimizers.adam.Adam object at 0x336f637d0>

Issues during LoRA Fine-Tuning: Got unexpected arguments: {'num_items_in_batch': 8192}