|
Practicality and Efficiency of Using Non-Power-of-Two Context Lengths in Fine-Tuning Hugging Face Models for SFT or Fine-Tuning
|
|
0
|
17
|
August 8, 2024
|
|
Question About the Practicality of the Context Length
|
|
3
|
6161
|
August 8, 2024
|
|
Dreambooth not generating model_index.json and thus is not able to make inference
|
|
6
|
2450
|
August 7, 2024
|
|
Mistral 7b gives suggestion questions and queries while generating sql query
|
|
0
|
55
|
August 7, 2024
|
|
HF Albert pretrained model missing some keys in state_dict()
|
|
0
|
12
|
August 7, 2024
|
|
One Line LLM Fine Tuning PyPI Package
|
|
0
|
23
|
August 7, 2024
|
|
Doubt about find model
|
|
1
|
32
|
August 7, 2024
|
|
For the Seq2SeqTrainingArguments class, what happens when I set both adafactor=True and set a learning rate?
|
|
1
|
342
|
August 6, 2024
|
|
Question about body params of "Get endpoint metric" request
|
|
0
|
8
|
August 7, 2024
|
|
A machine learning library that allows you to easily train agents
|
|
0
|
134
|
August 7, 2024
|
|
How to chose the platform functionality
|
|
0
|
13
|
August 7, 2024
|
|
Training GPT-type models for classification tasks CausalLM vs SequenceClassification
|
|
2
|
1054
|
August 7, 2024
|
|
How to see what part of model are offloaded to CPU?
|
|
1
|
118
|
August 7, 2024
|
|
Text Classification Without using Auto Model For Sequence Classification
|
|
0
|
31
|
August 7, 2024
|
|
Help needed in finetuning pix2struct in DocVQA type dataset
|
|
1
|
389
|
August 7, 2024
|
|
Process data shards
|
|
0
|
40
|
August 7, 2024
|
|
How dataset.map() reads data
|
|
0
|
19
|
August 6, 2024
|
|
Question regarding CLIP's model open-sourceness and commerciality
|
|
4
|
2661
|
August 7, 2024
|
|
How to make a huggingface chatbot spaces?
|
|
0
|
93
|
August 7, 2024
|
|
How do I get logits from an Inference API Wav2Vec2 model?
|
|
1
|
54
|
August 6, 2024
|
|
Big dataset when being tokenized using map function gives type error as TypeError: TextEncodeInput must be Union[TextInputSequence, Tuple[InputSequence, InputSequence]]
|
|
0
|
182
|
August 6, 2024
|
|
Transformer trackers pretrained weights
|
|
0
|
6
|
August 6, 2024
|
|
Track include_num_input_tokens_seen in Trainer
|
|
0
|
120
|
August 6, 2024
|
|
Extract data from text and parse it as a JSON
|
|
6
|
21572
|
August 6, 2024
|
|
Load Phi 3 small on Nvidia Tesla V100 - Flash Attention
|
|
3
|
850
|
August 6, 2024
|
|
My adapter model dominating the entire base model
|
|
1
|
114
|
August 6, 2024
|
|
Problems with seeing my newly created assistant from Assistants Tab
|
|
0
|
18
|
August 6, 2024
|
|
Set_seed and training argument's data_seed
|
|
2
|
137
|
August 6, 2024
|
|
Multi GPU traning with Accelerator vs Trainer
|
|
2
|
155
|
August 6, 2024
|
|
How to implement bind_tools to custom LLM from huggingface pipeline(Llama-3) for a custom agent
|
|
1
|
1165
|
August 5, 2024
|