|
Finetune whisper-tiny in german for tflite runtime
|
|
2
|
224
|
October 16, 2024
|
|
Setting `pad_token_id` to `eos_token_id`:128001 for open-end generation
|
|
5
|
4456
|
October 16, 2024
|
|
I have that issue i mainly upload rvc model
|
|
1
|
41
|
October 16, 2024
|
|
Please advise on parameter settings!
|
|
0
|
15
|
October 15, 2024
|
|
Help with a Npl Task
|
|
0
|
10
|
October 15, 2024
|
|
Friends, We have a dataset and want to create a pre-trained model for it. Our data is tabular and very simple. It includes numbers, strings, and some program codes. We have a total of 1000 records. 1- SCOPS 2- Pytorch 3- We can use Pytorch for codes, but
|
|
0
|
16
|
October 13, 2024
|
|
Multi modal models ( REALLY DO WE NEED IT? ) Can a Causal LM sufice?
|
|
2
|
215
|
October 10, 2024
|
|
Word Similarity Models
|
|
1
|
235
|
October 10, 2024
|
|
Encoding masks for Mask2Former and Panopic Segmentation
|
|
2
|
117
|
October 9, 2024
|
|
Low Accuracy and Stagnant Validation Accuracy in BERT Model for Multilabel Classification
|
|
1
|
197
|
October 8, 2024
|
|
Whisper Fine Tuned model cannot used on WhisperX
|
|
4
|
1149
|
October 6, 2024
|
|
mT5 translation tasks only generates <extra__id_0>result
|
|
0
|
32
|
October 4, 2024
|
|
CLIP allows commercial use?
|
|
3
|
761
|
October 4, 2024
|
|
Alibaba-NLP/gte-Qwen2-1.5B-instruct Error when downloading
|
|
3
|
264
|
October 4, 2024
|
|
Can I use Llama in certain part of my Saas?
|
|
1
|
52
|
October 3, 2024
|
|
Meta-Llama-3-8B-Instruct: Validation Error "Max_new_tokens"
|
|
6
|
664
|
October 2, 2024
|
|
Multihead attention
|
|
1
|
91
|
October 2, 2024
|
|
LLaMa3.1 8B Instruct Prompt Tuning for Text Classification doesn't improve test accuracy
|
|
3
|
863
|
October 1, 2024
|
|
Generate Mock but realistic data using NLP
|
|
5
|
195
|
September 29, 2024
|
|
Meta-llama / Meta-Llama-3-70B-Instruct is not available as a serverless API
|
|
10
|
1645
|
September 28, 2024
|
|
What is the best Multilingual NLI model out there? Not able to find many in opensource space
|
|
1
|
400
|
September 28, 2024
|
|
Why are some weights FP32 in Llama 3.1 405B FBGEMM FP8 Quantization?
|
|
7
|
538
|
September 27, 2024
|
|
Training a language model on Arabic data - handling right-to-left text direction
|
|
4
|
2182
|
September 26, 2024
|
|
Wav2vec2 config -- why is mask_time_prob=0.05 and not 0.5?
|
|
1
|
588
|
September 26, 2024
|
|
Seeking uncensored Chatgpt for Creative Writing
|
|
1
|
4420
|
September 26, 2024
|
|
Fine tuning a Facebook TTS model
|
|
1
|
607
|
September 26, 2024
|
|
Sentiment Analysis (5 Level Classification)
|
|
0
|
71
|
September 25, 2024
|
|
How to increase max_new_tokens beyond 1200 in code llama
|
|
2
|
813
|
September 25, 2024
|
|
Wav2Vec2: loss growing in training and validation after few epochs
|
|
6
|
2066
|
September 25, 2024
|
|
Best way to text-to-sql
|
|
1
|
3102
|
September 24, 2024
|