|
Help for using whisper with embeddings
|
|
1
|
110
|
November 22, 2023
|
|
How to calculate the memory required using Lora fine tuning
|
|
0
|
63
|
November 21, 2023
|
|
Find LLM to run on single gpu with only 8 GB ram
|
|
0
|
81
|
November 22, 2023
|
|
LLM security check
|
|
2
|
220
|
November 21, 2023
|
|
BLIP2 generation outputs depends on batch size
|
|
1
|
141
|
November 21, 2023
|
|
Problem while building an ArxivChat bot
|
|
0
|
51
|
November 20, 2023
|
|
Merged LoRA & text generation inference issues
|
|
5
|
941
|
November 20, 2023
|
|
Llama2 torch_dtype
|
|
0
|
103
|
November 20, 2023
|
|
WavLM ECAPA-TDNN embeddings for Speaker verification
|
|
0
|
65
|
November 19, 2023
|
|
<|nospeech|> tokens in seq2seq/whisper
|
|
0
|
66
|
November 19, 2023
|
|
How to train Wav2Vec2 in LoRA?
|
|
1
|
184
|
November 19, 2023
|
|
What is loss function for T5
|
|
10
|
8641
|
November 18, 2023
|
|
LLama2 Finetuning giving RuntimeError: mat1 and mat2 shapes cannot be multiplied (33x4096 and 1x8388608)
|
|
0
|
141
|
November 17, 2023
|
|
Creating a learning agent; to rag on vectordb or finetune
|
|
0
|
52
|
November 17, 2023
|
|
What are the Latest Methods to Evaluate Instruction-Tuned Model on a Custom Test Set?
|
|
0
|
55
|
November 17, 2023
|
|
Supervised BERTopic with multiple topics per document
|
|
7
|
201
|
November 16, 2023
|
|
New DALL•E 3 on HuggingFace
|
|
0
|
176
|
November 16, 2023
|
|
What to do when HuggingFace throws "Can't load tokenizer"
|
|
6
|
18252
|
November 16, 2023
|
|
Exploring optimal deployment strategies for Hugging Face's open-source embedding models in a high-usage, cost-effective environment without vendor lock-in
|
|
0
|
53
|
November 16, 2023
|
|
Transformer model works locally but not in Docker container
|
|
2
|
189
|
November 16, 2023
|
|
Usage of confidential data in querying LLMs
|
|
0
|
59
|
November 15, 2023
|
|
Always output generation config in terminal
|
|
1
|
83
|
November 15, 2023
|
|
How to save inference in local system and how to push the model to hub for layoutlmV3
|
|
0
|
55
|
November 15, 2023
|
|
Help picking a model for semantic search
|
|
1
|
62
|
November 15, 2023
|
|
I need a person identification by voice model
|
|
0
|
64
|
November 14, 2023
|
|
Potential discrepancy between the weights between Huggingface and Timm for google/vit-base-patch16-224-in21k
|
|
0
|
56
|
November 15, 2023
|
|
Different results with model hosted in HuggingFace and hosted in SageMaker
|
|
1
|
84
|
November 15, 2023
|
|
How to pass CLIP image embeddings to BLIP2 for captioning?
|
|
1
|
85
|
November 15, 2023
|
|
Rate limit reached. You reached free usage limit (reset hourly)
|
|
1
|
1989
|
November 14, 2023
|
|
Models with the same params react differently?
|
|
0
|
42
|
November 14, 2023
|