|
Different results from checkpoint evaluation when loading fine-tuned LLM model
|
|
4
|
808
|
September 21, 2023
|
|
Finetuned model of Codellam
|
|
0
|
14
|
September 21, 2023
|
|
Weird output from model.generate()
|
|
1
|
596
|
September 21, 2023
|
|
Position Embedding error in HuggingFace
|
|
1
|
20
|
September 21, 2023
|
|
Error when loading weights
|
|
0
|
14
|
September 21, 2023
|
|
Repeatedly decoding tokens multiple times after PEFT fine-tuning whisper
|
|
2
|
160
|
September 20, 2023
|
|
Text classification training on long text
|
|
0
|
24
|
September 19, 2023
|
|
LLM fine tuning for E-commerce product recommendation
|
|
0
|
20
|
September 19, 2023
|
|
GPT4all in a personal server to be access by many users
|
|
0
|
30
|
September 19, 2023
|
|
Sentence similarity - how to train it dynamically
|
|
0
|
29
|
September 18, 2023
|
|
Other aggregation on TAPAS beyond (SUM/COUNT/AVERAGE/NONE)
|
|
13
|
842
|
September 18, 2023
|
|
Decicoder finetune error: understanding naive_attention_prefill
|
|
1
|
103
|
September 17, 2023
|
|
Text Web UI Generation Blanks (goes Black) on a Character
|
|
0
|
34
|
September 17, 2023
|
|
The Correct Attention Mask For Examples Packing
|
|
1
|
99
|
September 16, 2023
|
|
Generate without using the generate method
|
|
6
|
1957
|
September 15, 2023
|
|
GPTQ+PEFT model running very slowly at inference
|
|
3
|
131
|
September 14, 2023
|
|
Trainer.train() will cause PretrainedConfig default construct
|
|
0
|
27
|
September 14, 2023
|
|
Although doing RAG does it worth fine tuning the LLM on the documents? - Llama2
|
|
1
|
91
|
September 14, 2023
|
|
Training Fails after multiple passes: ValueError: The model did not return a loss from the inputs
|
|
2
|
1640
|
September 11, 2023
|
|
Ai chatbot for lms
|
|
0
|
75
|
September 9, 2023
|
|
Fine tuning evaluation decode problem
|
|
0
|
48
|
September 8, 2023
|
|
Finetuning Scibert and encountering ValueError
|
|
0
|
41
|
September 8, 2023
|
|
How to run an end to end example of distributed data parallel with hugging face's trainer api (ideally on a single node multiple gpus)?
|
|
17
|
7279
|
September 6, 2023
|
|
Extractive Q&A - HF pipeline top_k returns same span as different answers
|
|
0
|
45
|
September 6, 2023
|
|
Reduced inference f1 score with QLoRA finetuned model
|
|
1
|
79
|
September 6, 2023
|
|
Huggingface using only half of the cores for inference
|
|
0
|
47
|
September 6, 2023
|
|
Why does Hugging Face's push_to_hub convert saved models to .bin instead of using safetensor mode?
|
|
2
|
87
|
September 6, 2023
|
|
Training Loss = 0.0, Validation Loss = nan
|
|
6
|
2618
|
September 5, 2023
|
|
SAM image size for fine-tuning
|
|
3
|
615
|
September 5, 2023
|
|
How to change the label names in Hosted Inference API results
|
|
0
|
47
|
September 5, 2023
|