How do I actually get to ask a question , where is the Playground
|
|
9
|
208
|
October 6, 2023
|
Inference input token number set as the max length always?
|
|
10
|
162
|
April 21, 2024
|
Error when running a text classification task
|
|
9
|
171
|
April 23, 2024
|
Convert_to_parquet fails for datasets with multiple configs
|
|
9
|
89
|
May 16, 2024
|
SSL Certificate Issue
|
|
5
|
10903
|
April 23, 2024
|
Using device_map='auto' for training
|
|
3
|
18124
|
August 17, 2023
|
The download of a model is too slow
|
|
0
|
4591
|
September 2, 2023
|
Having trouble loading a fine-tuned PEFT model (CodeLlama-13b-Instruct-hf base)
|
|
1
|
1777
|
November 21, 2023
|
ERROR: Failed building wheel for tokenizers
|
|
0
|
3670
|
December 16, 2023
|
Hugging Face pretrained models in android studio
|
|
0
|
661
|
August 28, 2023
|
LLM model for table data
|
|
7
|
23882
|
February 1, 2024
|
Using Google's Gemini for scientific literature
|
|
0
|
1090
|
December 14, 2023
|
From Crypto Mining to LLM Fine-tuning: Unlocking Large Language Model Fine-tuning through Collaborative Compute Pools
|
|
2
|
1087
|
April 25, 2024
|
Task_type parameter of LoraConfig
|
|
5
|
5954
|
February 25, 2024
|
LoRA vs QLoRA finetuning performance on llama2
|
|
0
|
2232
|
September 4, 2023
|
ImportError: Using the Trainer with PyTorch: Seq2SeqTrainingArguments
|
|
4
|
4356
|
June 17, 2023
|
Inference API has been turned off for this model
|
|
0
|
891
|
June 6, 2023
|
Recent Critical Issue with Hub, Links and 429 Error
|
|
0
|
1598
|
July 27, 2023
|
Fine-tuning TrOCR on new language
|
|
0
|
889
|
October 12, 2023
|
How does one do full fine-tuning on Falcon 180B?
|
|
0
|
1501
|
September 8, 2023
|
Is LLaMA rotary embedding implementation correct?
|
|
5
|
3281
|
April 10, 2024
|
Chat with a PDF
|
|
7
|
14673
|
March 13, 2024
|
[ssl: certificate_verify_failed]
|
|
1
|
2728
|
April 29, 2024
|
Getting warning message on creation of WeightedLossTrainer object
|
|
1
|
1391
|
April 19, 2024
|
How to avert 'loading checkpoint shards'?
|
|
2
|
6385
|
May 14, 2024
|
Question about loss calculation on LLM finetuning
|
|
0
|
5494
|
July 14, 2023
|
Getting Error when Finetuning Llama2 via Qlora in FSDP
|
|
0
|
1135
|
October 2, 2023
|
LLM fine tuning for E-commerce product recommendation
|
|
0
|
987
|
September 19, 2023
|
Subscription tiers descriptions unclear; e.g. "higher rate limits" doesn't specify what the rate limit is
|
|
0
|
1033
|
June 18, 2023
|
NotImplementedError when loading dataset with Streamlit
|
|
5
|
6650
|
December 22, 2023
|
Constraining an LLM output to match a regular expression
|
|
0
|
515
|
February 25, 2024
|
Some clarification on Conv1D
|
|
1
|
1100
|
May 1, 2024
|
Loading Llama 2 with quantization on M1 MacBooks
|
|
2
|
4535
|
December 15, 2023
|
Two errors (Xformers not installed correctly; 'RWForCausalLM' not supported) on my first attempt
|
|
4
|
5826
|
April 11, 2024
|
How to get username from inside the app in private huggingface spaces?
|
|
0
|
278
|
August 6, 2023
|
TypeError: LlamaForCausalLM.__init__() got an unexpected keyword argument 'load_in_4bit'
|
|
7
|
14617
|
October 7, 2023
|
Adding domain knowledge in LLMs via fine tuning
|
|
2
|
3646
|
July 23, 2023
|
Model "xxx" was not found on hub!
|
|
1
|
73519
|
November 2, 2023
|
Feature-request: add commit to 'push' event webhook payloads
|
|
2
|
249
|
November 1, 2023
|
Downloading a model from the hub without loading it
|
|
5
|
2577
|
November 6, 2023
|
Multi-GPU LLM inference data parallelism (llama)
|
|
1
|
7101
|
October 25, 2023
|
Number of tokens (2331) exceeded maximum context length (512) error.Even when model supports 8k Context length
|
|
7
|
11483
|
December 25, 2023
|
Getting cannot import name 'is_npu_available' from 'accelerate.utils'
|
|
1
|
3985
|
August 18, 2023
|
HFValidationError: Repo id must be in the form 'repo_name' or 'namespace/repo_name':
|
|
1
|
7029
|
November 9, 2023
|
How to finetune with a own private data and then build chatbot on that?
|
|
5
|
7716
|
April 22, 2024
|
Supervised Fine-tuning Trainer - Custom Loss Function
|
|
2
|
1964
|
February 12, 2024
|
Loss Increases But Metrics Get Better?
|
|
0
|
348
|
August 28, 2023
|
Support for docker-compose in spaces
|
|
1
|
1210
|
June 1, 2023
|
Dark theme on Hugging Face website by default
|
|
0
|
2698
|
July 15, 2023
|
Transformers Trainer + Accelerate FSDP: How do I load my model from a checkpoint?
|
|
2
|
2738
|
January 17, 2024
|