|
Retrieving avg_logprob and other metrics for segments using whisper
|
|
1
|
12
|
October 23, 2025
|
|
Model loading gets stuck when calling "from_pretrained"
|
|
10
|
1193
|
October 23, 2025
|
|
Contrastive search output type issue
|
|
0
|
9
|
October 23, 2025
|
|
Getting -100 in predictions from T5 during compute_metrics
|
|
2
|
19
|
October 22, 2025
|
|
Model not using all attention layers while inferencing on device_map="auto"
|
|
2
|
16
|
October 21, 2025
|
|
ValueError when using PatchTSTForClassification
|
|
4
|
157
|
October 20, 2025
|
|
WARN Status Code: 500
|
|
13
|
358
|
October 20, 2025
|
|
500 Internal Server Error when downloading model files (works for metadata, fails on large files)
|
|
1
|
119
|
October 20, 2025
|
|
PatchTSMixerForPrediction error with prediction of len 1
|
|
3
|
142
|
October 19, 2025
|
|
How to avert 'loading checkpoint shards'?
|
|
5
|
13530
|
October 17, 2025
|
|
How can I train a Polish-English translation Transformer model from scratch using PyTorch or Hugging Face?
|
|
0
|
11
|
October 16, 2025
|
|
SpiralTorch — a Rust-first ML stack that trains in Z-space (WebGPU/WASM/MPS/CUDA). It ships a tokenizer-free pre-embedding path and a Canvas Transformer projector that can feed HF Transformers via `inputs_embeds`
|
|
1
|
14
|
October 15, 2025
|
|
Quesiton about bf16 in Transformers
|
|
2
|
39
|
October 13, 2025
|
|
CUDA Deadlock while training DETR
|
|
3
|
14
|
October 11, 2025
|
|
AutoTokenizer 404 error issue
|
|
2
|
68
|
October 11, 2025
|
|
Persistent 404 Error on Inference API with Verified Account & Valid Token
|
|
1
|
43
|
October 10, 2025
|
|
Error 404 when downloading the tokenizer
|
|
2
|
430
|
October 7, 2025
|
|
Mes Spaces restent bloqués sur “Starting” malgré abonnement Pro et hébergement GPU
|
|
3
|
59
|
October 6, 2025
|
|
Unexpected behaviors of Compute_Metrics
|
|
2
|
23
|
October 6, 2025
|
|
How To add custom LLM architecture to transformersitectute
|
|
1
|
16
|
October 4, 2025
|
|
Using huggingface as a hosting / CDN for a pretrained model
|
|
2
|
170
|
October 3, 2025
|
|
Trainer class, compute_metrics and EvalPrediction
|
|
8
|
14710
|
October 3, 2025
|
|
How to make T5 model know when to stop generating during inference?
|
|
2
|
23
|
October 1, 2025
|
|
` transformers` '4.57.0.dev0' is not compatible with `evaluate`?
|
|
2
|
127
|
September 30, 2025
|
|
Questions about loading checkpoint by `.from_pretrained`
|
|
1
|
9
|
September 29, 2025
|
|
I don't get it why Llama.cpp / GGML is so much faster than PyTorch
|
|
3
|
131
|
September 27, 2025
|
|
Run_glue.py provides higher GLUE score on bert-base-uncased
|
|
2
|
295
|
September 26, 2025
|
|
Using AutoVideoProcessor or SmolVLMVideoProcessor for RTSP and Local Video Input
|
|
3
|
31
|
September 25, 2025
|
|
Confusion about Mistral Small 24B 3.1 head_dim calculation
|
|
1
|
10
|
September 24, 2025
|
|
SAM2 video streaming – VRAM usage keeps increasing until OOM
|
|
5
|
76
|
September 22, 2025
|