huggingface-transformers

Fix CUDA device mismatch in multi-GPU PEFT/LoRA training with Hugging Face Transformers 4.49.0

Jan. 11, 15:00

Fix NaN Embeddings in OmniEmbed on Qwen2.5-Omni: Disable Cache, Align Devices, Tame FlashAttention2

Jan. 4, 05:00

DeepSeek-VL2 Tiny Import Error: Fix mismatched deepseek_vl vs deepseek_vl2 module paths fast

Jan. 2, 01:00

Reduce Cold-Start Latency in Hugging Face Transformers with a Minimal Production Warm-Up

Jan. 1, 23:00

Fixing Empty Docling Exports: DocTags to Markdown Fails When load_from_doctags isn't Assigned

Dec. 15, 15:00

Fixing Unsloth GGUF Export Failures for Llama 3: RuntimeError Explained and Workaround

Dec. 12, 15:00

How to Find a Hugging Face Transformers Model's Full Class Definition and Forward Source Code

Nov. 29, 11:00

Fix GitHub Jupyter Notebook Rendering Error: 'state' Missing in metadata.widgets (Guide)

Nov. 26, 07:00

Fix SFTTrainer eos_token errors in TRL for Qwen2.5: Unsloth import order explained

Nov. 25, 03:00

Fixing NVIDIA NV-Embed-v2 ImportError in Transformers: MISTRAL_INPUTS_DOCSTRING mismatch

Nov. 7, 17:00

Align Token Counts for BGE-M3 Embeddings: LlamaIndex vs Hugging Face Tokenizers and Fix

Sep. 25, 15:00

Fix Transformers Import Error: Resolve PyTorch–torchvision/torchaudio CUDA Version Mismatch

Sep. 22, 19:00

Fix LangChain ReAct agent CUDA device mismatch with HuggingFacePipeline on transformers via device=0

Sep. 16, 01:00

1