Summarization
Transformers
Safetensors
qwen3_5_text
text-generation
merged
sft
context-compaction
agents
egirl
Instructions to use schneewolflabs/Compactor-Qwen3.5-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use schneewolflabs/Compactor-Qwen3.5-4B with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "summarization" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("summarization", model="schneewolflabs/Compactor-Qwen3.5-4B")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("schneewolflabs/Compactor-Qwen3.5-4B") model = AutoModelForCausalLM.from_pretrained("schneewolflabs/Compactor-Qwen3.5-4B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tokenizer.json from schneewolflabs/Compactor-Qwen3.5-4B: direct link, hf CLI and curl.
- Browser
- Download file 20 MB
-
https://huggingface.co/schneewolflabs/Compactor-Qwen3.5-4B/resolve/main/tokenizer.json
- Command line
-
hf download hf://schneewolflabs/Compactor-Qwen3.5-4B/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/schneewolflabs/Compactor-Qwen3.5-4B/resolve/main/tokenizer.json
20 MB
- Xet hash:
- 777bcaa63794fa47b8f53680be9d6d176f1fcbd7ba03cdc6c3bae2b3d76b323f
- Size of remote file:
- 20 MB
- SHA256:
- 06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.