Text Generation
PEFT
Safetensors
English
lora
fine-tuned-model
instruction-tuning
adaptation
parameter-efficient-finetuning
conversational
Instructions to use npc0/directional-embedder-v0.3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use npc0/directional-embedder-v0.3 with PEFT:
from peft import PeftModel from transformers import AutoModel base_model = AutoModel.from_pretrained("Qwen/Qwen3-Embedding-0.6B") model = PeftModel.from_pretrained(base_model, "npc0/directional-embedder-v0.3") - Notebooks
- Google Colab
- Kaggle
Download tokenizer.json from npc0/directional-embedder-v0.3: direct link, hf CLI and curl.
- Browser
- Download file 11.4 MB
-
https://huggingface.co/npc0/directional-embedder-v0.3/resolve/main/tokenizer.json
- Command line
-
hf download hf://npc0/directional-embedder-v0.3/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/npc0/directional-embedder-v0.3/resolve/main/tokenizer.json
11.4 MB
- Xet hash:
- 707ffdc2de83521acc0780ec1af52bf0f4bbab9bdb5ff85d4a144076ec1b16e7
- Size of remote file:
- 11.4 MB
- SHA256:
- c1c0f2a0940504af6a8bf439af1de17c0188ae0a6623af7fe428866f6fe37794
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.