Feature Extraction
Transformers
Safetensors
English
codexembed2b
code
embeddings
similarity
algorithmic-diversity
custom_code
Instructions to use jangraanubhav/codex-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jangraanubhav/codex-sft with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="jangraanubhav/codex-sft", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("jangraanubhav/codex-sft", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
CodeX-SFT v1: SFR-Embedding-Code-2B_R fine-tuned on DivAlgo judge ratings, with calibration head and threshold
26315d8 verified Download tokenizer.json from jangraanubhav/codex-sft: direct link, hf CLI and curl.
- Browser
- Download file 17.5 MB
-
https://huggingface.co/jangraanubhav/codex-sft/resolve/main/tokenizer.json
- Command line
-
hf download hf://jangraanubhav/codex-sft/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/jangraanubhav/codex-sft/resolve/main/tokenizer.json
17.5 MB
- Xet hash:
- f860575da4b138af1d132258e5adb6b7412a0f50897fcbc4dce85bb0507af4c2
- Size of remote file:
- 17.5 MB
- SHA256:
- d3ac7f76285fd4496ef32e22e3889b68592e2d12565f91be035ae776bf3dd3ee
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.