Feature Extraction
Transformers
Safetensors
llama
text-classification
reward-model
rlhf
sparse-autoencoder
interpretability
custom_code
text-embeddings-inference
Instructions to use Schrieffer/Llama-SARM-4B-PostSAEPretrain with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Schrieffer/Llama-SARM-4B-PostSAEPretrain with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="Schrieffer/Llama-SARM-4B-PostSAEPretrain", trust_remote_code=True)# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("Schrieffer/Llama-SARM-4B-PostSAEPretrain", trust_remote_code=True) model = AutoModelForSequenceClassification.from_pretrained("Schrieffer/Llama-SARM-4B-PostSAEPretrain", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Add pipeline tag and library name
#1
by nielsr HF Staff - opened
This PR improves the model card by adding relevant metadata:
library_name: transformers: Enables the "how to use" widget on the model page with a Transformers code snippet.pipeline_tag: feature-extraction: Ensures the model can be found under the correct task category on the Hugging Face Hub.
Schrieffer changed pull request status to merged