Hugging Face's logo

nanzhang
/
QuantLRM-R1-Llama-70B-3-bit

Text Generation
Transformers
Safetensors
llama
3-bit
Quantization
Pseudo-Quantization
text-generation-inference
Model card Files
xet
Community
1

Add pipeline tag, library name, and base_model metadata

#1
by nielsr HF Staff - opened
base: refs/heads/main
←
from: refs/pr/1
Discussion Files changed
+4
-5
nielsr

This PR improves the model card by:

  • Adding the pipeline_tag: text-generation for better discoverability.
  • Adding the library_name: transformers as the model uses a Llama architecture and is compatible with the transformers library for loading.
  • Adding base_model: deepseek-ai/DeepSeek-R1-Distill-Llama-70B to clearly link it to its original base model.
  • Removing template placeholder comments from the markdown content for a cleaner presentation.
 Add pipeline tag, library name, and base_model metadata8c28c85e
nanzhang changed pull request status to merged

Sign up or log in to comment