Hugging Face's logo

nm-testing
/
tinyllama-oneshot-w8a8-dynamic-token-v2

Text Generation
Transformers
Safetensors
llama
conversational
text-generation-inference
8-bit precision
compressed-tensors
Model card Files
xet
Community
tinyllama-oneshot-w8a8-dynamic-token-v2
1.23 GB
  • 2 contributors
 History: 7 commits
mgoin's picture
mgoin
Updated compression_config to quantization_config
d3fb66e verified