CoolFace
Modelpublic

BricksDisplay/Soprano-1.1-80M-GGUF

sourceHugging Faceapache-2.0updated 5mo agoView on Hugging Face
0likes123downloads
Model Card

Soprano-1.1-80M-GGUF

GGUF conversions of `ekwek/Soprano-1.1-80M` (LLM part only).

Files

  • —Soprano-1.1-80M.F16.gguf
  • —Soprano-1.1-80M.Q2_K.gguf
  • —Soprano-1.1-80M.Q3_K_M.gguf
  • —Soprano-1.1-80M.Q4_K_M.gguf
  • —Soprano-1.1-80M.Q5_K_M.gguf
  • —Soprano-1.1-80M.Q6_K.gguf
  • —Soprano-1.1-80M.Q8_0.gguf

Notes

  • —Converted with llama.cpp convert_hf_to_gguf.py and quantized with llama-quantize.
  • —Tokenizer pre-tokenizer is custom; conversion currently maps it to gpt-2 pretokenizer for llama.cpp compatibility.