CoolFace
Modelpublic

RichardErkhov/BSC-LT_-_Checkpoint_2b_instructed_beta-gguf

sourceHugging Faceupdated 2y agoView on Hugging Face
0likes667downloads
Model Card

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Checkpoint2binstructed_beta - GGUF

  • —Model creator: https://huggingface.co/BSC-LT/
  • —Original model: https://huggingface.co/BSC-LT/Checkpoint2binstructed_beta/
NameQuant methodSize
Checkpoint_2b_instructed_beta.Q2_K.ggufQ2_K1.01GB
Checkpoint_2b_instructed_beta.IQ3_XS.ggufIQ3_XS1.11GB
Checkpoint_2b_instructed_beta.IQ3_S.ggufIQ3_S1.13GB
Checkpoint_2b_instructed_beta.Q3_K_S.ggufQ3KS1.13GB
Checkpoint_2b_instructed_beta.IQ3_M.ggufIQ3_M1.16GB
Checkpoint_2b_instructed_beta.Q3_K.ggufQ3_K1.19GB
Checkpoint_2b_instructed_beta.Q3_K_M.ggufQ3KM1.19GB
Checkpoint_2b_instructed_beta.Q3_K_L.ggufQ3KL1.23GB
Checkpoint_2b_instructed_beta.IQ4_XS.ggufIQ4_XS1.28GB
Checkpoint_2b_instructed_beta.Q4_0.ggufQ4_01.31GB
Checkpoint_2b_instructed_beta.IQ4_NL.ggufIQ4_NL1.32GB
Checkpoint_2b_instructed_beta.Q4_K_S.ggufQ4KS1.35GB
Checkpoint_2b_instructed_beta.Q4_K.ggufQ4_K1.4GB
Checkpoint_2b_instructed_beta.Q4_K_M.ggufQ4KM1.4GB
Checkpoint_2b_instructed_beta.Q4_1.ggufQ4_11.41GB
Checkpoint_2b_instructed_beta.Q5_0.ggufQ5_01.51GB
Checkpoint_2b_instructed_beta.Q5_K_S.ggufQ5KS1.53GB
Checkpoint_2b_instructed_beta.Q5_K.ggufQ5_K1.57GB
Checkpoint_2b_instructed_beta.Q5_K_M.ggufQ5KM1.57GB
Checkpoint_2b_instructed_beta.Q5_1.ggufQ5_11.61GB
Checkpoint_2b_instructed_beta.Q6_K.ggufQ6_K1.79GB
Checkpoint_2b_instructed_beta.Q8_0.ggufQ8_02.24GB

Original model description: --- license: apache-2.0 libraryname: transformers pipelinetag: text-generation --- 2b Version of model Sxxxxxx, without last epoch, instructed with baseline dataset including RAG_Multilingual