Skip to content
This repository has been archived by the owner on Aug 30, 2024. It is now read-only.

Commit

Permalink
remove pdb
Browse files Browse the repository at this point in the history
  • Loading branch information
Zhenzhong1 committed Mar 22, 2024
1 parent b091d75 commit 9e73a0c
Showing 1 changed file with 0 additions and 2 deletions.
2 changes: 0 additions & 2 deletions neural_speed/convert/convert_chatglm.py
Original file line number Diff line number Diff line change
Expand Up @@ -156,8 +156,6 @@ def chatglm3_convert_gguf(model, tokenizer, dir_model, fname_out, ftype, hparams
gguf_file = fname_out
gguf_writer = gguf.GGUFWriter(gguf_file, "chatglm3")
gguf_writer.add_uint32('magic', 0x67676d66)
import pdb
pdb.set_trace()
gguf_writer.add_uint32('version', 1)
gguf_writer.add_uint32('n_vocab', hparams["padded_vocab_size"])
gguf_writer.add_embedding_length(hparams["hidden_size"])
Expand Down

0 comments on commit 9e73a0c

Please sign in to comment.