vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

convert-falcon-hf-to-gguf.py : remove extra kv

Browse source
This commit is contained in:
klosax 2023-08-19 00:31:28 +02:00 • committed by GitHub
parent d5e976c12b
commit 16ab9ba3b3
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 0 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

1
convert-falcon-hf-to-gguf.py
View file

@ -94,7 +94,6 @@ print("gguf: get model metadata")
block_count = hparams["n_layer"]
gguf_writer.add_architecture()
gguf_writer.add_name(last_dir)
gguf_writer.add_context_length(2048)
gguf_writer.add_embedding_length(hparams["hidden_size"])