vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-09 16:44:35 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

llama : add jinja template for rwkv-world (#14665)

Browse source 
* llama : add jinja template for rwkv-world

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

* Update convert_hf_to_gguf.py

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

---------

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
This commit is contained in:
Molly Sophia 2025-07-14 07:43:43 +08:00 • committed by GitHub
parent 982e347255
commit 0d9226763c
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 43 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

9
convert_hf_to_gguf.py
View file

@ -1082,7 +1082,14 @@ class TextModel(ModelBase):
self.gguf_writer.add_token_list(tokens)
self.gguf_writer.add_token_types(toktypes)
special_vocab = gguf.SpecialVocab(self.dir_model, load_merges=False)
special_vocab.chat_template = "rwkv-world"
if special_vocab.chat_template is None:
template_path = Path(__file__).parent / "models" / "templates" / "llama-cpp-rwkv-world.jinja"
if template_path.is_file():
with open(template_path, "r", encoding="utf-8") as f:
template = f.read()
else:
template = "rwkv-world"
special_vocab.chat_template = template
# hack: Add '\n\n' as the EOT token to make it chat normally
special_vocab._set_special_token("eot", 261)
# hack: Override these as they have already been set (incorrectly)