Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fix OLMo HF to GGUF conversion #6910

Merged
merged 5 commits into from
May 7, 2024
Merged

Fix OLMo HF to GGUF conversion #6910

Changes from 1 commit
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
00f3fb6
fix setting clamp_qkv value in OLMo conversion
nopperl Apr 25, 2024
c807683
add OLMo to pre-tokenizer generation script
nopperl May 5, 2024
da41960
Merge branch 'update-olmo-tokenizer' into fix-olmo-conversion
nopperl May 5, 2024
6943250
add OLMo to pre-tokenizer function
nopperl May 5, 2024
25be8f5
implment olmo pre-tokenizer type in llama.cpp
nopperl May 7, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 3 additions & 2 deletions convert-hf-to-gguf.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2764,8 +2764,9 @@ class OlmoModel(Model):
def set_gguf_parameters(self):
super().set_gguf_parameters()
self.gguf_writer.add_layer_norm_eps(1e-5)
if "clip_qkv" in self.hparams is not None:
self.gguf_writer.add_clamp_kqv(self.hparams["clip_qkv"])
clip_qkv = self.hparams.get("clip_qkv")
if clip_qkv is not None:
self.gguf_writer.add_clamp_kqv(clip_qkv)

# Same as super class, but permuting q_proj, k_proj
# Copied from: LlamaModel
Expand Down
Loading