8000 Add NeoBERT by huydt84 · Pull Request #14164 · ggml-org/llama.cpp · GitHub
[go: up one dir, main page]
Skip to content

Add NeoBERT #14164

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

Merged
merged 8 commits into from
Jun 16, 2025
Merged

Add NeoBERT #14164

Changes from 1 commit
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
9bb46ee
convert neobert model to gguf
huydt-bti Jun 13, 2025
116ee89
add inference graph
huydt-bti Jun 13, 2025
55fa0c2
fix flake8 lint
huydt-bti Jun 13, 2025
d82eacf
followed reviewer suggestions
huydt84 Jun 13, 2025
9863d02
follow reviewers suggestions
huydt84 Jun 13, 2025
6481a68
Merge branch 'ggml-org:master' into huydt/neobert
huydt84 Jun 15, 2025
44e9400
Merge branch 'master' into huydt/neobert
huydt-bti Jun 16, 2025
b989962
override NeoBERT feed-forward length
huydt-bti Jun 16, 2025
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
Prev Previous commit
Next Next commit
follow reviewers suggestions 
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
  • Loading branch information
@huydt84 @ggerganov
huydt84 and ggerganov authored Jun 13, 2025
commit 9863d020e2b5eb0a2a4f4372098c77d1554a2b7d
6 changes: 3 additions & 3 deletions src/llama-model.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -740,9 +740,9 @@ void llama_model::load_hparams(llama_model_loader & ml) {
} break;
case LLM_ARCH_NEO_BERT:
{
ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps);
ml.get_key(LLM_KV_ATTENTION_CAUSAL, hparams.causal_attn);
ml.get_key(LLM_KV_POOLING_TYPE, hparams.pooling_type);
ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps);
ml.get_key(LLM_KV_ATTENTION_CAUSAL, hparams.causal_attn);
ml.get_key(LLM_KV_POOLING_TYPE, hparams.pooling_type);

if (hparams.n_layer == 28) {
type = LLM_TYPE_250M;
Expand Down
Loading
0