diff options
| author | Douglas Hanley <thesecretaryofwar@gmail.com> | 2024-02-13 06:06:58 -0600 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-02-13 14:06:58 +0200 |
| commit | 03bf161eb6dea6400ee49c6dc6b69bdcfa9fd3fc (patch) | |
| tree | 49320ac8aca35d2ba8162c2a280924bacbd7e06b /convert-hf-to-gguf.py | |
| parent | ad014bba97ef6ef6c3e2f78b2fc463e91ae94579 (diff) | |
llama : support batched embeddings (#5466)
* batched embedding: pool outputs by sequence id. updated embedding example
* bring back non-causal attention
* embd : minor improvements
* llama : minor
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Diffstat (limited to 'convert-hf-to-gguf.py')
| -rwxr-xr-x | convert-hf-to-gguf.py | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/convert-hf-to-gguf.py b/convert-hf-to-gguf.py index cae1551a..5adfdc14 100755 --- a/convert-hf-to-gguf.py +++ b/convert-hf-to-gguf.py @@ -1648,6 +1648,7 @@ class BertModel(Model): self.gguf_writer.add_head_count(self.hparams["num_attention_heads"]) self.gguf_writer.add_layer_norm_eps(self.hparams["layer_norm_eps"]) self.gguf_writer.add_causal_attention(False) + self.gguf_writer.add_pooling_layer(True) self.gguf_writer.add_file_type(self.ftype) def set_vocab(self): |