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

Support rotary_factor for LlavaStableLM

Browse source 
Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>
This commit is contained in:
Anas Ahouzi 2024-02-24 22:26:24 +01:00 • committed by GitHub
parent 79959cae73
commit 19891864e2
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 2 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

3
convert-hf-to-gguf.py
View file

@ -1074,7 +1074,8 @@ class StableLMModel(Model):
self.gguf_writer.add_embedding_length(hparams["hidden_size"])
self.gguf_writer.add_block_count(block_count)
self.gguf_writer.add_feed_forward_length(hparams["intermediate_size"])
self.gguf_writer.add_rope_dimension_count(int(hparams["partial_rotary_factor"] * (hparams["hidden_size"] // hparams["num_attention_heads"])))
rotary_factor = self.find_hparam(["partial_rotary_factor", "rotary_pct"])
self.gguf_writer.add_rope_dimension_count(int(rotary_factor * (hparams["hidden_size"] // hparams["num_attention_heads"])))
self.gguf_writer.add_head_count(hparams["num_attention_heads"])
self.gguf_writer.add_parallel_residual(hparams["use_parallel_residual"] if "use_parallel_residual" in hparams else True)
self.gguf_writer.add_layer_norm_eps(self.find_hparam(["layer_norm_eps", "norm_eps"]))