CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-04 09:32:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

add bos False

Browse Source
This commit is contained in:
ibrahimkhadraoui
2025-07-07 16:57:52 +04:00
parent ae937f442c
commit b6df0a49d5
1 changed files with 1 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
convert_hf_to_gguf.py
View File

@@ -6649,6 +6649,7 @@ class FalconH1Model(Mamba2Model):
self.gguf_writer.add_block_count(self.block_count) self.gguf_writer.add_block_count(self.block_count)
self.gguf_writer.add_context_length(self.hparams.get("max_position_embeddings", 0)) self.gguf_writer.add_context_length(self.hparams.get("max_position_embeddings", 0))
self.gguf_writer.add_vocab_size(self.hparams["vocab_size"]) self.gguf_writer.add_vocab_size(self.hparams["vocab_size"])
self.gguf_writer.add_add_bos_token(False)
self.gguf_writer.add_feed_forward_length(self.hparams["intermediate_size"]) self.gguf_writer.add_feed_forward_length(self.hparams["intermediate_size"])
## Mamba mixer params ## ## Mamba mixer params ##