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

model: dbrx: convert add n_ff

Browse source
This commit is contained in:
Pierrick HYMBERT 2024-04-07 03:17:24 +02:00
parent 52c403355f
commit 06a59abf0a
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

@ -1441,6 +1441,7 @@ class Qwen2MoeModel(Model):
self.gguf_writer.add_clamp_kqv(attn_config["clip_qkv"])
self.gguf_writer.add_file_type(self.ftype)
self.gguf_writer.add_feed_forward_length(ffn_config["ffn_hidden_size"])
self.gguf_writer.add_expert_count(ffn_config["moe_num_experts"])
self.gguf_writer.add_expert_used_count(ffn_config["moe_top_k"])