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

set n_positions to max_positioin_embeddings

Browse Source
This commit is contained in:
Meng Zhang
2023-09-15 12:35:29 +08:00
parent a17ef39792
commit 2683611944
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
convert-starcoder-hf-to-gguf.py
View File

@@ -105,10 +105,10 @@ block_count = hparams["n_layer"]
gguf_writer.add_name("StarCoder")
gguf_writer.add_context_length(2048) # not in config.json
gguf_writer.add_embedding_length(hparams["n_embd"])
gguf_writer.add_max_position_embeddings(hparams["n_positions"])
gguf_writer.add_feed_forward_length(4 * hparams["n_embd"])
gguf_writer.add_block_count(block_count)
gguf_writer.add_head_count(hparams["n_head"])
gguf_writer.add_head_count_kv(1)
gguf_writer.add_layer_norm_eps(hparams["layer_norm_epsilon"])
gguf_writer.add_file_type(ftype)