tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-18 05:56:00 -04:00
Code Issues Packages Projects Releases Wiki Activity

MPT : support GQA for replit-code-v1.5 (#3627)

Browse Source
This commit is contained in:
cebtenzzre
2023-10-15 02:32:06 -04:00
committed by GitHub
parent 11dc1091f6
commit 11bff29045
2 changed files with 5 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -98,6 +98,8 @@ gguf_writer.add_embedding_length(hparams["d_model"])
gguf_writer.add_block_count(block_count)
gguf_writer.add_feed_forward_length(4 * hparams["d_model"])
gguf_writer.add_head_count(hparams["n_heads"])
if kv_n_heads := hparams["attn_config"].get("kv_n_heads"):
gguf_writer.add_head_count_kv(kv_n_heads)
gguf_writer.add_layer_norm_eps(1e-05)
if hparams["attn_config"]["clip_qkv"] is not None:
gguf_writer.add_clamp_kqv(hparams["attn_config"]["clip_qkv"])