tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-28 12:25:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

convert : update for baichuan (#2081)

Browse Source 
1. guess n_layers;
2. relax warnings on context size;
3. add a note that its derivations are also supported.

Co-authored-by: Judd <foldl@boxvest.com>
This commit is contained in:
Judd
2023-07-07 00:23:49 +08:00
committed by GitHub
parent a17a2683d8
commit 36680f6e40
6 changed files with 11 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
convert.py
View File

@ -154,9 +154,15 @@ class Params:
# try transformer naming first
if "model.layers.0.self_attn.q_proj.weight" in model:
n_layer=next(i for i in itertools.count() if f"model.layers.{i}.self_attn.q_proj.weight" not in model)
elif "model.layers.0.self_attn.W_pack.weight" in model: # next: try baichuan naming
n_layer=next(i for i in itertools.count() if f"model.layers.{i}.self_attn.W_pack.weight" not in model)
else:
n_layer=next(i for i in itertools.count() if f"layers.{i}.attention.wq.weight" not in model)
if n_layer < 1:
raise Exception("failed to guess 'n_layer'. This model is unknown or unsupported.\n"
"Suggestion: provide 'config.json' of the model in the same directory containing model files.")
n_head=n_embd // 128 # guessed
return Params(