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

[Fix]: convert.py support baichuan7B

Browse source
This commit is contained in:
jameswu2014 2023-08-29 16:37:59 +08:00
parent 3a007648f2
commit 3aedf97ca0
1 changed files with 6 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

11
convert.py
View file

@ -469,7 +469,7 @@ class UnquantizedTensor(Tensor):
def permute_part(self, n_part: int, n_head: int) -> 'UnquantizedTensor':
r = self.ndarray.shape[0] // 3
return UnquantizedTensor(permute(self.ndarray[r * n_part : r * n_part + r, ...], n_head))
return UnquantizedTensor(permute(self.ndarray[r * n_part : r * n_part + r, ...], n_head, n_head))
def part(self, n_part: int) -> 'UnquantizedTensor':
r = self.ndarray.shape[0] // 3
@ -952,16 +952,17 @@ def convert_model_names(model: LazyModel, params: Params) -> LazyModel:
#tmp[f"model.layers.{i}.self_attn.v_proj.weight"] = model[f"model.layers.{i}.self_attn.v_proj.weight"]
elif f"model.layers.{i}.self_attn.W_pack.weight" in model:
print(f"Unpacking and permuting layer {i}")
tmp[f"model.layers.{i}.self_attn.q_proj.weight"] = permute_part_lazy(model[f"model.layers.{i}.self_attn.W_pack.weight"], 0, params.n_head, params.n_head)
tmp[f"model.layers.{i}.self_attn.k_proj.weight"] = permute_part_lazy(model[f"model.layers.{i}.self_attn.W_pack.weight"], 1, params.n_head, params.n_head_kv)
tmp[f"model.layers.{i}.self_attn.q_proj.weight"] = permute_part_lazy(model[f"model.layers.{i}.self_attn.W_pack.weight"], 0, params.n_head)
tmp[f"model.layers.{i}.self_attn.k_proj.weight"] = permute_part_lazy(model[f"model.layers.{i}.self_attn.W_pack.weight"], 1, params.n_head)
tmp[f"model.layers.{i}.self_attn.v_proj.weight"] = part_lazy (model[f"model.layers.{i}.self_attn.W_pack.weight"], 2)
del tmp[f"model.layers.{i}.self_attn.W_pack.weight"]
else:
break
out: LazyModel = {}
for name, lazy_tensor in model.items():
name_new = name
if name in tmap:
name_new = tmap[name]
elif name.endswith(".weight") and name[:-7] in tmap:
@ -1112,7 +1113,7 @@ def main(args_in: Optional[List[str]] = None) -> None:
parser.add_argument("--ctx", type=int, help="model training context (default: based on input)")
parser.add_argument("--concurrency", type=int, help=f"concurrency used for conversion (default: {DEFAULT_CONCURRENCY})", default = DEFAULT_CONCURRENCY)
args = parser.parse_args(args_in)
if args.dump_single:
model_plus = lazy_load_file(args.model)
do_dump_model(model_plus)