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

update convert.py for mixtral hf models

Browse source
This commit is contained in:
slaren 2024-03-31 01:35:10 +01:00
parent 4a5d50eb61
commit 3b3298af17
1 changed files with 3 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

3
convert.py
View file

@ -1264,6 +1264,9 @@ def convert_model_names(model: LazyModel, params: Params, skip_unknown: bool) ->
if f"layers.{l}.feed_forward.experts.{e}.w{w}.weight" in model: if f"layers.{l}.feed_forward.experts.{e}.w{w}.weight" in model:
experts.append(model[f"layers.{l}.feed_forward.experts.{e}.w{w}.weight"]) experts.append(model[f"layers.{l}.feed_forward.experts.{e}.w{w}.weight"])
del tmp[f"layers.{l}.feed_forward.experts.{e}.w{w}.weight"] del tmp[f"layers.{l}.feed_forward.experts.{e}.w{w}.weight"]
elif f"model.layers.{l}.block_sparse_moe.experts.{e}.w{w}.weight" in model:
experts.append(model[f"model.layers.{l}.block_sparse_moe.experts.{e}.w{w}.weight"])
del tmp[f"model.layers.{l}.block_sparse_moe.experts.{e}.w{w}.weight"]
else: else:
raise ValueError(f"Expert tensor not found: layers.{l}.feed_forward.experts.{e}.w{w}.weight") raise ValueError(f"Expert tensor not found: layers.{l}.feed_forward.experts.{e}.w{w}.weight")
tmp[f"layers.{l}.feed_forward.experts.w{w}.weight"] = pack_experts_lazy(experts) tmp[f"layers.{l}.feed_forward.experts.w{w}.weight"] = pack_experts_lazy(experts)