Skip to content

GitLab

"tests/vscode:/vscode.git/clone" did not exist on "a77aea59fd2f0300160dee6fff2e359f572d7f57"
Unverified Commit 8334c39f authored by Isotr0py's avatar Isotr0py Committed by GitHub
Browse files

[Bugfix] Fix new Llama3.1 GGUF model loading (#7269)

parent e9045767
Show whitespace changes
Inline Side-by-side
Showing with 16 additions and 14 deletions
vllm/model_executor/model_loader/weight_utils.py
View file @ 8334c39f
...@@ -435,6 +435,7 @@ def gguf_quant_weights_iterator( ...@@ -435,6 +435,7 @@ def gguf_quant_weights_iterator(
reader = gguf.GGUFReader(gguf_file) reader = gguf.GGUFReader(gguf_file)
for tensor in reader.tensors: for tensor in reader.tensors:
if tensor.name in gguf_to_hf_name_map:
weight_type = tensor.tensor_type weight_type = tensor.tensor_type
name = gguf_to_hf_name_map[tensor.name] name = gguf_to_hf_name_map[tensor.name]
...@@ -444,6 +445,7 @@ def gguf_quant_weights_iterator( ...@@ -444,6 +445,7 @@ def gguf_quant_weights_iterator(
yield weight_type_name, weight_type yield weight_type_name, weight_type
for tensor in reader.tensors: for tensor in reader.tensors:
if tensor.name in gguf_to_hf_name_map:
weight = tensor.data weight = tensor.data
weight_type = tensor.tensor_type weight_type = tensor.tensor_type
name = gguf_to_hf_name_map[tensor.name] name = gguf_to_hf_name_map[tensor.name]
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment