Skip to content

GitLab

".codespellrc" did not exist on "3cfe73de3ff75cdb657f0db77cd6228c28f41da1"
Commit c9156538 authored by zhuwenwen's avatar zhuwenwen
Browse files

support glm and baichuan nn

parent 6634a0e0
Show whitespace changes
Inline Side-by-side
Showing with 2 additions and 2 deletions
vllm/model_executor/model_loader.py
View file @ c9156538
...@@ -23,7 +23,7 @@ def _set_default_torch_dtype(dtype: torch.dtype): ...@@ -23,7 +23,7 @@ def _set_default_torch_dtype(dtype: torch.dtype):
def _get_model_architecture(model_config: ModelConfig) -> Type[nn.Module]: def _get_model_architecture(model_config: ModelConfig) -> Type[nn.Module]:
architectures = getattr(model_config.hf_config, "architectures", []) architectures = getattr(model_config.hf_config, "architectures", [])
if architectures == ['LlamaForCausalLM']: if architectures == ['LlamaForCausalLM'] or architectures == ['ChatGLMModel'] or architectures == ['BaichuanForCausalLM']:
if os.getenv('LLAMA_NN') != '0': if os.getenv('LLAMA_NN') != '0':
os.environ['LLAMA_NN'] = '1' os.environ['LLAMA_NN'] = '1'
# Special handling for quantized Mixtral. # Special handling for quantized Mixtral.
......
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