Skip to content

GitLab

Commit 5f5a62dd authored by zhouxiang's avatar zhouxiang
Browse files

修复turbomind从hf读模型时存在bf16不支持的问题

parent 9b3cb662
Hide whitespace changes
Inline Side-by-side
Showing with 3 additions and 3 deletions
lmdeploy/turbomind/turbomind.py
View file @ 5f5a62dd
...@@ -305,9 +305,9 @@ class TurboMind: ...@@ -305,9 +305,9 @@ class TurboMind:
data_type = 'int4' data_type = 'int4'
cfg.group_size = 128 cfg.group_size = 128
else: else:
output_format = update_output_format(cfg.model_name, # output_format = update_output_format(cfg.model_name,
inferred_model_format, # inferred_model_format,
model_path, output_format) # model_path, output_format)
data_type = output_format data_type = output_format
update_config_weight_type(output_format, cfg) update_config_weight_type(output_format, cfg)
......
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