squall/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

Support for Stable LM 2 (#2598)

Browse Source 
Co-authored-by: Zhuohan Li <zhuohan123@gmail.com>
This commit is contained in:
dakotamahan-stability 2024-01-26 14:45:19 -06:00 committed by GitHub
parent 6b7de1a030
commit 3a0e1fc070
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
vllm/model_executor/models/stablelm.py
View File

@ -98,7 +98,7 @@ class StablelmAttention(nn.Module):
self.scaling = self.head_dim**-0.5
self.q_size = self.num_heads * self.head_dim
self.kv_size = self.num_key_value_heads * self.head_dim
self.qkv_bias = getattr(config, "use_qkv_bias", False)
if (self.head_dim * self.num_heads * tp_size) != self.hidden_size:
raise ValueError(
f"hidden_size must be divisible by num_heads (got `hidden_size`: {self.hidden_size}"
@ -108,7 +108,7 @@ class StablelmAttention(nn.Module):
self.head_dim,
self.total_num_heads,
self.total_num_key_value_heads,
bias=False,
self.qkv_bias,
linear_method=linear_method)
self.o_proj = RowParallelLinear(self.total_num_heads * self.head_dim,
self.hidden_size,