mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-09-11 04:14:52 +00:00
Fix santacoder.
This commit is contained in:
parent
9f42e5f6fd
commit
d3b5ae27b0
@ -71,7 +71,7 @@ def _load_multi_mqa_gptq(
|
||||
|
||||
g_idx = weights.get_tensor(f"{prefix}.c_attn.g_idx")
|
||||
g_idx = g_idx.to(device=weights.device)
|
||||
bits, groupsize = weights._get_gptq_params()
|
||||
bits, groupsize, _ = weights._get_gptq_params()
|
||||
|
||||
from text_generation_server.utils.layers import HAS_EXLLAMA
|
||||
|
||||
|
Loading…
Reference in New Issue
Block a user