mirror of
https://github.com/oobabooga/text-generation-webui.git
synced 2025-06-07 22:25:54 -04:00
Fix loading Llama-3_3-Nemotron-Super-49B-v1
and similar models (closes #7012)
This commit is contained in:
parent
7f6579ab20
commit
bae1aa34aa
1 changed files with 1 additions and 1 deletions
|
@ -335,7 +335,7 @@ def estimate_vram(gguf_file, gpu_layers, ctx_size, cache_type):
|
||||||
if key.endswith('.block_count'):
|
if key.endswith('.block_count'):
|
||||||
n_layers = value
|
n_layers = value
|
||||||
elif key.endswith('.attention.head_count_kv'):
|
elif key.endswith('.attention.head_count_kv'):
|
||||||
n_kv_heads = value
|
n_kv_heads = max(value) if isinstance(value, list) else value
|
||||||
elif key.endswith('.embedding_length'):
|
elif key.endswith('.embedding_length'):
|
||||||
embedding_dim = value
|
embedding_dim = value
|
||||||
|
|
||||||
|
|
Loading…
Add table
Reference in a new issue