Skip to content

[MODEL] support deepseek_vl#2942

Merged
Qubitium merged 3 commits into
mainfrom
zx_support_deepseek_vl
Jul 9, 2026
Merged

[MODEL] support deepseek_vl#2942
Qubitium merged 3 commits into
mainfrom
zx_support_deepseek_vl

Conversation

@ZX-ModelCloud

Copy link
Copy Markdown
Collaborator

No description provided.

Signed-off-by: ZX-ModelCloud <zx@modelcloud.ai>
Comment thread gptqmodel/models/definitions/deepseek_vl.py Fixed
Comment thread tests/models/test_deepseek_vl.py Fixed
…-derived

  missing_keys into tie_weights after accelerate checkpoint loading. This prevents
  models with incorrect tie_word_embeddings config from tying distinct checkpoint
  weights such as lm_head and input embeddings.

Signed-off-by: ZX-ModelCloud <zx@modelcloud.ai>
@ZX-ModelCloud ZX-ModelCloud marked this pull request as ready for review July 8, 2026 06:42
Signed-off-by: ZX-ModelCloud <zx@modelcloud.ai>
@Qubitium Qubitium merged commit c294bf1 into main Jul 9, 2026
6 checks passed
@Qubitium Qubitium deleted the zx_support_deepseek_vl branch July 9, 2026 09:32
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants