open-compass / open-compass/VLMEvalKit

Reproducibility of deepseek-vl inference results

Open
#1,367 4 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
4.4k
Forks
768
Avg merge
1d 10h
Merged PRs (30d)
17

Description

Hello, I am using the deepseek-vl model "deepseek-ai/deepseek-vl-7b-chat" and have observed significant variability in its outputs: different runs produce different results. I have already tried setting do_sample=False and temperature=0, but the outputs remain non-deterministic. Could you advise what settings or steps are required to obtain reproducible responses?
Thank you very much.

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

No files, tests, or entry points are identified in the report. Start by reproducing inference with deepseek-ai/deepseek-vl-7b-chat while checking the current generation settings and the attempted do_sample=False and temperature=0 configuration. Done means identifying documented settings or steps that produce reproducible responses.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.