reproduce https://huggingface.co/DeepGlint-AI/llava-mlcd-qwen2.5-7b
- Dominant language
- Python
- Stars
- 702
- Forks
- 34
- PR merge metrics
- No merged PRs in 30d
Description
Dear @anxiangsir,
Thanks for releasing the codes.
Can I use the scripts https://github.com/deepglint/unicom/blob/main/mlcd_vl/scripts/pretrain_mlcd.sh and https://github.com/deepglint/unicom/blob/main/mlcd_vl/scripts/finetune_mlcd.sh to reproduce the model at https://huggingface.co/DeepGlint-AI/llava-mlcd-qwen2.5-7b? Thanks.
Contributor guide
No contributing guide indexed for this repository
Research direction
Start by reviewing mlcd_vl/scripts/pretrain_mlcd.sh and mlcd_vl/scripts/finetune_mlcd.sh, then compare their stated outputs with the llava-mlcd-qwen2.5-7b model on Hugging Face. Done would be an answer establishing whether those scripts reproduce that model; the issue names no tests or implementation change.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- huggingface, python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100