No Merge?

#55
by Enderchef - opened

I have been trying for weeks to merge my models but no matter what I do it doesn't work. This space, my last resort, does not work. Could somebody please help me? Here's my merge I want -

method: linear

base_model: Qwen/Qwen2.5-14B-Instruct-1M

  • model: Qwen/Qwen2.5-14B-Instruct-1M
    alpha: 0.20

  • model: YOYO-AI/ZYH-LLM-Qwen2.5-14B-V4
    alpha: 0.20

  • model: JungZoona/T3Q-qwen2.5-14b-v1.0-e3
    alpha: 0.40

  • model: prithivMLmods/Gauss-Opus-14B-R999
    alpha: 0.20

tokenizer_source: base

i will leave this here, as it may be of help to some people.

https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing

if you are using the free tier, your time will be limited.

Usually, you have about an hour of service, which might not be enough for most mergers. However, it is not the merge itself that will take long; it is downloading the files into the notebook.

If you use it outside of peak hours, you could have up to 3 hours of service, which should be enough for most sensible merges.

i recommend using the TPU runtime. it has some 300 gigs of RAM and 200 gigs of storage.

Do take some time to read about the notebook. Good luck.

Sign up or log in to comment