[GH-ISSUE #600] Support speechless-llama2-hermes-orca-platypus-wizardlm-13b or Qwen-14b models #26027

Closed
opened 2026-04-22 01:54:47 -05:00 by GiteaMirror · 5 comments
Owner

Originally created by @cheuk-cheng on GitHub (Sep 26, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/600

Is there any plan to support recent models like speechless-llama2-hermes-orca-platypus-wizardlm-13b or Qwen-14b? User reviews seem to indicate that they are powerful and fast even when compared with other llama2 models that have larger sizes. Thanks.

Originally created by @cheuk-cheng on GitHub (Sep 26, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/600 Is there any plan to support recent models like speechless-llama2-hermes-orca-platypus-wizardlm-13b or Qwen-14b? User reviews seem to indicate that they are powerful and fast even when compared with other llama2 models that have larger sizes. Thanks.
Author
Owner

@FairyTail2000 commented on GitHub (Sep 27, 2023):

Speechless works flawlessly for me. I downloaded speechless-llama2-hermes-orca-platypus-wizardlm-13b.Q4_K_M.gguf from huggingfaces and used the following modelfile:

FROM ./speechless-llama2-hermes-orca-platypus-wizardlm-13b.Q4_K_M.gguf

And then ollama create speechless:13b-q4 -f Modelfile. You can replace speechless:13b-q4 with whatever name you like or go with mine. You can then use it like any other model

<!-- gh-comment-id:1736999630 --> @FairyTail2000 commented on GitHub (Sep 27, 2023): Speechless works flawlessly for me. I downloaded speechless-llama2-hermes-orca-platypus-wizardlm-13b.Q4_K_M.gguf from huggingfaces and used the following modelfile: ``` FROM ./speechless-llama2-hermes-orca-platypus-wizardlm-13b.Q4_K_M.gguf ``` And then `ollama create speechless:13b-q4 -f Modelfile`. You can replace speechless:13b-q4 with whatever name you like or go with mine. You can then use it like any other model
Author
Owner

@cheuk-cheng commented on GitHub (Sep 27, 2023):

Thanks @FairyTail2000.

<!-- gh-comment-id:1737694728 --> @cheuk-cheng commented on GitHub (Sep 27, 2023): Thanks @FairyTail2000.
Author
Owner

@pdevine commented on GitHub (Sep 29, 2023):

@FairyTail2000 do you want to push it to ollama.ai? You can DM me on Discord and I can give you the details.

<!-- gh-comment-id:1741519854 --> @pdevine commented on GitHub (Sep 29, 2023): @FairyTail2000 do you want to push it to ollama.ai? You can DM me on Discord and I can give you the details.
Author
Owner

@FairyTail2000 commented on GitHub (Oct 3, 2023):

Pushed to rasun/speechless-llama2-hermes-orca-platypus-wizardlm:13b-q4

<!-- gh-comment-id:1744292030 --> @FairyTail2000 commented on GitHub (Oct 3, 2023): Pushed to rasun/speechless-llama2-hermes-orca-platypus-wizardlm:13b-q4
Author
Owner

@jmorganca commented on GitHub (Dec 22, 2023):

@FairyTail2000 awesome - will close this for now!

<!-- gh-comment-id:1867202668 --> @jmorganca commented on GitHub (Dec 22, 2023): @FairyTail2000 awesome - will close this for now!
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#26027