github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-16 21:25:46 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #7918] Request to add semikong-8b to ollama #67124

New Issue
Closed
opened 2026-05-04 09:30:52 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-05-04 09:30:52 -05:00
Owner
Copy Link

Originally created by @luoLojic on GitHub (Dec 3, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/7918

I would like to deploy the semikong-8b model locally. Semikong is a large model fine-tuned from Llama focused on the semiconductor domain. You can find the model on Hugging Face at this link: “https://huggingface.co/pentagoniac/SEMIKONG-8b-GPTQ and the GitHub repository here: “https://github.com/aitomatic/semikong. The model is in the .safetensors format. I attempted to convert it using llama.cpp, but encountered the following error: “ValueError: Can not map tensor 'model.layers.0.mlp.down_proj.g_idx'”. I have not found a suitable solution for this issue. I would love to see this model added to Ollama. Thanks for the developers' hard work.
My English is not very good, and these sentences were generated using a translation tool.

Originally created by @luoLojic on GitHub (Dec 3, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/7918 I would like to deploy the semikong-8b model locally. Semikong is a large model fine-tuned from Llama focused on the semiconductor domain. You can find the model on Hugging Face at this link: “[https://huggingface.co/pentagoniac/SEMIKONG-8b-GPTQ](https://huggingface.co/pentagoniac/SEMIKONG-8b-GPTQ) and the GitHub repository here: “[https://github.com/aitomatic/semikong](https://github.com/aitomatic/semikong). The model is in the .safetensors format. I attempted to convert it using llama.cpp, but encountered the following error: “ValueError: Can not map tensor 'model.layers.0.mlp.down_proj.g_idx'”. I have not found a suitable solution for this issue. I would love to see this model added to Ollama. Thanks for the developers' hard work. My English is not very good, and these sentences were generated using a translation tool.
GiteaMirror added the model label 2026-05-04 09:30:52 -05:00
GiteaMirror commented 2026-05-04 09:30:54 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Dec 3, 2024):

Unfortunately llama.cpp doesn't suppot GPTQ quantization. In order for the model be imported, it would have to be quantized from the original source, which doesn't appear to be on huggingface. The 70B unquantized model is available.

<!-- gh-comment-id:2514900712 --> @rick-github commented on GitHub (Dec 3, 2024): Unfortunately llama.cpp doesn't suppot GPTQ quantization. In order for the model be imported, it would have to be quantized from the original source, which [doesn't appear](https://github.com/aitomatic/semikong/issues/6) to be on huggingface. The [70B unquantized](https://huggingface.co/pentagoniac/SEMIKONG-70B/tree/main) model is available.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label model
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#67124
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?