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 #6486] add LongWrtier Llama3.1 8b and LongWrtier GLM4 9b #29840

New Issue
Closed
opened 2026-04-22 09:06:34 -05:00 by GiteaMirror · 5 comments
GiteaMirror commented 2026-04-22 09:06:34 -05:00
Owner
Copy Link

Originally created by @Willian7004 on GitHub (Aug 24, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/6486

The LongWrtier models are good at writing long content in a single reply.I have successfully impoeted QuantFactory/LongWriter-llama3.1-8b-GGUF so it can be uploaded derectly.I tried to quantize the F32 verson in QuantPanda/LongWriter-glm4-9B-GGUF for a Q4_0 version so that I can load all layers on my GPU,but the quantization failed with "Error: quantization is only supported for F16 and F32 models", so please create a Q4_0 version and upload.

Originally created by @Willian7004 on GitHub (Aug 24, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/6486 The LongWrtier models are good at writing long content in a single reply.I have successfully impoeted QuantFactory/LongWriter-llama3.1-8b-GGUF so it can be uploaded derectly.I tried to quantize the F32 verson in QuantPanda/LongWriter-glm4-9B-GGUF for a Q4_0 version so that I can load all layers on my GPU,but the quantization failed with "Error: quantization is only supported for F16 and F32 models", so please create a Q4_0 version and upload.
GiteaMirror added the model label 2026-04-22 09:06:34 -05:00
GiteaMirror commented 2026-04-22 09:06:35 -05:00
Author
Owner
Copy Link

@Willian7004 commented on GitHub (Aug 24, 2024):

I tried to import the Q4_K_M version of QuantPanda/LongWriter-glm4-9B-GGUF but also failed, maybe the current version of Ollama does not support LongWriter-glm4-9B.

<!-- gh-comment-id:2308186957 --> @Willian7004 commented on GitHub (Aug 24, 2024): I tried to import the Q4_K_M version of QuantPanda/LongWriter-glm4-9B-GGUF but also failed, maybe the current version of Ollama does not support LongWriter-glm4-9B.
GiteaMirror commented 2026-04-22 09:06:36 -05:00
Author
Owner
Copy Link

@EntropyYue commented on GitHub (Aug 31, 2024):

Hello, I have uploaded LongWriter-glm4 q4_0 at https://ollama.com/EntropyYue/longwriter-glm4. You can download it by ollama run EntropyYue/longwriter-glm4:9b

<!-- gh-comment-id:2322831131 --> @EntropyYue commented on GitHub (Aug 31, 2024): Hello, I have uploaded LongWriter-glm4 q4_0 at https://ollama.com/EntropyYue/longwriter-glm4. You can download it by `ollama run EntropyYue/longwriter-glm4:9b`
GiteaMirror commented 2026-04-22 09:06:36 -05:00
Author
Owner
Copy Link

@biox86 commented on GitHub (Aug 31, 2024):

Does this work correctly or does it start to respond with "GGGGGGGGGGG" after a while? Every other GLM4 model on ollama unfortunately does that.

<!-- gh-comment-id:2322832195 --> @biox86 commented on GitHub (Aug 31, 2024): Does this work correctly or does it start to respond with "GGGGGGGGGGG" after a while? Every other GLM4 model on ollama unfortunately does that.
GiteaMirror commented 2026-04-22 09:06:36 -05:00
Author
Owner
Copy Link

@EntropyYue commented on GitHub (Aug 31, 2024):

Please enable Flash Attention when using glm4 model

<!-- gh-comment-id:2322833167 --> @EntropyYue commented on GitHub (Aug 31, 2024): Please enable `Flash Attention` when using glm4 model
GiteaMirror commented 2026-04-22 09:06:37 -05:00
Author
Owner
Copy Link

@biox86 commented on GitHub (Aug 31, 2024):

I'll try soon and get back to you.

<!-- gh-comment-id:2322836620 --> @biox86 commented on GitHub (Aug 31, 2024): I'll try soon and get back to you.
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#29840
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?