github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #4826] Model request: GLM-4 9B #65087

New Issue
Closed
opened 2026-05-03 19:43:40 -05:00 by GiteaMirror · 22 comments
GiteaMirror commented 2026-05-03 19:43:40 -05:00
Owner
Copy Link

Originally created by @mywwq on GitHub (Jun 5, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4826

Add GLM-4 9B model

Model Type Seq Length Download
GLM-4-9B Base 8K 🤗 Huggingface
GLM-4-9B-Chat Chat 128K 🤗 Huggingface
GLM-4-9B-Chat-1M Chat 1M 🤗 Huggingface
GLM-4V-9B Chat 8K 🤗 Huggingface

请问什么时候引入glm4-9b模型

Originally created by @mywwq on GitHub (Jun 5, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4826 Add GLM-4 9B model Model | Type | Seq Length | Download -- | -- | -- | -- GLM-4-9B | Base | 8K | [🤗 Huggingface](https://huggingface.co/THUDM/glm-4-9b) GLM-4-9B-Chat | Chat | 128K | [🤗 Huggingface](https://huggingface.co/THUDM/glm-4-9b-chat) GLM-4-9B-Chat-1M | Chat | 1M | [🤗 Huggingface](https://huggingface.co/THUDM/glm-4-9b-chat-1m) GLM-4V-9B | Chat | 8K | [🤗 Huggingface](https://huggingface.co/THUDM/glm-4v-9b) ----- 请问什么时候引入glm4-9b模型
GiteaMirror added the model label 2026-05-03 19:43:40 -05:00
GiteaMirror commented 2026-05-03 19:43:41 -05:00
Author
Owner
Copy Link

@mili-tan commented on GitHub (Jun 5, 2024):

对 GLM 的支持还没有添加到 ollama 的上游 llama.cpp，也许你应该看看https://github.com/li-plus/chatglm.cpp？

<!-- gh-comment-id:2150975667 --> @mili-tan commented on GitHub (Jun 5, 2024): 对 GLM 的支持还没有添加到 ollama 的上游 llama.cpp，也许你应该看看[https://github.com/li-plus/chatglm.cpp](https://github.com/li-plus/chatglm.cpp)？
GiteaMirror commented 2026-05-03 19:43:42 -05:00
Author
Owner
Copy Link

@io-q commented on GitHub (Jun 21, 2024):

the feature seem ready for llama.cpp soon
https://github.com/ggerganov/llama.cpp/pull/8031

<!-- gh-comment-id:2182013656 --> @io-q commented on GitHub (Jun 21, 2024): the feature seem ready for llama.cpp soon https://github.com/ggerganov/llama.cpp/pull/8031
GiteaMirror commented 2026-05-03 19:43:42 -05:00
Author
Owner
Copy Link

@GHOST1834 commented on GitHub (Jun 27, 2024):

It seems that there are already gguf format glm4 models on huggingface:
https://hf-mirror.com/models?search=glm
Is it possible to add these models now?

<!-- gh-comment-id:2194188468 --> @GHOST1834 commented on GitHub (Jun 27, 2024): It seems that there are already gguf format glm4 models on huggingface: https://hf-mirror.com/models?search=glm Is it possible to add these models now?
GiteaMirror commented 2026-05-03 19:43:43 -05:00
Author
Owner
Copy Link

@cvanelteren commented on GitHub (Jun 27, 2024):

If the Guf are available, we can add them manually 🫡

<!-- gh-comment-id:2194647968 --> @cvanelteren commented on GitHub (Jun 27, 2024): If the Guf are available, we can add them manually 🫡
GiteaMirror commented 2026-05-03 19:43:43 -05:00
Author
Owner
Copy Link

@GHOST1834 commented on GitHub (Jun 27, 2024):

We can, but it will be more convenient if glm4 is added officially.

发自我的iPhone

------------------ Original ------------------
From: Casper van Elteren @.>
Date: Thu,Jun 27,2024 9:06 PM
To: ollama/ollama @.>
Cc: GHOST1834 @.>, Comment @.>
Subject: Re: [ollama/ollama] Model request: GLM-4 9B (Issue #4826)

If the Guf are available, we can add them manually 🫡

—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you commented.Message ID: @.***>

<!-- gh-comment-id:2194652804 --> @GHOST1834 commented on GitHub (Jun 27, 2024): We can, but it will be more convenient if glm4 is added officially. 发自我的iPhone ------------------ Original ------------------ From: Casper van Elteren ***@***.***&gt; Date: Thu,Jun 27,2024 9:06 PM To: ollama/ollama ***@***.***&gt; Cc: GHOST1834 ***@***.***&gt;, Comment ***@***.***&gt; Subject: Re: [ollama/ollama] Model request: GLM-4 9B (Issue #4826) If the Guf are available, we can add them manually 🫡 — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you commented.Message ID: ***@***.***&gt;
GiteaMirror commented 2026-05-03 19:43:44 -05:00
Author
Owner
Copy Link

@cleverpig commented on GitHub (Jun 29, 2024):

If the Guf are available, we can add them manually 🫡

Error: llama runner process has terminated: signal: aborted (core dumped)

<!-- gh-comment-id:2198021031 --> @cleverpig commented on GitHub (Jun 29, 2024): > If the Guf are available, we can add them manually 🫡 Error: llama runner process has terminated: signal: aborted (core dumped)
GiteaMirror commented 2026-05-03 19:43:45 -05:00
Author
Owner
Copy Link

@GHOST1834 commented on GitHub (Jun 29, 2024):

It failed?

发自我的iPhone

------------------ Original ------------------
From: cleverpig @.>
Date: Sat,Jun 29,2024 3:07 PM
To: ollama/ollama @.>
Cc: GHOST1834 @.>, Comment @.>
Subject: Re: [ollama/ollama] Model request: GLM-4 9B (Issue #4826)

If the Guf are available, we can add them manually 🫡

Error: llama runner process has terminated: signal: aborted (core dumped)

—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you commented.Message ID: @.***>

<!-- gh-comment-id:2198024594 --> @GHOST1834 commented on GitHub (Jun 29, 2024): It failed? 发自我的iPhone ------------------ Original ------------------ From: cleverpig ***@***.***&gt; Date: Sat,Jun 29,2024 3:07 PM To: ollama/ollama ***@***.***&gt; Cc: GHOST1834 ***@***.***&gt;, Comment ***@***.***&gt; Subject: Re: [ollama/ollama] Model request: GLM-4 9B (Issue #4826) If the Guf are available, we can add them manually 🫡 Error: llama runner process has terminated: signal: aborted (core dumped) — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you commented.Message ID: ***@***.***&gt;
GiteaMirror commented 2026-05-03 19:43:45 -05:00
Author
Owner
Copy Link

@cvanelteren commented on GitHub (Jun 29, 2024):

Same issue. The format apparently is not compatible.

On Sat, 29 Jun 2024 at 09:21, GHOST1834 @.***> wrote:

It failed?

发自我的iPhone

------------------ Original ------------------
From: cleverpig @.>
Date: Sat,Jun 29,2024 3:07 PM
To: ollama/ollama @.>
Cc: GHOST1834 @.>, Comment @.>
Subject: Re: [ollama/ollama] Model request: GLM-4 9B (Issue #4826)

If the Guf are available, we can add them manually 🫡

Error: llama runner process has terminated: signal: aborted (core dumped)

—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you commented.Message ID: @.***>

—
Reply to this email directly, view it on GitHub
https://github.com/ollama/ollama/issues/4826#issuecomment-2198024594,
or unsubscribe
https://github.com/notifications/unsubscribe-auth/AEUVDV34ZTACC25O2MDJAWLZJZN7BAVCNFSM6AAAAABIZ74XU6VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDCOJYGAZDINJZGQ
.
You are receiving this because you are subscribed to this thread.Message
ID: @.***>

--

<!-- gh-comment-id:2198025090 --> @cvanelteren commented on GitHub (Jun 29, 2024): Same issue. The format apparently is not compatible. On Sat, 29 Jun 2024 at 09:21, GHOST1834 ***@***.***> wrote: > It failed? > > > > 发自我的iPhone > > > ------------------ Original ------------------ > From: cleverpig ***@***.***&gt; > Date: Sat,Jun 29,2024 3:07 PM > To: ollama/ollama ***@***.***&gt; > Cc: GHOST1834 ***@***.***&gt;, Comment ***@***.***&gt; > Subject: Re: [ollama/ollama] Model request: GLM-4 9B (Issue #4826) > > > > > > > If the Guf are available, we can add them manually 🫡 > > Error: llama runner process has terminated: signal: aborted (core dumped) > > — > Reply to this email directly, view it on GitHub, or unsubscribe. > You are receiving this because you commented.Message ID: ***@***.***&gt; > > — > Reply to this email directly, view it on GitHub > <https://github.com/ollama/ollama/issues/4826#issuecomment-2198024594>, > or unsubscribe > <https://github.com/notifications/unsubscribe-auth/AEUVDV34ZTACC25O2MDJAWLZJZN7BAVCNFSM6AAAAABIZ74XU6VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDCOJYGAZDINJZGQ> > . > You are receiving this because you are subscribed to this thread.Message > ID: ***@***.***> > -- - Checkout my website <https://cvanelteren.github.io/> for contact info and current projects!
GiteaMirror commented 2026-05-03 19:43:46 -05:00
Author
Owner
Copy Link

@V-I-C-T-O-R commented on GitHub (Jul 2, 2024):

It failed? 发自我的iPhone
…
------------------ Original ------------------ From: cleverpig @.> Date: Sat,Jun 29,2024 3:07 PM To: ollama/ollama @.> Cc: GHOST1834 @.>, Comment @.> Subject: Re: [ollama/ollama] Model request: GLM-4 9B (Issue #4826) If the Guf are available, we can add them manually 🫡 Error: llama runner process has terminated: signal: aborted (core dumped) — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you commented.Message ID: @.***>

It will happen error "unknown model architecture"

<!-- gh-comment-id:2201770083 --> @V-I-C-T-O-R commented on GitHub (Jul 2, 2024): > It failed? 发自我的iPhone > […](#) > ------------------ Original ------------------ From: cleverpig ***@***.***&gt; Date: Sat,Jun 29,2024 3:07 PM To: ollama/ollama ***@***.***&gt; Cc: GHOST1834 ***@***.***&gt;, Comment ***@***.***&gt; Subject: Re: [ollama/ollama] Model request: GLM-4 9B (Issue #4826) If the Guf are available, we can add them manually 🫡 Error: llama runner process has terminated: signal: aborted (core dumped) — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you commented.Message ID: ***@***.***&gt; It will happen error "unknown model architecture"
GiteaMirror commented 2026-05-03 19:43:47 -05:00
Author
Owner
Copy Link

@zalyoung commented on GitHub (Jul 7, 2024):

The llama.cpp is supporting GLM3 and GLM4 now. As the https://github.com/ggerganov/llama.cpp/pull/8031 has been merged

I use convert_hf_to_gguf.py to convert THUDM/glm-4-9b-chat model to GGUF format, then import the GGUF file into Ollama by using a Modelfile.

FROM ./glm-4-9b-chat.gguf
# sets the temperature to 1 [higher is more creative, lower is more coherent]
PARAMETER temperature 0.5
# sets the context window size to 4096, this controls how many tokens the LLM can use as context to generate the next token
PARAMETER num_ctx 4096

# sets a custom system message to specify the behavior of the chat assistant
SYSTEM You are a helpful AI assistant

When I want a try, Ollama throw out unknown model architecture: 'chatglm' error.

As below:

(base) ➜  ~ ollama ls |grep glm
glm-4-9b-chat:latest                  	54b1c4ad3aec	10.0 GB	16 minutes ago

(base) ➜  ~ ollama run glm-4-9b-chat:latest
Error: llama runner process has terminated: signal: abort trap error:error loading model architecture: unknown model architecture: 'chatglm'
<!-- gh-comment-id:2212499615 --> @zalyoung commented on GitHub (Jul 7, 2024): The llama.cpp is supporting GLM3 and GLM4 now. As the https://github.com/ggerganov/llama.cpp/pull/8031 has been merged I use [convert_hf_to_gguf.py](https://github.com/ggerganov/llama.cpp/blob/master/convert_hf_to_gguf.py) to convert [`THUDM/glm-4-9b-chat`](https://huggingface.co/THUDM/glm-4-9b-chat) model to GGUF format, then [import](https://github.com/ollama/ollama/blob/main/docs/import.md) the GGUF file into Ollama by using a Modelfile. ```Modelfile FROM ./glm-4-9b-chat.gguf # sets the temperature to 1 [higher is more creative, lower is more coherent] PARAMETER temperature 0.5 # sets the context window size to 4096, this controls how many tokens the LLM can use as context to generate the next token PARAMETER num_ctx 4096 # sets a custom system message to specify the behavior of the chat assistant SYSTEM You are a helpful AI assistant ``` When I want a try, Ollama throw out `unknown model architecture: 'chatglm'` error. As below: ``` (base) ➜ ~ ollama ls |grep glm glm-4-9b-chat:latest 54b1c4ad3aec 10.0 GB 16 minutes ago (base) ➜ ~ ollama run glm-4-9b-chat:latest Error: llama runner process has terminated: signal: abort trap error:error loading model architecture: unknown model architecture: 'chatglm' ```
GiteaMirror commented 2026-05-03 19:43:48 -05:00
Author
Owner
Copy Link

@kiradzS commented on GitHub (Jul 8, 2024):

llama.cpp现在支持 GLM3 和 GLM4。由于 ggerganov/llama.cpp#8031 已合并

我使用convert_hf_to_gguf.py将模型转换为GGUF格式，然后使用Modelfile将GGUF文件导入Ollama。

FROM ./glm-4-9b-chat.gguf
# sets the temperature to 1 [higher is more creative, lower is more coherent]
PARAMETER temperature 0.5
# sets the context window size to 4096, this controls how many tokens the LLM can use as context to generate the next token
PARAMETER num_ctx 4096

# sets a custom system message to specify the behavior of the chat assistant
SYSTEM You are a helpful AI assistant

当我想尝试时，Ollama 抛出错误。unknown model architecture: 'chatglm'

如下：

(base) ➜  ~ ollama ls |grep glm
glm-4-9b-chat:latest                  	54b1c4ad3aec	10.0 GB	16 minutes ago

(base) ➜  ~ ollama run glm-4-9b-chat:latest
Error: llama runner process has terminated: signal: abort trap error:error loading model architecture: unknown model architecture: 'chatglm'

me too

<!-- gh-comment-id:2214625207 --> @kiradzS commented on GitHub (Jul 8, 2024): > llama.cpp现在支持 GLM3 和 GLM4。由于 [ggerganov/llama.cpp#8031](https://github.com/ggerganov/llama.cpp/pull/8031) 已合并 > > 我使用[convert_hf_to_gguf.py](https://github.com/ggerganov/llama.cpp/blob/master/convert_hf_to_gguf.py)将模型转换为[](https://huggingface.co/THUDM/glm-4-9b-chat)GGUF格式，然后使用Modelfile将GGUF文件[导入](https://github.com/ollama/ollama/blob/main/docs/import.md)Ollama。 > > ``` > FROM ./glm-4-9b-chat.gguf > # sets the temperature to 1 [higher is more creative, lower is more coherent] > PARAMETER temperature 0.5 > # sets the context window size to 4096, this controls how many tokens the LLM can use as context to generate the next token > PARAMETER num_ctx 4096 > > # sets a custom system message to specify the behavior of the chat assistant > SYSTEM You are a helpful AI assistant > ``` > > 当我想尝试时，Ollama 抛出错误。`unknown model architecture: 'chatglm'` > > 如下： > > ``` > (base) ➜ ~ ollama ls |grep glm > glm-4-9b-chat:latest 54b1c4ad3aec 10.0 GB 16 minutes ago > > (base) ➜ ~ ollama run glm-4-9b-chat:latest > Error: llama runner process has terminated: signal: abort trap error:error loading model architecture: unknown model architecture: 'chatglm' > ``` me too
GiteaMirror commented 2026-05-03 19:43:48 -05:00
Author
Owner
Copy Link

@Forevery1 commented on GitHub (Jul 9, 2024):

https://github.com/ollama/ollama/issues/5529

<!-- gh-comment-id:2215718296 --> @Forevery1 commented on GitHub (Jul 9, 2024): https://github.com/ollama/ollama/issues/5529
GiteaMirror commented 2026-05-03 19:43:49 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Jul 9, 2024):

This is now supported. Make sure you upgrade to version 0.2.1 and then you can ollama run glm4.

<!-- gh-comment-id:2218153529 --> @pdevine commented on GitHub (Jul 9, 2024): This is now supported. Make sure you upgrade to version `0.2.1` and then you can `ollama run glm4`.
GiteaMirror commented 2026-05-03 19:43:50 -05:00
Author
Owner
Copy Link

@cvanelteren commented on GitHub (Jul 10, 2024):

Great. Sometimes it responds in chinese tho ;-)

On Tue, 9 Jul 2024 at 18:35, Patrick Devine @.***>
wrote:

Closed #4826 https://github.com/ollama/ollama/issues/4826 as completed.

—
Reply to this email directly, view it on GitHub
https://github.com/ollama/ollama/issues/4826#event-13443189784, or
unsubscribe
https://github.com/notifications/unsubscribe-auth/AEUVDV7LAUPJND2ZCANSEILZLQGLHAVCNFSM6AAAAABIZ74XU6VHI2DSMVQWIX3LMV45UABCJFZXG5LFIV3GK3TUJZXXI2LGNFRWC5DJN5XDWMJTGQ2DGMJYHE3TQNA
.
You are receiving this because you are subscribed to this thread.Message
ID: @.***>

--

<!-- gh-comment-id:2219717917 --> @cvanelteren commented on GitHub (Jul 10, 2024): Great. Sometimes it responds in chinese tho ;-) On Tue, 9 Jul 2024 at 18:35, Patrick Devine ***@***.***> wrote: > Closed #4826 <https://github.com/ollama/ollama/issues/4826> as completed. > > — > Reply to this email directly, view it on GitHub > <https://github.com/ollama/ollama/issues/4826#event-13443189784>, or > unsubscribe > <https://github.com/notifications/unsubscribe-auth/AEUVDV7LAUPJND2ZCANSEILZLQGLHAVCNFSM6AAAAABIZ74XU6VHI2DSMVQWIX3LMV45UABCJFZXG5LFIV3GK3TUJZXXI2LGNFRWC5DJN5XDWMJTGQ2DGMJYHE3TQNA> > . > You are receiving this because you are subscribed to this thread.Message > ID: ***@***.***> > -- - Checkout my website <https://cvanelteren.github.io/> for contact info and current projects!
GiteaMirror commented 2026-05-03 19:43:50 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Jul 10, 2024):

@cvanelteren you could try telling it not to :-D

<!-- gh-comment-id:2220852886 --> @pdevine commented on GitHub (Jul 10, 2024): @cvanelteren you could try telling it not to :-D
GiteaMirror commented 2026-05-03 19:43:51 -05:00
Author
Owner
Copy Link

@cvanelteren commented on GitHub (Jul 10, 2024):

I did but sometimes it switches out of the blue.

On Wed, 10 Jul 2024 at 17:38, Patrick Devine @.***>
wrote:

@cvanelteren https://github.com/cvanelteren you could try telling it
not to :-D

—
Reply to this email directly, view it on GitHub
https://github.com/ollama/ollama/issues/4826#issuecomment-2220852886,
or unsubscribe
https://github.com/notifications/unsubscribe-auth/AEUVDVZIG7T65V2VSJPSJELZLVIN3AVCNFSM6AAAAABIZ74XU6VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDEMRQHA2TEOBYGY
.
You are receiving this because you were mentioned.Message ID:
@.***>

<!-- gh-comment-id:2221059885 --> @cvanelteren commented on GitHub (Jul 10, 2024): I did but sometimes it switches out of the blue. - Checkout my website <https://cvanelteren.github.io/> for contact info and current projects! On Wed, 10 Jul 2024 at 17:38, Patrick Devine ***@***.***> wrote: > @cvanelteren <https://github.com/cvanelteren> you could try telling it > not to :-D > > — > Reply to this email directly, view it on GitHub > <https://github.com/ollama/ollama/issues/4826#issuecomment-2220852886>, > or unsubscribe > <https://github.com/notifications/unsubscribe-auth/AEUVDVZIG7T65V2VSJPSJELZLVIN3AVCNFSM6AAAAABIZ74XU6VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDEMRQHA2TEOBYGY> > . > You are receiving this because you were mentioned.Message ID: > ***@***.***> >
GiteaMirror commented 2026-05-03 19:43:52 -05:00
Author
Owner
Copy Link

@VarLad commented on GitHub (Jul 11, 2024):

@pdevine what about glm4v-9b (the multimodal one) though? Is that supported too?

<!-- gh-comment-id:2221923515 --> @VarLad commented on GitHub (Jul 11, 2024): @pdevine what about glm4v-9b (the multimodal one) though? Is that supported too?
GiteaMirror commented 2026-05-03 19:43:52 -05:00
Author
Owner
Copy Link

@cvanelteren commented on GitHub (Jul 11, 2024):

image
the Chinese is pretty prevalent on text..., any workaround for this?

<!-- gh-comment-id:2223004248 --> @cvanelteren commented on GitHub (Jul 11, 2024): ![image](https://github.com/ollama/ollama/assets/19485143/3276fb84-f869-4514-a349-f604160fda94) the Chinese is pretty prevalent on text..., any workaround for this?
GiteaMirror commented 2026-05-03 19:43:53 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Jul 11, 2024):

@cvanelteren that doesn't seem like a problem w/ chinese, but there was an issue w/ the graph calculation w/ glm4 where we weren't calculating the memory correctly. There's a fix for that in 0.2.2 which is coming out imminently.

<!-- gh-comment-id:2223521892 --> @pdevine commented on GitHub (Jul 11, 2024): @cvanelteren that doesn't seem like a problem w/ chinese, but there was an issue w/ the graph calculation w/ glm4 where we weren't calculating the memory correctly. There's a fix for that in 0.2.2 which is coming out imminently.
GiteaMirror commented 2026-05-03 19:43:53 -05:00
Author
Owner
Copy Link

@cvanelteren commented on GitHub (Jul 11, 2024):

Ah ok! I thought it was ASCII encoding for Chinese 😂

On Thu, 11 Jul 2024 at 19:43, Patrick Devine @.***>
wrote:

@cvanelteren https://github.com/cvanelteren that doesn't seem like a
problem w/ chinese, but there was an issue w/ the graph calculation w/ glm4
where we weren't calculating the memory correctly. There's a fix for that
in 0.2.2 which is coming out imminently.

—
Reply to this email directly, view it on GitHub
https://github.com/ollama/ollama/issues/4826#issuecomment-2223521892,
or unsubscribe
https://github.com/notifications/unsubscribe-auth/AEUVDVZ3LEZOTABMGVKQS2DZL272VAVCNFSM6AAAAABIZ74XU6VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDEMRTGUZDCOBZGI
.
You are receiving this because you were mentioned.Message ID:
@.***>

<!-- gh-comment-id:2223624656 --> @cvanelteren commented on GitHub (Jul 11, 2024): Ah ok! I thought it was ASCII encoding for Chinese 😂 - Checkout my website <https://cvanelteren.github.io/> for contact info and current projects! On Thu, 11 Jul 2024 at 19:43, Patrick Devine ***@***.***> wrote: > @cvanelteren <https://github.com/cvanelteren> that doesn't seem like a > problem w/ chinese, but there was an issue w/ the graph calculation w/ glm4 > where we weren't calculating the memory correctly. There's a fix for that > in 0.2.2 which is coming out imminently. > > — > Reply to this email directly, view it on GitHub > <https://github.com/ollama/ollama/issues/4826#issuecomment-2223521892>, > or unsubscribe > <https://github.com/notifications/unsubscribe-auth/AEUVDVZ3LEZOTABMGVKQS2DZL272VAVCNFSM6AAAAABIZ74XU6VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDEMRTGUZDCOBZGI> > . > You are receiving this because you were mentioned.Message ID: > ***@***.***> >
GiteaMirror commented 2026-05-03 19:43:54 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Jul 11, 2024):

well, I'm not 100% sure, but the ascii seems suspicious to me 😅 . What platform are you running on?

<!-- gh-comment-id:2223633753 --> @pdevine commented on GitHub (Jul 11, 2024): well, I'm not 100% sure, but the ascii seems suspicious to me 😅 . What platform are you running on?
GiteaMirror commented 2026-05-03 19:43:55 -05:00
Author
Owner
Copy Link

@cvanelteren commented on GitHub (Jul 11, 2024):

Linux (arch)

On Thu, 11 Jul 2024 at 20:34, Patrick Devine @.***>
wrote:

well, I'm not 100% sure, but the ascii seems suspicious to me 😅 . What
platform are you running on?

—
Reply to this email directly, view it on GitHub
https://github.com/ollama/ollama/issues/4826#issuecomment-2223633753,
or unsubscribe
https://github.com/notifications/unsubscribe-auth/AEUVDV3KZULDDLGIHTSLITLZL3F3RAVCNFSM6AAAAABIZ74XU6VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDEMRTGYZTGNZVGM
.
You are receiving this because you were mentioned.Message ID:
@.***>

--

<!-- gh-comment-id:2223718522 --> @cvanelteren commented on GitHub (Jul 11, 2024): Linux (arch) On Thu, 11 Jul 2024 at 20:34, Patrick Devine ***@***.***> wrote: > well, I'm not 100% sure, but the ascii seems suspicious to me 😅 . What > platform are you running on? > > — > Reply to this email directly, view it on GitHub > <https://github.com/ollama/ollama/issues/4826#issuecomment-2223633753>, > or unsubscribe > <https://github.com/notifications/unsubscribe-auth/AEUVDV3KZULDDLGIHTSLITLZL3F3RAVCNFSM6AAAAABIZ74XU6VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDEMRTGYZTGNZVGM> > . > You are receiving this because you were mentioned.Message ID: > ***@***.***> > -- - Checkout my website <https://cvanelteren.github.io/> for contact info and current projects!
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#65087
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?