github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #3160] When will the ChatGLM model be supported？ #27704

New Issue
Open
opened 2026-04-22 05:14:38 -05:00 by GiteaMirror · 22 comments
GiteaMirror commented 2026-04-22 05:14:38 -05:00
Owner
Copy Link

Originally created by @yongxingMa on GitHub (Mar 15, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/3160

What model would you like?

When will the ChatGLM model be supported

Originally created by @yongxingMa on GitHub (Mar 15, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/3160 ### What model would you like? When will the ChatGLM model be supported
GiteaMirror added the model label 2026-04-22 05:14:38 -05:00
GiteaMirror commented 2026-04-22 05:14:39 -05:00
Author
Owner
Copy Link

@34892002 commented on GitHub (Mar 15, 2024):

Convert the ChatGLM3 model Error:
(.venv) (base) [root@10-9-159-200 ollama]# python llm/llama.cpp/convert-hf-to-gguf.py /data/chatglm3 --outtype f16 --outfile chatglm3.bin
Loading model: chatglm3
Traceback (most recent call last):
File "/data/ollama/llm/llama.cpp/convert-hf-to-gguf.py", line 1938, in
main()
File "/data/ollama/llm/llama.cpp/convert-hf-to-gguf.py", line 1918, in main
model_class = Model.from_model_architecture(hparams["architectures"][0])
File "/data/ollama/llm/llama.cpp/convert-hf-to-gguf.py", line 204, in from_model_architecture
raise NotImplementedError(f'Architecture {arch!r} not supported!') from None
NotImplementedError: Architecture 'ChatGLMModel' not supported!
(.venv) (base) [root@10-9-159-200 ollama]# python llm/llama.cpp/convert.py /data/chatglm3 --outtype f16 --outfile chatglm3.bin
Loading model file /data/chatglm3/model-00001-of-00007.safetensors
Traceback (most recent call last):
File "/data/ollama/llm/llama.cpp/convert.py", line 1466, in
main()
File "/data/ollama/llm/llama.cpp/convert.py", line 1402, in main
model_plus = load_some_model(args.model)
File "/data/ollama/llm/llama.cpp/convert.py", line 1278, in load_some_model
models_plus.append(lazy_load_file(path))
File "/data/ollama/llm/llama.cpp/convert.py", line 888, in lazy_load_file
elif struct.unpack('<Q', first8)[0] < 16 * 1024 * 1024:
struct.error: unpack requires a buffer of 8 bytes
(.venv) (base) [root@10-9-159-200 ollama]# unpack requires a buffer of 8 bytes

https://github.com/ollama/ollama/blob/main/docs/import.md

<!-- gh-comment-id:1998980308 --> @34892002 commented on GitHub (Mar 15, 2024): Convert the ChatGLM3 model Error: (.venv) (base) [root@10-9-159-200 ollama]# python llm/llama.cpp/convert-hf-to-gguf.py /data/chatglm3 --outtype f16 --outfile chatglm3.bin Loading model: chatglm3 Traceback (most recent call last): File "/data/ollama/llm/llama.cpp/convert-hf-to-gguf.py", line 1938, in <module> main() File "/data/ollama/llm/llama.cpp/convert-hf-to-gguf.py", line 1918, in main model_class = Model.from_model_architecture(hparams["architectures"][0]) File "/data/ollama/llm/llama.cpp/convert-hf-to-gguf.py", line 204, in from_model_architecture raise NotImplementedError(f'Architecture {arch!r} not supported!') from None NotImplementedError: Architecture 'ChatGLMModel' not supported! (.venv) (base) [root@10-9-159-200 ollama]# python llm/llama.cpp/convert.py /data/chatglm3 --outtype f16 --outfile chatglm3.bin Loading model file /data/chatglm3/model-00001-of-00007.safetensors Traceback (most recent call last): File "/data/ollama/llm/llama.cpp/convert.py", line 1466, in <module> main() File "/data/ollama/llm/llama.cpp/convert.py", line 1402, in main model_plus = load_some_model(args.model) File "/data/ollama/llm/llama.cpp/convert.py", line 1278, in load_some_model models_plus.append(lazy_load_file(path)) File "/data/ollama/llm/llama.cpp/convert.py", line 888, in lazy_load_file elif struct.unpack('<Q', first8)[0] < 16 * 1024 * 1024: struct.error: unpack requires a buffer of 8 bytes (.venv) (base) [root@10-9-159-200 ollama]# unpack requires a buffer of 8 bytes # https://github.com/ollama/ollama/blob/main/docs/import.md
GiteaMirror commented 2026-04-22 05:14:39 -05:00
Author
Owner
Copy Link

@BruceMacD commented on GitHub (Mar 15, 2024):

Hi @yongxingMa we have added any ChatGLM models to our main library repo yet, but some community members have uploaded it:
https://ollama.com/search?q=chatglm&p=1

<!-- gh-comment-id:1999455110 --> @BruceMacD commented on GitHub (Mar 15, 2024): Hi @yongxingMa we have added any ChatGLM models to our main library repo yet, but some community members have uploaded it: https://ollama.com/search?q=chatglm&p=1
GiteaMirror commented 2026-04-22 05:14:40 -05:00
Author
Owner
Copy Link

@34892002 commented on GitHub (Mar 18, 2024):

No models have been pushed.

<!-- gh-comment-id:2002777838 --> @34892002 commented on GitHub (Mar 18, 2024): No models have been pushed.
GiteaMirror commented 2026-04-22 05:14:40 -05:00
Author
Owner
Copy Link

@LukeCara commented on GitHub (Mar 19, 2024):

no model has been pushed. Looking forward to have some chatglm3 models soon!

<!-- gh-comment-id:2005924265 --> @LukeCara commented on GitHub (Mar 19, 2024): no model has been pushed. Looking forward to have some chatglm3 models soon!
GiteaMirror commented 2026-04-22 05:14:41 -05:00
Author
Owner
Copy Link

@yaoice commented on GitHub (Mar 29, 2024):

+1

<!-- gh-comment-id:2027219494 --> @yaoice commented on GitHub (Mar 29, 2024): +1
GiteaMirror commented 2026-04-22 05:14:42 -05:00
Author
Owner
Copy Link

@EaglePPP commented on GitHub (Apr 10, 2024):

Hi @yongxingMa we have added any ChatGLM models to our main library repo yet, but some community members have uploaded it: https://ollama.com/search?q=chatglm&p=1

its gone

<!-- gh-comment-id:2047438837 --> @EaglePPP commented on GitHub (Apr 10, 2024): > Hi @yongxingMa we have added any ChatGLM models to our main library repo yet, but some community members have uploaded it: https://ollama.com/search?q=chatglm&p=1 its gone
GiteaMirror commented 2026-04-22 05:14:42 -05:00
Author
Owner
Copy Link

@yongxingMa commented on GitHub (Apr 12, 2024):

Hi @yongxingMa we have added any ChatGLM models to our main library repo yet, but some community members have uploaded it: https://ollama.com/search?q=chatglm&p=1

its gone

No chatglm models have been search yet.

<!-- gh-comment-id:2051270177 --> @yongxingMa commented on GitHub (Apr 12, 2024): > > Hi @yongxingMa we have added any ChatGLM models to our main library repo yet, but some community members have uploaded it: https://ollama.com/search?q=chatglm&p=1 > > its gone No chatglm models have been search yet.
GiteaMirror commented 2026-04-22 05:14:42 -05:00
Author
Owner
Copy Link

@DUZHUJUN commented on GitHub (Apr 18, 2024):

i cant't convert chatglm model to GGUF format,how can i run a chatglm model local?

<!-- gh-comment-id:2062918138 --> @DUZHUJUN commented on GitHub (Apr 18, 2024): i cant't convert chatglm model to GGUF format,how can i run a chatglm model local?
GiteaMirror commented 2026-04-22 05:14:43 -05:00
Author
Owner
Copy Link

@flyfox666 commented on GitHub (Apr 20, 2024):

Yes I've run into this problem as well, and sincerely request that chatglm support be added!

<!-- gh-comment-id:2067633060 --> @flyfox666 commented on GitHub (Apr 20, 2024): Yes I've run into this problem as well, and sincerely request that chatglm support be added!
GiteaMirror commented 2026-04-22 05:14:44 -05:00
Author
Owner
Copy Link

@shinyzhu commented on GitHub (Apr 20, 2024):

I updated to latest Ollama and llama.cpp source. but got this error:

(.venv) shiny@ubuntuinr2:/data/llmbuild/ollama$ python llm/llama.cpp/convert.py ./model --outtype f16 --outfile converted.bin
Loading model file model/model-00001-of-00007.safetensors
Loading model file model/model-00001-of-00007.safetensors
Loading model file model/model-00002-of-00007.safetensors
Loading model file model/model-00003-of-00007.safetensors
Loading model file model/model-00004-of-00007.safetensors
Loading model file model/model-00005-of-00007.safetensors
Loading model file model/model-00006-of-00007.safetensors
Loading model file model/model-00007-of-00007.safetensors
Traceback (most recent call last):
  File "/data/llmbuild/ollama/llm/llama.cpp/convert.py", line 1548, in <module>
    main()
  File "/data/llmbuild/ollama/llm/llama.cpp/convert.py", line 1480, in main
    model_plus = load_some_model(args.model)
  File "/data/llmbuild/ollama/llm/llama.cpp/convert.py", line 1371, in load_some_model
    model_plus = merge_multifile_models(models_plus)
  File "/data/llmbuild/ollama/llm/llama.cpp/convert.py", line 804, in merge_multifile_models
    model = merge_sharded([mp.model for mp in models_plus])
  File "/data/llmbuild/ollama/llm/llama.cpp/convert.py", line 783, in merge_sharded
    return {name: convert(name) for name in names}
  File "/data/llmbuild/ollama/llm/llama.cpp/convert.py", line 783, in <dictcomp>
    return {name: convert(name) for name in names}
  File "/data/llmbuild/ollama/llm/llama.cpp/convert.py", line 758, in convert
    lazy_tensors = [model[name] for model in models]
  File "/data/llmbuild/ollama/llm/llama.cpp/convert.py", line 758, in <listcomp>
    lazy_tensors = [model[name] for model in models]
KeyError: 'transformer.embedding.word_embeddings.weight'
<!-- gh-comment-id:2067718876 --> @shinyzhu commented on GitHub (Apr 20, 2024): I updated to latest `Ollama` and `llama.cpp` source. but got this error: ```sh (.venv) shiny@ubuntuinr2:/data/llmbuild/ollama$ python llm/llama.cpp/convert.py ./model --outtype f16 --outfile converted.bin Loading model file model/model-00001-of-00007.safetensors Loading model file model/model-00001-of-00007.safetensors Loading model file model/model-00002-of-00007.safetensors Loading model file model/model-00003-of-00007.safetensors Loading model file model/model-00004-of-00007.safetensors Loading model file model/model-00005-of-00007.safetensors Loading model file model/model-00006-of-00007.safetensors Loading model file model/model-00007-of-00007.safetensors Traceback (most recent call last): File "/data/llmbuild/ollama/llm/llama.cpp/convert.py", line 1548, in <module> main() File "/data/llmbuild/ollama/llm/llama.cpp/convert.py", line 1480, in main model_plus = load_some_model(args.model) File "/data/llmbuild/ollama/llm/llama.cpp/convert.py", line 1371, in load_some_model model_plus = merge_multifile_models(models_plus) File "/data/llmbuild/ollama/llm/llama.cpp/convert.py", line 804, in merge_multifile_models model = merge_sharded([mp.model for mp in models_plus]) File "/data/llmbuild/ollama/llm/llama.cpp/convert.py", line 783, in merge_sharded return {name: convert(name) for name in names} File "/data/llmbuild/ollama/llm/llama.cpp/convert.py", line 783, in <dictcomp> return {name: convert(name) for name in names} File "/data/llmbuild/ollama/llm/llama.cpp/convert.py", line 758, in convert lazy_tensors = [model[name] for model in models] File "/data/llmbuild/ollama/llm/llama.cpp/convert.py", line 758, in <listcomp> lazy_tensors = [model[name] for model in models] KeyError: 'transformer.embedding.word_embeddings.weight' ```
GiteaMirror commented 2026-04-22 05:14:44 -05:00
Author
Owner
Copy Link

@alexsworld commented on GitHub (Apr 28, 2024):

Currently not supported ChatGLM3?

screenshot-20240428-174054

<!-- gh-comment-id:2081412453 --> @alexsworld commented on GitHub (Apr 28, 2024): Currently not supported ChatGLM3? ![screenshot-20240428-174054](https://github.com/ollama/ollama/assets/58976423/ef9069ea-e9f5-4f2e-a5dc-9786c933a04c)
GiteaMirror commented 2026-04-22 05:14:44 -05:00
Author
Owner
Copy Link

@evnydd0f commented on GitHub (Apr 30, 2024):

ChatGLM not Supported

<!-- gh-comment-id:2085315724 --> @evnydd0f commented on GitHub (Apr 30, 2024): ChatGLM not Supported
GiteaMirror commented 2026-04-22 05:14:45 -05:00
Author
Owner
Copy Link

@darkknight0007 commented on GitHub (May 11, 2024):

When will the ChatGLM model be supported？

<!-- gh-comment-id:2106048817 --> @darkknight0007 commented on GitHub (May 11, 2024): When will the ChatGLM model be supported？
GiteaMirror commented 2026-04-22 05:14:45 -05:00
Author
Owner
Copy Link

@mufenzhimi commented on GitHub (May 16, 2024):

+1 looking forward to this

<!-- gh-comment-id:2113978504 --> @mufenzhimi commented on GitHub (May 16, 2024): +1 looking forward to this
GiteaMirror commented 2026-04-22 05:14:46 -05:00
Author
Owner
Copy Link

@shengbox commented on GitHub (May 16, 2024):

+1

<!-- gh-comment-id:2115334586 --> @shengbox commented on GitHub (May 16, 2024): +1
GiteaMirror commented 2026-04-22 05:14:46 -05:00
Author
Owner
Copy Link

@xukecheng commented on GitHub (May 20, 2024):

+1

<!-- gh-comment-id:2120030671 --> @xukecheng commented on GitHub (May 20, 2024): +1
GiteaMirror commented 2026-04-22 05:14:46 -05:00
Author
Owner
Copy Link

@aboutmydreams commented on GitHub (May 27, 2024):

+1

<!-- gh-comment-id:2132537934 --> @aboutmydreams commented on GitHub (May 27, 2024): +1
GiteaMirror commented 2026-04-22 05:14:46 -05:00
Author
Owner
Copy Link

@ztsweet commented on GitHub (Jun 3, 2024):

+1

<!-- gh-comment-id:2144389053 --> @ztsweet commented on GitHub (Jun 3, 2024): +1
GiteaMirror commented 2026-04-22 05:14:47 -05:00
Author
Owner
Copy Link

@weirdo-adam commented on GitHub (Jun 7, 2024):

+1

<!-- gh-comment-id:2154383407 --> @weirdo-adam commented on GitHub (Jun 7, 2024): +1
GiteaMirror commented 2026-04-22 05:14:47 -05:00
Author
Owner
Copy Link

@zhangzhiqiangcs commented on GitHub (Jun 11, 2024):

+1

<!-- gh-comment-id:2159716344 --> @zhangzhiqiangcs commented on GitHub (Jun 11, 2024): +1
GiteaMirror commented 2026-04-22 05:14:47 -05:00
Author
Owner
Copy Link

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

Hi guys, I just happen to be the first one to reply with a successful use of ChatGLM:

https://ollama.com/library/codegeex4

I noticed it said Ollama 0.2 is needed. I had to restart for it to work.

ollama run codegeex4
Error: llama runner process has terminated: signal: abort trap error:error loading model architecture: unknown model architecture: 'chatglm'
(I restarted ollama to update)

$ ollama run codegeex4
>>> hi
Hello! How can I assist you today?

>>> Send a message (/? for help)

ChatGLM arch seems to work now

<!-- gh-comment-id:2216609443 --> @funkytaco commented on GitHub (Jul 9, 2024): Hi guys, I just happen to be the first one to reply with a successful use of ChatGLM: https://ollama.com/library/codegeex4 I noticed it said Ollama 0.2 is needed. I had to restart for it to work. ``` ollama run codegeex4 Error: llama runner process has terminated: signal: abort trap error:error loading model architecture: unknown model architecture: 'chatglm' (I restarted ollama to update) $ ollama run codegeex4 >>> hi Hello! How can I assist you today? >>> Send a message (/? for help) ``` ChatGLM arch seems to work now
GiteaMirror commented 2026-04-22 05:14:48 -05:00
Author
Owner
Copy Link

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

EDIT:
i updated to ollama v0.2.1 and it's working now as @funkytaco mentioned earlier

C:\Users\Tasmetime>ollama run codegeex4
Error: llama runner process has terminated: exit status 0xc0000409

app.log
time=2024-07-09T15:09:04.106+03:30 level=INFO source=logging.go:50 msg="ollama app started" time=2024-07-09T15:09:04.125+03:30 level=INFO source=server.go:176 msg="unable to connect to server" time=2024-07-09T15:09:04.125+03:30 level=INFO source=server.go:135 msg="starting server..." time=2024-07-09T15:09:04.128+03:30 level=INFO source=server.go:121 msg="started ollama server with pid 27128" time=2024-07-09T15:09:04.128+03:30 level=INFO source=server.go:123 msg="ollama server logs C:\\Users\\Tasmetime\\AppData\\Local\\Ollama\\server.log" time=2024-07-09T15:09:07.520+03:30 level=INFO source=updater.go:91 msg="check update error 403 - \n<html><head>\n<meta http-equiv=\"content-type\" content=\"text/html;charset=utf-8\">\n<title>403 Forb"

server.log

`
2024/07/09 15:09:04 routes.go:1064: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE: OLLAMA_LLM_LIBRARY: OLLAMA_MAX_LOADED_MODELS:1 OLLAMA_MAX_QUEUE:512 OLLAMA_MAX_VRAM:0 OLLAMA_MODELS:F:\AI\ollama_models OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://*] OLLAMA_RUNNERS_DIR:C:\Users\Tasmetime\AppData\Local\Programs\Ollama\ollama_runners OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES:]"
time=2024-07-09T15:09:04.178+03:30 level=INFO source=images.go:730 msg="total blobs: 24"
time=2024-07-09T15:09:04.178+03:30 level=INFO source=images.go:737 msg="total unused blobs removed: 0"
time=2024-07-09T15:09:04.179+03:30 level=INFO source=routes.go:1111 msg="Listening on 127.0.0.1:11434 (version 0.1.48)"
time=2024-07-09T15:09:04.179+03:30 level=INFO source=payload.go:44 msg="Dynamic LLM libraries [cuda_v11.3 rocm_v5.7 cpu cpu_avx cpu_avx2]"
time=2024-07-09T15:09:04.287+03:30 level=INFO source=types.go:98 msg="inference compute" id=GPU-b3ce8207-e375-8cea-dcd3-f475728acad1 library=cuda compute=8.6 driver=12.4 name="NVIDIA GeForce RTX 3070" total="8.0 GiB" available="6.9 GiB"
[GIN] 2024/07/09 - 15:09:04 | 200 | 0s | 127.0.0.1 | HEAD "/"
[GIN] 2024/07/09 - 15:09:04 | 200 | 21.4613ms | 127.0.0.1 | POST "/api/show"
time=2024-07-09T15:09:04.653+03:30 level=INFO source=memory.go:309 msg="offload to cuda" layers.requested=-1 layers.model=41 layers.offload=41 layers.split="" memory.available="[7.3 GiB]" memory.required.full="5.6 GiB" memory.required.partial="5.6 GiB" memory.required.kv="80.0 MiB" memory.required.allocations="[5.6 GiB]" memory.weights.total="4.4 GiB" memory.weights.repeating="3.9 GiB" memory.weights.nonrepeating="485.6 MiB" memory.graph.full="213.3 MiB" memory.graph.partial="213.3 MiB"
time=2024-07-09T15:09:04.661+03:30 level=INFO source=server.go:368 msg="starting llama server" cmd="C:\Users\Tasmetime\AppData\Local\Programs\Ollama\ollama_runners\cuda_v11.3\ollama_llama_server.exe --model F:\AI\ollama_models\blobs\sha256-816441b33390807d429fbdb1de7e33bb4d569ac68e2203bdbca5d8d79b5c7266 --ctx-size 2048 --batch-size 512 --embedding --log-disable --n-gpu-layers 41 --no-mmap --parallel 1 --port 57883"
time=2024-07-09T15:09:04.663+03:30 level=INFO source=sched.go:382 msg="loaded runners" count=1
time=2024-07-09T15:09:04.663+03:30 level=INFO source=server.go:556 msg="waiting for llama runner to start responding"
time=2024-07-09T15:09:04.664+03:30 level=INFO source=server.go:594 msg="waiting for server to become available" status="llm server error"
INFO [wmain] build info | build=3171 commit="7c26775a" tid="26740" timestamp=1720525144
INFO [wmain] system info | n_threads=8 n_threads_batch=-1 system_info="AVX = 1 | AVX_VNNI = 0 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | AVX512_BF16 = 0 | FMA = 0 | NEON = 0 | SVE = 0 | ARM_FMA = 0 | F16C = 0 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 1 | " tid="26740" timestamp=1720525144 total_threads=16
INFO [wmain] HTTP server listening | hostname="127.0.0.1" n_threads_http="15" port="57883" tid="26740" timestamp=1720525144
llama_model_loader: loaded meta data with 23 key-value pairs and 283 tensors from F:\AI\ollama_models\blobs\sha256-816441b33390807d429fbdb1de7e33bb4d569ac68e2203bdbca5d8d79b5c7266 (version GGUF V3 (latest))
llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
llama_model_loader: - kv 0: general.architecture str = chatglm
llama_model_loader: - kv 1: general.name str = codegeex4-all-9b
llama_model_loader: - kv 2: chatglm.context_length u32 = 131072
llama_model_loader: - kv 3: chatglm.embedding_length u32 = 4096
llama_model_loader: - kv 4: chatglm.feed_forward_length u32 = 13696
llama_model_loader: - kv 5: chatglm.block_count u32 = 40
llama_model_loader: - kv 6: chatglm.attention.head_count u32 = 32
llama_model_loader: - kv 7: chatglm.attention.head_count_kv u32 = 2
llama_model_loader: - kv 8: chatglm.attention.layer_norm_rms_epsilon f32 = 0.000010
llama_model_loader: - kv 9: general.file_type u32 = 2
llama_model_loader: - kv 10: chatglm.rope.dimension_count u32 = 64
llama_model_loader: - kv 11: tokenizer.ggml.add_bos_token bool = false
llama_model_loader: - kv 12: chatglm.rope.freq_base f32 = 5000000.000000
llama_model_loader: - kv 13: tokenizer.ggml.model str = gpt2
llama_model_loader: - kv 14: tokenizer.ggml.pre str = chatglm-bpe
llama_model_loader: - kv 15: tokenizer.ggml.tokens arr[str,151552] = ["!", """, "#", "$", "%", "&", "'", ...
llama_model_loader: - kv 16: tokenizer.ggml.token_type arr[i32,151552] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv 17: tokenizer.ggml.merges arr[str,151073] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv 18: tokenizer.ggml.padding_token_id u32 = 151329
llama_model_loader: - kv 19: tokenizer.ggml.eos_token_id u32 = 151329
llama_model_loader: - kv 20: tokenizer.ggml.eot_token_id u32 = 151336
llama_model_loader: - kv 21: tokenizer.ggml.unknown_token_id u32 = 151329
llama_model_loader: - kv 22: general.quantization_version u32 = 2
llama_model_loader: - type f32: 121 tensors
llama_model_loader: - type q4_0: 161 tensors
llama_model_loader: - type q6_K: 1 tensors
llama_model_load: error loading model: error loading model architecture: unknown model architecture: 'chatglm'
llama_load_model_from_file: exception loading model
time=2024-07-09T15:09:04.921+03:30 level=ERROR source=sched.go:388 msg="error loading llama server" error="llama runner process has terminated: exit status 0xc0000409 "
[GIN] 2024/07/09 - 15:09:04 | 500 | 302.0822ms | 127.0.0.1 | POST "/api/chat"

`
not working for me.
is there a way I can install the chatglm arch or it's just not supported?

<!-- gh-comment-id:2217424362 --> @TasmeTime commented on GitHub (Jul 9, 2024): **EDIT:** `i updated to ollama v0.2.1 and it's working now as @funkytaco mentioned earlier` C:\Users\Tasmetime>ollama run codegeex4 Error: llama runner process has terminated: exit status 0xc0000409 app.log ` time=2024-07-09T15:09:04.106+03:30 level=INFO source=logging.go:50 msg="ollama app started" time=2024-07-09T15:09:04.125+03:30 level=INFO source=server.go:176 msg="unable to connect to server" time=2024-07-09T15:09:04.125+03:30 level=INFO source=server.go:135 msg="starting server..." time=2024-07-09T15:09:04.128+03:30 level=INFO source=server.go:121 msg="started ollama server with pid 27128" time=2024-07-09T15:09:04.128+03:30 level=INFO source=server.go:123 msg="ollama server logs C:\\Users\\Tasmetime\\AppData\\Local\\Ollama\\server.log" time=2024-07-09T15:09:07.520+03:30 level=INFO source=updater.go:91 msg="check update error 403 - \n<html><head>\n<meta http-equiv=\"content-type\" content=\"text/html;charset=utf-8\">\n<title>403 Forb" ` server.log ` 2024/07/09 15:09:04 routes.go:1064: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE: OLLAMA_LLM_LIBRARY: OLLAMA_MAX_LOADED_MODELS:1 OLLAMA_MAX_QUEUE:512 OLLAMA_MAX_VRAM:0 OLLAMA_MODELS:F:\\AI\\ollama_models OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://*] OLLAMA_RUNNERS_DIR:C:\\Users\\Tasmetime\\AppData\\Local\\Programs\\Ollama\\ollama_runners OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES:]" time=2024-07-09T15:09:04.178+03:30 level=INFO source=images.go:730 msg="total blobs: 24" time=2024-07-09T15:09:04.178+03:30 level=INFO source=images.go:737 msg="total unused blobs removed: 0" time=2024-07-09T15:09:04.179+03:30 level=INFO source=routes.go:1111 msg="Listening on 127.0.0.1:11434 (version 0.1.48)" time=2024-07-09T15:09:04.179+03:30 level=INFO source=payload.go:44 msg="Dynamic LLM libraries [cuda_v11.3 rocm_v5.7 cpu cpu_avx cpu_avx2]" time=2024-07-09T15:09:04.287+03:30 level=INFO source=types.go:98 msg="inference compute" id=GPU-b3ce8207-e375-8cea-dcd3-f475728acad1 library=cuda compute=8.6 driver=12.4 name="NVIDIA GeForce RTX 3070" total="8.0 GiB" available="6.9 GiB" [GIN] 2024/07/09 - 15:09:04 | 200 | 0s | 127.0.0.1 | HEAD "/" [GIN] 2024/07/09 - 15:09:04 | 200 | 21.4613ms | 127.0.0.1 | POST "/api/show" time=2024-07-09T15:09:04.653+03:30 level=INFO source=memory.go:309 msg="offload to cuda" layers.requested=-1 layers.model=41 layers.offload=41 layers.split="" memory.available="[7.3 GiB]" memory.required.full="5.6 GiB" memory.required.partial="5.6 GiB" memory.required.kv="80.0 MiB" memory.required.allocations="[5.6 GiB]" memory.weights.total="4.4 GiB" memory.weights.repeating="3.9 GiB" memory.weights.nonrepeating="485.6 MiB" memory.graph.full="213.3 MiB" memory.graph.partial="213.3 MiB" time=2024-07-09T15:09:04.661+03:30 level=INFO source=server.go:368 msg="starting llama server" cmd="C:\\Users\\Tasmetime\\AppData\\Local\\Programs\\Ollama\\ollama_runners\\cuda_v11.3\\ollama_llama_server.exe --model F:\\AI\\ollama_models\\blobs\\sha256-816441b33390807d429fbdb1de7e33bb4d569ac68e2203bdbca5d8d79b5c7266 --ctx-size 2048 --batch-size 512 --embedding --log-disable --n-gpu-layers 41 --no-mmap --parallel 1 --port 57883" time=2024-07-09T15:09:04.663+03:30 level=INFO source=sched.go:382 msg="loaded runners" count=1 time=2024-07-09T15:09:04.663+03:30 level=INFO source=server.go:556 msg="waiting for llama runner to start responding" time=2024-07-09T15:09:04.664+03:30 level=INFO source=server.go:594 msg="waiting for server to become available" status="llm server error" INFO [wmain] build info | build=3171 commit="7c26775a" tid="26740" timestamp=1720525144 INFO [wmain] system info | n_threads=8 n_threads_batch=-1 system_info="AVX = 1 | AVX_VNNI = 0 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | AVX512_BF16 = 0 | FMA = 0 | NEON = 0 | SVE = 0 | ARM_FMA = 0 | F16C = 0 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 1 | " tid="26740" timestamp=1720525144 total_threads=16 INFO [wmain] HTTP server listening | hostname="127.0.0.1" n_threads_http="15" port="57883" tid="26740" timestamp=1720525144 llama_model_loader: loaded meta data with 23 key-value pairs and 283 tensors from F:\AI\ollama_models\blobs\sha256-816441b33390807d429fbdb1de7e33bb4d569ac68e2203bdbca5d8d79b5c7266 (version GGUF V3 (latest)) llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. llama_model_loader: - kv 0: general.architecture str = **chatglm** llama_model_loader: - kv 1: general.name str = codegeex4-all-9b llama_model_loader: - kv 2: chatglm.context_length u32 = 131072 llama_model_loader: - kv 3: chatglm.embedding_length u32 = 4096 llama_model_loader: - kv 4: chatglm.feed_forward_length u32 = 13696 llama_model_loader: - kv 5: chatglm.block_count u32 = 40 llama_model_loader: - kv 6: chatglm.attention.head_count u32 = 32 llama_model_loader: - kv 7: chatglm.attention.head_count_kv u32 = 2 llama_model_loader: - kv 8: chatglm.attention.layer_norm_rms_epsilon f32 = 0.000010 llama_model_loader: - kv 9: general.file_type u32 = 2 llama_model_loader: - kv 10: chatglm.rope.dimension_count u32 = 64 llama_model_loader: - kv 11: tokenizer.ggml.add_bos_token bool = false llama_model_loader: - kv 12: chatglm.rope.freq_base f32 = 5000000.000000 llama_model_loader: - kv 13: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 14: tokenizer.ggml.pre str = chatglm-bpe llama_model_loader: - kv 15: tokenizer.ggml.tokens arr[str,151552] = ["!", "\"", "#", "$", "%", "&", "'", ... llama_model_loader: - kv 16: tokenizer.ggml.token_type arr[i32,151552] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 17: tokenizer.ggml.merges arr[str,151073] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",... llama_model_loader: - kv 18: tokenizer.ggml.padding_token_id u32 = 151329 llama_model_loader: - kv 19: tokenizer.ggml.eos_token_id u32 = 151329 llama_model_loader: - kv 20: tokenizer.ggml.eot_token_id u32 = 151336 llama_model_loader: - kv 21: tokenizer.ggml.unknown_token_id u32 = 151329 llama_model_loader: - kv 22: general.quantization_version u32 = 2 llama_model_loader: - type f32: 121 tensors llama_model_loader: - type q4_0: 161 tensors llama_model_loader: - type q6_K: 1 tensors llama_model_load: **error loading model: error loading model architecture: unknown model architecture: 'chatglm'** llama_load_model_from_file: exception loading model time=2024-07-09T15:09:04.921+03:30 level=ERROR source=sched.go:388 msg="error loading llama server" error="llama runner process has terminated: exit status 0xc0000409 " [GIN] 2024/07/09 - 15:09:04 | 500 | 302.0822ms | 127.0.0.1 | POST "/api/chat" ` not working for me. is there a way I can install the chatglm arch or it's just not supported?
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#27704
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?