[GH-ISSUE #4169] Error: invalid character '\x00' looking for beginning of value #49103

Closed
opened 2026-04-28 10:45:10 -05:00 by GiteaMirror · 6 comments
Owner

Originally created by @TapsHTS on GitHub (May 5, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4169

What is the issue?

When i run: ollama run llama3:8b or ollama run llama3 I have:

Error: invalid character '\x00' looking for beginning of value

OS

Windows

GPU

Nvidia

CPU

AMD

Ollama version

0.1.33

Originally created by @TapsHTS on GitHub (May 5, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4169 ### What is the issue? When i run: `ollama run llama3:8b` or `ollama run llama3` I have: Error: invalid character '\x00' looking for beginning of value ### OS Windows ### GPU Nvidia ### CPU AMD ### Ollama version 0.1.33
GiteaMirror added the bugnvidiawindows labels 2026-04-28 10:45:11 -05:00
Author
Owner

@pdevine commented on GitHub (May 5, 2024):

Can you post the server logs?

<!-- gh-comment-id:2094915054 --> @pdevine commented on GitHub (May 5, 2024): Can you post the [server logs](https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-issues)?
Author
Owner

@TapsHTS commented on GitHub (May 12, 2024):

Hi !
Here is the server logs:

I have delete the previous file and I have run the command again:

time=2024-05-12T11:17:13.284+02:00 level=INFO source=routes.go:1052 msg="Listening on 127.0.0.1:11434 (version 0.1.37)"
time=2024-05-12T11:17:13.284+02:00 level=INFO source=payload.go:44 msg="Dynamic LLM libraries [cuda_v11.3 rocm_v5.7 cpu cpu_avx cpu_avx2]"
time=2024-05-12T11:17:13.407+02:00 level=INFO source=types.go:71 msg="inference compute" id=GPU-14cc9ccb-5028-c909-07c9-e5b369883d2d library=cuda compute=8.6 driver=12.4 name="NVIDIA GeForce RTX 3060" total="12.0 GiB" available="11.0 GiB"
[GIN] 2024/05/12 - 11:17:44 | 200 |            0s |       127.0.0.1 | HEAD     "/"
[GIN] 2024/05/12 - 11:17:44 | 404 |       510.9µs |       127.0.0.1 | POST     "/api/show"
[GIN] 2024/05/12 - 11:17:46 | 200 |    1.2103544s |       127.0.0.1 | POST     "/api/pull"

Ollama version: 0.1.37

<!-- gh-comment-id:2106180728 --> @TapsHTS commented on GitHub (May 12, 2024): Hi ! Here is the server logs: I have delete the previous file and I have run the command again: ```2024/05/12 11:17:13 routes.go:1006: INFO server config env="map[OLLAMA_DEBUG:false OLLAMA_LLM_LIBRARY: OLLAMA_MAX_LOADED_MODELS:1 OLLAMA_MAX_QUEUE:512 OLLAMA_MAX_VRAM:0 OLLAMA_NOPRUNE:true 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:*] OLLAMA_RUNNERS_DIR:C:\\Users\\legot\\AppData\\Local\\Programs\\Ollama\\ollama_runners OLLAMA_TMPDIR:]" time=2024-05-12T11:17:13.284+02:00 level=INFO source=routes.go:1052 msg="Listening on 127.0.0.1:11434 (version 0.1.37)" time=2024-05-12T11:17:13.284+02:00 level=INFO source=payload.go:44 msg="Dynamic LLM libraries [cuda_v11.3 rocm_v5.7 cpu cpu_avx cpu_avx2]" time=2024-05-12T11:17:13.407+02:00 level=INFO source=types.go:71 msg="inference compute" id=GPU-14cc9ccb-5028-c909-07c9-e5b369883d2d library=cuda compute=8.6 driver=12.4 name="NVIDIA GeForce RTX 3060" total="12.0 GiB" available="11.0 GiB" [GIN] 2024/05/12 - 11:17:44 | 200 | 0s | 127.0.0.1 | HEAD "/" [GIN] 2024/05/12 - 11:17:44 | 404 | 510.9µs | 127.0.0.1 | POST "/api/show" [GIN] 2024/05/12 - 11:17:46 | 200 | 1.2103544s | 127.0.0.1 | POST "/api/pull" ``` Ollama version: `0.1.37`
Author
Owner

@pdevine commented on GitHub (May 24, 2024):

@TapsHTS Was it still exhibiting the same behaviour in 0.1.37?

<!-- gh-comment-id:2130460664 --> @pdevine commented on GitHub (May 24, 2024): @TapsHTS Was it still exhibiting the same behaviour in `0.1.37`?
Author
Owner

@pdevine commented on GitHub (May 24, 2024):

@TapsHTS also, can you post an exact screenshot of the error? I'm having problems finding it in the code.

<!-- gh-comment-id:2130469598 --> @pdevine commented on GitHub (May 24, 2024): @TapsHTS also, can you post an exact screenshot of the error? I'm having problems finding it in the code.
Author
Owner

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

@TapsHTS I'm going to go ahead and close the issue. Feel free to comment and I'll reopen if you're still running into problems. Definitely upgrade to ollama 0.2.1 as well too.

<!-- gh-comment-id:2221935570 --> @pdevine commented on GitHub (Jul 11, 2024): @TapsHTS I'm going to go ahead and close the issue. Feel free to comment and I'll reopen if you're still running into problems. Definitely upgrade to ollama 0.2.1 as well too.
Author
Owner

@mowne67 commented on GitHub (Jul 12, 2024):

Hi I am running into the same issue, my ollama version is 0.2.1

<!-- gh-comment-id:2226198498 --> @mowne67 commented on GitHub (Jul 12, 2024): Hi I am running into the same issue, my ollama version is 0.2.1
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#49103