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 #11111] {"error":"\"llava:7b\" does not support generate"} #7330

New Issue
Closed
opened 2026-04-12 19:22:50 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-12 19:22:50 -05:00
Owner
Copy Link

Originally created by @fishfl on GitHub (Jun 18, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/11111

What is the issue?

The same error as qwen2.5VL.

When we try to load the multi-modal Model:llava:7b use the API:
curl http://localhost:11434/api/generate -d '{"model":"llava:7b"}'

The ollama response as follows:
{"error":""llava:7b" does not support generate"}

The same error use the CLI 'ollama run' command.

the logs:

Your new public key is:

ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIGtfRGwRWs5PLyKMMIN3ld4Tm4HJOSBzXQYWO+OEWzT6

time=2025-06-18T09:37:29.091Z level=INFO source=routes.go:1234 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES:
HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:
0 OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_
MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/root/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLL
AMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 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://* vscode-webvie
w://* vscode-file://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]"
time=2025-06-18T09:37:29.091Z level=INFO source=images.go:479 msg="total blobs: 0"
time=2025-06-18T09:37:29.091Z level=INFO source=images.go:486 msg="total unused blobs removed: 0"
time=2025-06-18T09:37:29.092Z level=INFO source=routes.go:1287 msg="Listening on [::]:11434 (version 0.9.0)"
time=2025-06-18T09:37:29.092Z level=INFO source=gpu.go:217 msg="looking for compatible GPUs"
time=2025-06-18T09:37:29.102Z level=INFO source=gpu.go:377 msg="no compatible GPUs were discovered"
time=2025-06-18T09:37:29.102Z level=INFO source=types.go:130 msg="inference compute" id=0 library=cpu variant="" compute="" driver=0.0 name="" total="375.9
GiB" available="109.3 GiB"
time=2025-06-18T09:40:48.874Z level=ERROR source=images.go:90 msg="couldn't decode ggml" error=EOF
[GIN] 2025/06/18 - 09:40:48 | 400 | 1.420815ms | 10.149.27.129 | POST "/api/chat"
[GIN] 2025/06/18 - 09:42:18 | 200 | 46.531µs | 127.0.0.1 | HEAD "/"
[GIN] 2025/06/18 - 09:42:18 | 200 | 448.135µs | 127.0.0.1 | GET "/api/tags"
[GIN] 2025/06/18 - 09:42:25 | 200 | 46.517µs | 127.0.0.1 | HEAD "/"
[GIN] 2025/06/18 - 09:42:25 | 200 | 123.973µs | 127.0.0.1 | GET "/api/ps"
time=2025-06-18T09:42:31.427Z level=ERROR source=images.go:90 msg="couldn't decode ggml" error=EOF
[GIN] 2025/06/18 - 09:42:31 | 400 | 845.128µs | 127.0.0.1 | POST "/api/chat"
time=2025-06-18T09:42:59.984Z level=ERROR source=images.go:90 msg="couldn't decode ggml" error=EOF
[GIN] 2025/06/18 - 09:42:59 | 400 | 1.205107ms | 127.0.0.1 | POST "/api/generate"
[GIN] 2025/06/18 - 09:46:20 | 200 | 40.065µs | 127.0.0.1 | HEAD "/"
[GIN] 2025/06/18 - 09:46:20 | 200 | 33.703µs | 127.0.0.1 | GET "/api/ps"
[GIN] 2025/06/18 - 09:46:24 | 200 | 40.982µs | 127.0.0.1 | HEAD "/"
[GIN] 2025/06/18 - 09:46:24 | 200 | 357.713µs | 127.0.0.1 | GET "/api/tags"
time=2025-06-18T09:46:55.932Z level=ERROR source=images.go:90 msg="couldn't decode ggml" error=EOF
[GIN] 2025/06/18 - 09:46:55 | 400 | 1.218459ms | 127.0.0.1 | POST "/api/generate"

Relevant log output

uname -r
5.10.109-1.el7.x86_64

OS

Linux

GPU

No response

CPU

Intel

Ollama version

0.9.0

Originally created by @fishfl on GitHub (Jun 18, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/11111 ### What is the issue? The same error as qwen2.5VL. When we try to load the multi-modal Model:llava:7b use the API: curl http://localhost:11434/api/generate -d '{"model":"llava:7b"}' The ollama response as follows: {"error":"\"llava:7b\" does not support generate"} The same error use the CLI 'ollama run' command. the logs: Your new public key is: ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIGtfRGwRWs5PLyKMMIN3ld4Tm4HJOSBzXQYWO+OEWzT6 time=2025-06-18T09:37:29.091Z level=INFO source=routes.go:1234 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD: 0 OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_ MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/root/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLL AMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 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://* vscode-webvie w://* vscode-file://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]" time=2025-06-18T09:37:29.091Z level=INFO source=images.go:479 msg="total blobs: 0" time=2025-06-18T09:37:29.091Z level=INFO source=images.go:486 msg="total unused blobs removed: 0" time=2025-06-18T09:37:29.092Z level=INFO source=routes.go:1287 msg="Listening on [::]:11434 (version 0.9.0)" time=2025-06-18T09:37:29.092Z level=INFO source=gpu.go:217 msg="looking for compatible GPUs" time=2025-06-18T09:37:29.102Z level=INFO source=gpu.go:377 msg="no compatible GPUs were discovered" time=2025-06-18T09:37:29.102Z level=INFO source=types.go:130 msg="inference compute" id=0 library=cpu variant="" compute="" driver=0.0 name="" total="375.9 GiB" available="109.3 GiB" time=2025-06-18T09:40:48.874Z level=ERROR source=images.go:90 msg="couldn't decode ggml" error=EOF [GIN] 2025/06/18 - 09:40:48 | 400 | 1.420815ms | 10.149.27.129 | POST "/api/chat" [GIN] 2025/06/18 - 09:42:18 | 200 | 46.531µs | 127.0.0.1 | HEAD "/" [GIN] 2025/06/18 - 09:42:18 | 200 | 448.135µs | 127.0.0.1 | GET "/api/tags" [GIN] 2025/06/18 - 09:42:25 | 200 | 46.517µs | 127.0.0.1 | HEAD "/" [GIN] 2025/06/18 - 09:42:25 | 200 | 123.973µs | 127.0.0.1 | GET "/api/ps" time=2025-06-18T09:42:31.427Z level=ERROR source=images.go:90 msg="couldn't decode ggml" error=EOF [GIN] 2025/06/18 - 09:42:31 | 400 | 845.128µs | 127.0.0.1 | POST "/api/chat" time=2025-06-18T09:42:59.984Z level=ERROR source=images.go:90 msg="couldn't decode ggml" error=EOF [GIN] 2025/06/18 - 09:42:59 | 400 | 1.205107ms | 127.0.0.1 | POST "/api/generate" [GIN] 2025/06/18 - 09:46:20 | 200 | 40.065µs | 127.0.0.1 | HEAD "/" [GIN] 2025/06/18 - 09:46:20 | 200 | 33.703µs | 127.0.0.1 | GET "/api/ps" [GIN] 2025/06/18 - 09:46:24 | 200 | 40.982µs | 127.0.0.1 | HEAD "/" [GIN] 2025/06/18 - 09:46:24 | 200 | 357.713µs | 127.0.0.1 | GET "/api/tags" time=2025-06-18T09:46:55.932Z level=ERROR source=images.go:90 msg="couldn't decode ggml" error=EOF [GIN] 2025/06/18 - 09:46:55 | 400 | 1.218459ms | 127.0.0.1 | POST "/api/generate" ### Relevant log output ```shell uname -r 5.10.109-1.el7.x86_64 ``` ### OS Linux ### GPU _No response_ ### CPU Intel ### Ollama version 0.9.0
GiteaMirror added the bug label 2026-04-12 19:22:50 -05:00
GiteaMirror commented 2026-04-12 19:22:52 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jun 18, 2025):

#11103

<!-- gh-comment-id:2983657544 --> @rick-github commented on GitHub (Jun 18, 2025): #11103
GiteaMirror commented 2026-04-12 19:22:52 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jun 18, 2025):

Actually, this may be a different issue that causes the same results.

<!-- gh-comment-id:2983678817 --> @rick-github commented on GitHub (Jun 18, 2025): Actually, this may be a different issue that causes the same results.
GiteaMirror commented 2026-04-12 19:22:53 -05:00
Author
Owner
Copy Link

@Ales999 commented on GitHub (Jun 18, 2025):

And this (get example with https://ollama.com/library/codellama ):

$ ollama run codellama:7b-code '# A simple python function to remove whitespace from a string:'
Error: "codellama:7b-code" does not support generate
<!-- gh-comment-id:2984017337 --> @Ales999 commented on GitHub (Jun 18, 2025): And this (get example with https://ollama.com/library/codellama ): ```bash $ ollama run codellama:7b-code '# A simple python function to remove whitespace from a string:' Error: "codellama:7b-code" does not support generate ```
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 bug
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#7330
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?