ollama/ollama-python
1
0
Fork 0
mirror of https://github.com/ollama/ollama-python.git synced 2026-07-21 09:05:23 -04:00
Code Issues 101 Packages Projects Releases 10 Wiki Activity

test asyncio_tool.py with qwen32B(distrilled by deepseek-r1) #224

New Issue
Closed
opened 2026-02-15 16:28:51 -05:00 by yindo · 2 comments
yindo commented 2026-02-15 16:28:51 -05:00
Owner
Copy Link
Copy Source

Originally created by @SoulProficiency on GitHub (Feb 18, 2025).

Prompt: What is three plus one?
Traceback (most recent call last):
File "/home/wxj/llm/llm_test/asyncio_tools.py", line 91, in
asyncio.run(main())
File "/usr/python/lib/python3.10/asyncio/runners.py", line 44, in run
return loop.run_until_complete(main)
File "/usr/python/lib/python3.10/asyncio/base_events.py", line 649, in run_until_complete
return future.result()
File "/home/wxj/llm/llm_test/asyncio_tools.py", line 57, in main
response: ChatResponse = await client.chat(
File "/usr/python/lib/python3.10/site-packages/ollama/_client.py", line 837, in chat
return await self._request(
File "/usr/python/lib/python3.10/site-packages/ollama/_client.py", line 682, in _request
return cls(**(await self._request_raw(*args, **kwargs)).json())
File "/usr/python/lib/python3.10/site-packages/ollama/_client.py", line 626, in _request_raw
raise ResponseError(e.response.text, e.response.status_code) from None
ollama._types.ResponseError: registry.ollama.ai/library/qwen32_ds:latest does not support tools (status code: 400)

Originally created by @SoulProficiency on GitHub (Feb 18, 2025). Prompt: What is three plus one? Traceback (most recent call last): File "/home/wxj/llm/llm_test/asyncio_tools.py", line 91, in <module> asyncio.run(main()) File "/usr/python/lib/python3.10/asyncio/runners.py", line 44, in run return loop.run_until_complete(main) File "/usr/python/lib/python3.10/asyncio/base_events.py", line 649, in run_until_complete return future.result() File "/home/wxj/llm/llm_test/asyncio_tools.py", line 57, in main response: ChatResponse = await client.chat( File "/usr/python/lib/python3.10/site-packages/ollama/_client.py", line 837, in chat return await self._request( File "/usr/python/lib/python3.10/site-packages/ollama/_client.py", line 682, in _request return cls(**(await self._request_raw(*args, **kwargs)).json()) File "/usr/python/lib/python3.10/site-packages/ollama/_client.py", line 626, in _request_raw raise ResponseError(e.response.text, e.response.status_code) from None ollama._types.ResponseError: registry.ollama.ai/library/qwen32_ds:latest does not support tools (status code: 400)
yindo closed this issue 2026-02-15 16:28:51 -05:00
yindo commented 2026-02-15 16:28:52 -05:00
Author
Owner
Copy Link
Copy Source

@ParthSareen commented on GitHub (Feb 20, 2025):

ollama._types.ResponseError: registry.ollama.ai/library/qwen32_ds:latest does not support tools (status code: 400)

Deepseek does not support tools at the moment

@ParthSareen commented on GitHub (Feb 20, 2025): > ollama._types.ResponseError: registry.ollama.ai/library/qwen32_ds:latest does not support tools (status code: 400) Deepseek does not support tools at the moment
yindo commented 2026-02-15 16:28:52 -05:00
Author
Owner
Copy Link
Copy Source

@SoulProficiency commented on GitHub (Feb 20, 2025):

ollama._types.ResponseError: registry.ollama.ai/library/qwen32_ds:latest does not support tools (status code: 400)

Deepseek does not support tools at the moment

i test deepseek-r1-32b(qwen32), it works：
based on qwen2.5, its easy to do
here is my step:

  1. downlond the deepseek-r1 from hugging face.
  2. use llama.cpp convert deepseek-r1 to .bin format.
  3. use llama.cpp quantize deepseek.bin with q4_0.
  4. make Modelfile with same template（ollama qwen2.5 template）
  5. run the example
    by the way,distilled model can follow the official model but the deepseek-r1 671B may not work
@SoulProficiency commented on GitHub (Feb 20, 2025): > > ollama._types.ResponseError: registry.ollama.ai/library/qwen32_ds:latest does not support tools (status code: 400) > > Deepseek does not support tools at the moment i test deepseek-r1-32b(qwen32), it works： **based on qwen2.5, its easy to do** here is my step: 1) downlond the deepseek-r1 from hugging face. 2) use llama.cpp convert deepseek-r1 to .bin format. 3) use llama.cpp quantize deepseek.bin with q4_0. 4) make Modelfile with same template（ollama qwen2.5 template） 5) run the example by the way,distilled model can follow the official model but the deepseek-r1 671B may not work
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
bug
enhancement
pull-request
Mirrored from GitHub Pull Request
 thinking
No Label
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: ollama/ollama-python#224
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?