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 #12719] deepseek-r1:14b does not support tools #54953

New Issue
Closed
opened 2026-04-29 08:04:24 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-29 08:04:24 -05:00
Owner
Copy Link

Originally created by @arjandouwes on GitHub (Oct 21, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/12719

What is the issue?

The LLM deepseek-r1:14b is tagged as supporting tools but when checking the capabilities the tools is missing in the capabilities section. When providing tools to deepseek-r1:14b and asking it to use it, the model responds with:

{"error":"registry.ollama.ai/library/deepseek-r1:14b does not support tools"}

Relevant log output

ollama show deepseek-r1:14b -v
  Model
    architecture        qwen2
    parameters          14.8B
    context length      131072
    embedding length    5120
    quantization        Q4_K_M

  Capabilities
    completion
    thinking

  Parameters
    stop    "<｜begin▁of▁sentence｜>"
    stop    "<｜end▁of▁sentence｜>"
    stop    "<｜User｜>"
    stop    "<｜Assistant｜>"

  Metadata
    general.architecture                      qwen2
    general.basename                          DeepSeek-R1-Distill-Qwen
    general.file_type                         15
    general.parameter_count                   1.4770033664e+10
    general.quantization_version              2
    general.size_label                        14B
    general.type                              model
    qwen2.attention.head_count                40
    qwen2.attention.head_count_kv             8
    qwen2.attention.layer_norm_rms_epsilon    1e-05
    qwen2.block_count                         48
    qwen2.context_length                      131072
    qwen2.embedding_length                    5120
    qwen2.feed_forward_length                 13824
    qwen2.rope.freq_base                      1e+06
    tokenizer.ggml.add_bos_token              true
    tokenizer.ggml.add_eos_token              false
    tokenizer.ggml.bos_token_id               151646
    tokenizer.ggml.eos_token_id               151643
    tokenizer.ggml.merges                     [Ġ Ġ ...+151386 more]
    tokenizer.ggml.model                      gpt2
    tokenizer.ggml.padding_token_id           151643
    tokenizer.ggml.pre                        qwen2
    tokenizer.ggml.token_type                 [1 1 1 ...+152061 more]
    tokenizer.ggml.tokens                     [! " # ...+152061 more]
...

OS

Windows

GPU

Nvidia

CPU

Intel

Ollama version

0.12.6

Originally created by @arjandouwes on GitHub (Oct 21, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/12719 ### What is the issue? The LLM **deepseek-r1:14b** is tagged as supporting tools but when checking the capabilities the **tools** is missing in the capabilities section. When providing tools to **deepseek-r1:14b** and asking it to use it, the model responds with: ``` {"error":"registry.ollama.ai/library/deepseek-r1:14b does not support tools"} ``` ### Relevant log output ```shell ollama show deepseek-r1:14b -v Model architecture qwen2 parameters 14.8B context length 131072 embedding length 5120 quantization Q4_K_M Capabilities completion thinking Parameters stop "<｜begin▁of▁sentence｜>" stop "<｜end▁of▁sentence｜>" stop "<｜User｜>" stop "<｜Assistant｜>" Metadata general.architecture qwen2 general.basename DeepSeek-R1-Distill-Qwen general.file_type 15 general.parameter_count 1.4770033664e+10 general.quantization_version 2 general.size_label 14B general.type model qwen2.attention.head_count 40 qwen2.attention.head_count_kv 8 qwen2.attention.layer_norm_rms_epsilon 1e-05 qwen2.block_count 48 qwen2.context_length 131072 qwen2.embedding_length 5120 qwen2.feed_forward_length 13824 qwen2.rope.freq_base 1e+06 tokenizer.ggml.add_bos_token true tokenizer.ggml.add_eos_token false tokenizer.ggml.bos_token_id 151646 tokenizer.ggml.eos_token_id 151643 tokenizer.ggml.merges [Ġ Ġ ...+151386 more] tokenizer.ggml.model gpt2 tokenizer.ggml.padding_token_id 151643 tokenizer.ggml.pre qwen2 tokenizer.ggml.token_type [1 1 1 ...+152061 more] tokenizer.ggml.tokens [! " # ...+152061 more] ... ``` ### OS Windows ### GPU Nvidia ### CPU Intel ### Ollama version 0.12.6
GiteaMirror added the bug label 2026-04-29 08:04:24 -05:00
GiteaMirror commented 2026-04-29 08:04:26 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Oct 21, 2025):

#12539

<!-- gh-comment-id:3425079630 --> @rick-github commented on GitHub (Oct 21, 2025): #12539
GiteaMirror commented 2026-04-29 08:04:27 -05:00
Author
Owner
Copy Link

@arjandouwes commented on GitHub (Oct 21, 2025):

It seems that a similar issue was logged under DeepSeek-R1 0528 models missing tool calling updates in Ollama registry #10993

<!-- gh-comment-id:3425222855 --> @arjandouwes commented on GitHub (Oct 21, 2025): It seems that a similar issue was logged under DeepSeek-R1 0528 models missing tool calling updates in Ollama registry #10993
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#54953
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?