# Tokenizer.template not working with ollama

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ftokenizer-template-not-working-with-ollama%2F138389%3E%5C
**Category:** 🤗Hub\
**Created:** [February 1, 2025, 2:18am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ftokenizer-template-not-working-with-ollama%2F138389 "2025-02-01T02:18:47Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Javier-Jimenez99](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/javier-jimenez99/32/40198_2.png) [@Javier-Jimenez99](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FJavier-Jimenez99)%5C
**Post date:** [February 1, 2025, 2:18am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ftokenizer-template-not-working-with-ollama%2F138389%2F1 "2025-02-01T02:18:47Z")

</div>

Hello,

I have a question about downloading a model to run locally with ollama. It seems that new DeppSeek-R1 model doesn’t currently support function calling, but the guys from unsloth did something on their tokenizer.template to allow them.

I just want to try if the model really works with tools in ollama. I download it with :

```auto
ollama run hf.co/unsloth/DeepSeek-R1-Distill-Qwen-14B-GGUF:Q2_K_L

```

This is the tokenizer.template in Huggingface Hub:

````auto
{% if not add_generation_prompt is defined %}
{% set add_generation_prompt = false %}
{% endif %}
{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}
{%- for message in messages %}
{%- if message['role'] == 'system' %}
{% set ns.system_prompt = message['content'] %}
{%- endif %}
{%- endfor %}
{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}
{%- if message['role'] == 'user' %}
{%- set ns.is_tool = false -%}
{{'<｜User｜>' + message['content']}}{%- endif %}
{%- if message['role'] == 'assistant' and message['content'] is none %}
{%- set ns.is_tool = false -%}
{%- for tool in message['tool_calls']%}
{%- if not ns.is_first %}
{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}
{%- else %}
{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}
{%- endfor %}
{%- endif %}
{%- if message['role'] == 'assistant' and message['content'] is not none %}
{%- if ns.is_tool %}
{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}
{%- else %}
{% set content = message['content'] %}
{% if '</think>' in content %}
{% set content = content.split('</think>')[-1] %}
{% endif %}
{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}
{%- endif %}
{%- if message['role'] == 'tool' %}
{%- set ns.is_tool = true -%}
{%- if ns.is_output_first %}
{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}
{%- else %}
{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}
{%- endif %}
{%- endfor -%}
{% if ns.is_tool %}
{{'<｜tool▁outputs▁end｜>'}}{% endif %}
{% if add_generation_prompt and not ns.is_tool %}
{{'<｜Assistant｜>'}}{% endif %}

````

But his is what I get from: `ollama show hf.co/unsloth/DeepSeek-R1-Distill-Qwen-14B-GGUF:Q2_K_L --modelfile`

```auto
# Modelfile generated by "ollama show"
# To build a new Modelfile based on this, replace FROM with:
# FROM hf.co/unsloth/DeepSeek-R1-Distill-Qwen-14B-GGUF:Q2_K_L

FROM /usr/share/ollama/.ollama/models/blobs/sha256-d7b38b112a9b76e7e926fd2826b6e2aa325c9bfe41afa65742fc4f3a3a751c38
TEMPLATE """{{- if .Suffix }}<｜fim▁begin｜>{{ .Prompt }}<｜fim▁hole｜>{{ .Suffix }}<｜fim▁end｜>
{{- else if .Messages }}
{{- range $i, $_ := .Messages }}
{{- if eq .Role "user" }}<｜User｜>
{{- else if eq .Role "assistant" }}<｜Assistant｜>
{{- end }}{{ .Content }}
{{- if eq (len (slice $.Messages $i)) 1 }}
{{- if eq .Role "user" }}<｜Assistant｜>
{{- end }}
{{- else if eq .Role "assistant" }}<｜end▁of▁sentence｜><｜begin▁of▁sentence｜>
{{- end }}
{{- end }}
{{- end }}"""
PARAMETER stop <｜begin▁of▁sentence｜>
PARAMETER stop <｜end▁of▁sentence｜>
PARAMETER stop <｜User｜>
PARAMETER stop <｜Assistant｜>
PARAMETER stop <｜fim▁begin｜>
PARAMETER stop <｜fim▁hole｜>
PARAMETER stop <｜fim▁end｜>

```

As you can see the template is not the same. I know that I can change the model file and add the template by hand, but shouldn’t be this managed by Huggingface?

Have a nice day!