chore: import upstream snapshot with attribution

examples/pooling/embed/template/dse_qwen2_vl.jinja

@@ -0,0 +1,7 @@
+{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}{% raw %}<|im_start|>system
+You are a helpful assistant.<|im_end|>
+{% endraw %}{% endif %}<|im_start|>{{ message['role'] }}{% raw %}
+{% endraw %}{% if message['content'] is string %}{{ message['content'] }}<|im_end|>{% raw %}
+{% endraw %}{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>{% raw %}
+{% endraw %}{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant{% raw %}
+{% endraw %}{% endif %}<|endoftext|>

examples/pooling/embed/template/nemotron_embed_vl.jinja

@@ -0,0 +1,20 @@
+{%- if messages | length > 1 -%}
+    {{ raise_exception('Embedding models should only embed one message at a time') }}
+{%- endif -%}
+
+{% set vars = namespace(prefix='', images=[], texts=[]) %}
+{%- for message in messages -%}
+    {%- if message['role'] == 'query' -%}
+        {%- set vars.prefix = 'query: ' %}
+    {%- elif message['role'] == 'document' -%}
+        {%- set vars.prefix = 'passage: ' %}
+    {%- endif -%}
+    {%- for content in message['content'] -%}
+        {%- if content['type'] == 'text' -%}
+            {%- set vars.texts = vars.texts + [content['text']] %}
+        {%- elif content['type'] == 'image' -%}
+            {%- set vars.images = vars.images + ['<image> '] %}
+        {%- endif -%}
+    {%- endfor -%}
+{%- endfor -%}
+{{- bos_token }}{{ vars.prefix }}{{ (vars.images + vars.texts) | join('') }}

examples/pooling/embed/template/vlm2vec_phi3v.jinja

@@ -0,0 +1,16 @@
+{%- if messages | length > 1 -%}
+    {{ raise_exception('Embedding models should only embed one message at a time') }}
+{%- endif -%}
+
+{% set vars = namespace(parts=[], next_image_id=1) %}
+{%- for message in messages -%}
+    {%- for content in message['content'] -%}
+        {%- if content['type'] == 'text' -%}
+            {%- set vars.parts = vars.parts + [content['text']] %}
+        {%- elif content['type'] == 'image' -%}
+            {%- set vars.parts = vars.parts + ['<|image_{i:d}|>'.format(i=vars.next_image_id)] %}
+            {%- set vars.next_image_id = vars.next_image_id + 1 %}
+        {%- endif -%}
+    {%- endfor -%}
+{%- endfor -%}
+{{ vars.parts | join(' ') }}

examples/pooling/embed/template/vlm2vec_qwen2vl.jinja

@@ -0,0 +1,15 @@
+{%- if messages | length > 1 -%}
+    {{ raise_exception('Embedding models should only embed one message at a time') }}
+{%- endif -%}
+
+{% set vars = namespace(parts=[]) %}
+{%- for message in messages -%}
+    {%- for content in message['content'] -%}
+        {%- if content['type'] == 'text' -%}
+            {%- set vars.parts = vars.parts + [content['text']] %}
+        {%- elif content['type'] == 'image' -%}
+            {%- set vars.parts = vars.parts + ['<|image_pad|>'] %}
+        {%- endif -%}
+    {%- endfor -%}
+{%- endfor -%}
+{{ vars.parts | join(' ') }}