Add files using upload-large-folder tool

chat_template.jinja

@@ -0,0 +1,140 @@
+[gMASK]<sop>
+{%- if tools -%}
+<|system|>
+# Tools
+
+You may call one or more functions to assist with the user query.
+
+You are provided with function signatures within <tools></tools> XML tags:
+<tools>
+{% for tool in tools %}
+{{ tool | tojson(ensure_ascii=False) }}
+{% endfor %}
+</tools>
+
+For each function call, output the function name and arguments within the following XML format:
+<tool_call>{function-name}
+<arg_key>{arg-key-1}</arg_key>
+<arg_value>{arg-value-1}</arg_value>
+<arg_key>{arg-key-2}</arg_key>
+<arg_value>{arg-value-2}</arg_value>
+...
+</tool_call>{%- endif -%}
+{%- macro visible_text(content) -%}
+    {%- if content is string -%}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping -%}
+        {%- for item in content -%}
+            {%- if item is mapping and item.type == 'text' -%}
+                {{- item.text }}
+            {%- elif item is mapping and (item.type == 'image' or 'image' in item) -%}
+                <|begin_of_image|><|image|><|end_of_image|>
+            {%- elif item is mapping and (item.type == 'video' or 'video' in item) -%}
+                <|begin_of_video|><|video|><|end_of_video|>
+            {%- elif item is string -%}
+                {{- item }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{- content }}
+    {%- endif -%}
+{%- endmacro -%}
+{%- set ns = namespace(last_user_index=-1) %}
+{%- for m in messages %}
+    {%- if m.role == 'user' %}
+        {% set ns.last_user_index = loop.index0 -%}
+    {%- endif %}
+{%- endfor %}
+{% for m in messages %}
+{%- if m.role == 'user' -%}<|user|>
+{% if m.content is string %}
+{{ m.content }}
+{%- else %}
+{%- for item in m.content %}
+{% if item.type == 'video' or 'video' in item %}
+<|begin_of_video|><|video|><|end_of_video|>{% elif item.type == 'image' or 'image' in item %}
+<|begin_of_image|><|image|><|end_of_image|>{% elif item.type == 'text' %}
+{{ item.text }}
+{%- endif %}
+{%- endfor %}
+{%- endif %}
+{{- '/nothink' if (enable_thinking is defined and not enable_thinking and not visible_text(m.content).endswith("/nothink")) else '' -}}
+{%- elif m.role == 'assistant' -%}
+<|assistant|>
+{%- set reasoning_content = '' %}
+{%- set content = visible_text(m.content) %}
+{%- if m.reasoning_content is string %}
+    {%- set reasoning_content = m.reasoning_content %}
+{%- else %}
+    {%- if '</think>' in content %}
+        {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+        {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+    {%- endif %}
+{%- endif %}
+{%- if loop.index0 > ns.last_user_index and reasoning_content -%}
+{{ '\n<think>' + reasoning_content.strip() +  '</think>'}}
+{%- else -%}
+{{ '\n<think></think>' }}
+{%- endif -%}
+{%- if content.strip() -%}
+{{ '\n' + content.strip() }}
+{%- endif -%}
+{% if m.tool_calls %}
+{% for tc in m.tool_calls %}
+{%- if tc.function %}
+    {%- set tc = tc.function %}
+{%- endif %}
+{{ '\n<tool_call>' + tc.name }}
+{% set _args = tc.arguments %}
+{% for k, v in _args.items() %}
+<arg_key>{{ k }}</arg_key>
+<arg_value>{{ v | tojson(ensure_ascii=False) if v is not string else v }}</arg_value>
+{% endfor %}
+</tool_call>{% endfor %}
+{% endif %}
+{%- elif m.role == 'tool' -%}
+{%- if m.content is string -%}
+{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+    {{- '<|observation|>' }}
+{%- endif %}
+{{- '\n<tool_response>\n' }}
+{{- m.content }}
+{{- '\n</tool_response>' }}
+{% elif m.content is iterable and m.content is not mapping %}
+{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+{{- '<|observation|>' }}
+{%- endif %}
+{{- '\n<tool_response>\n' }}
+{%- for tr in m.content -%}
+  {%- if tr is mapping and tr.type is defined -%}
+    {%- set t = tr.type | lower -%}
+    {%- if t == 'text' and tr.text is defined -%}
+{{ tr.text }}
+    {%- elif t in ['image', 'image_url'] -%}
+<|begin_of_image|><|image|><|end_of_image|>
+    {%- elif t in ['video', 'video_url'] -%}
+<|begin_of_video|><|video|><|end_of_video|>
+    {%- else -%}
+{{ tr | tojson(ensure_ascii=False) }}
+    {%- endif -%}
+  {%- else -%}
+{{ tr.output if tr.output is defined else tr }}
+  {%- endif -%}
+{%- endfor -%}
+{{- '\n</tool_response>' }}
+{%- else -%}
+<|observation|>{% for tr in m.content %}
+
+<tool_response>
+{{ tr.output if tr.output is defined else tr }}
+</tool_response>{% endfor -%}
+{% endif -%}
+{%- elif m.role == 'system' -%}
+<|system|>
+{{ visible_text(m.content) }}
+{%- endif -%}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+<|assistant|>
+{{'<think></think>\n' if (enable_thinking is defined and not enable_thinking) else ''}}
+{%- endif -%}

model/params/lm_head/kernel/.zarray

@@ -0,0 +1 @@
+{"chunks":[1024,151552],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,151552],"zarr_format":2}

model/params/model/language_model/embed_tokens/embedding/.zarray

@@ -0,0 +1 @@
+{"chunks":[37888,4096],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[151552,4096],"zarr_format":2}

model/params/model/language_model/layers/0/input_layernorm/kernel/.zarray

@@ -0,0 +1 @@
+{"chunks":[4096],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096],"zarr_format":2}

model/params/model/language_model/layers/0/mlp/down_proj/kernel/.zarray

@@ -0,0 +1 @@
+{"chunks":[13696,1024],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[13696,4096],"zarr_format":2}

model/params/model/language_model/layers/0/mlp/gate_up_proj/kernel/.zarray

@@ -0,0 +1 @@
+{"chunks":[1024,27392],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,27392],"zarr_format":2}

model/params/model/language_model/layers/0/post_attention_layernorm/kernel/.zarray

@@ -0,0 +1 @@
+{"chunks":[4096],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096],"zarr_format":2}

model/params/model/language_model/layers/0/post_mlp_layernorm/kernel/.zarray

@@ -0,0 +1 @@
+{"chunks":[4096],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096],"zarr_format":2}

model/params/model/language_model/layers/0/post_self_attn_layernorm/kernel/.zarray

@@ -0,0 +1 @@
+{"chunks":[4096],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096],"zarr_format":2}

model/params/model/language_model/layers/0/self_attn/k_proj/bias/.zarray

@@ -0,0 +1 @@
+{"chunks":[256],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[256],"zarr_format":2}

model/params/model/language_model/layers/0/self_attn/k_proj/kernel/.zarray

@@ -0,0 +1 @@
+{"chunks":[1024,256],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,256],"zarr_format":2}

model/params/model/language_model/layers/0/self_attn/q_proj/bias/.zarray

@@ -0,0 +1 @@
+{"chunks":[4096],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096],"zarr_format":2}

model/params/model/language_model/layers/0/self_attn/q_proj/kernel/.zarray

@@ -0,0 +1 @@
+{"chunks":[1024,4096],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,4096],"zarr_format":2}

model/params/model/language_model/layers/0/self_attn/v_proj/bias/.zarray

@@ -0,0 +1 @@
+{"chunks":[256],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[256],"zarr_format":2}

model/params/model/language_model/layers/0/self_attn/v_proj/kernel/.zarray

@@ -0,0 +1 @@
+{"chunks":[1024,256],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,256],"zarr_format":2}

model/params/model/language_model/layers/1/input_layernorm/kernel/.zarray

@@ -0,0 +1 @@
+{"chunks":[4096],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096],"zarr_format":2}

model/params/model/language_model/layers/1/mlp/gate_up_proj/kernel/.zarray

@@ -0,0 +1 @@
+{"chunks":[1024,27392],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,27392],"zarr_format":2}

model/params/model/language_model/layers/1/post_attention_layernorm/kernel/.zarray

@@ -0,0 +1 @@
+{"chunks":[4096],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096],"zarr_format":2}

model/params/model/language_model/layers/1/post_mlp_layernorm/kernel/.zarray

@@ -0,0 +1 @@
+{"chunks":[4096],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096],"zarr_format":2}

model/params/model/language_model/layers/1/post_self_attn_layernorm/kernel/.zarray

@@ -0,0 +1 @@
+{"chunks":[4096],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096],"zarr_format":2}

model/params/model/language_model/layers/1/self_attn/k_proj/bias/.zarray

@@ -0,0 +1 @@
+{"chunks":[256],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[256],"zarr_format":2}

model/params/model/language_model/layers/1/self_attn/k_proj/kernel/.zarray

@@ -0,0 +1 @@
+{"chunks":[1024,256],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,256],"zarr_format":2}

model/params/model/language_model/layers/1/self_attn/o_proj/kernel/.zarray

@@ -0,0 +1 @@
+{"chunks":[4096,1024],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,4096],"zarr_format":2}

model/params/model/language_model/layers/1/self_attn/q_proj/bias/.zarray

@@ -0,0 +1 @@
+{"chunks":[4096],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096],"zarr_format":2}

model/params/model/language_model/layers/1/self_attn/q_proj/kernel/.zarray

@@ -0,0 +1 @@
+{"chunks":[1024,4096],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,4096],"zarr_format":2}

model/params/model/language_model/layers/1/self_attn/v_proj/bias/.zarray

@@ -0,0 +1 @@
+{"chunks":[256],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[256],"zarr_format":2}

model/params/model/language_model/layers/1/self_attn/v_proj/kernel/.zarray

@@ -0,0 +1 @@
+{"chunks":[1024,256],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,256],"zarr_format":2}

model/params/model/language_model/layers/10/mlp/down_proj/kernel/.zarray

@@ -0,0 +1 @@
+{"chunks":[13696,1024],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[13696,4096],"zarr_format":2}

model/params/model/language_model/layers/10/mlp/gate_up_proj/kernel/.zarray

@@ -0,0 +1 @@
+{"chunks":[1024,27392],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,27392],"zarr_format":2}

model/params/model/language_model/layers/10/post_attention_layernorm/kernel/.zarray

@@ -0,0 +1 @@
+{"chunks":[4096],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096],"zarr_format":2}

model/params/model/language_model/layers/10/post_self_attn_layernorm/kernel/.zarray

@@ -0,0 +1 @@
+{"chunks":[4096],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096],"zarr_format":2}

model/params/model/language_model/layers/10/self_attn/k_proj/bias/.zarray

@@ -0,0 +1 @@
+{"chunks":[256],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[256],"zarr_format":2}

model/params/model/language_model/layers/10/self_attn/k_proj/kernel/.zarray

@@ -0,0 +1 @@
+{"chunks":[1024,256],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,256],"zarr_format":2}

model/params/model/language_model/layers/10/self_attn/o_proj/kernel/.zarray

@@ -0,0 +1 @@
+{"chunks":[4096,1024],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,4096],"zarr_format":2}