Upload folder using huggingface_hub

README.md

@@ -86,8 +86,10 @@ Reconstructs pixel-accurate HTML/CSS from UI screenshots and supports natural-la
 For `SGLang`:
 
 ```bash
-pip install sglang>=0.5.6post1
-pip install transformers>=5.0.0rc0
+pip install sglang>=0.5.6.post1
+pip install nvidia-cudnn-cu12==9.16.0.29
+sudo apt update
+sudo apt install ffmpeg
 ```
 
 For `vLLM`:
@@ -100,7 +102,7 @@ pip install transformers>=5.0.0rc0
 ### Quick Start with Transformers
 
 ```python
-from transformers import AutoProcessor, Glm4vMoeForConditionalGeneration
+from transformers import AutoProcessor, Glm4vForConditionalGeneration
 import torch
 
 MODEL_PATH = "zai-org/GLM-4.6V-Flash"
@@ -120,7 +122,7 @@ messages = [
     }
 ]
 processor = AutoProcessor.from_pretrained(MODEL_PATH)
-model = Glm4vMoeForConditionalGeneration.from_pretrained(
+model = Glm4vForConditionalGeneration.from_pretrained(
     pretrained_model_name_or_path=MODEL_PATH,
     torch_dtype="auto",
     device_map="auto",

chat_template.jinja

@@ -86,11 +86,11 @@ For each function call, output the function name and arguments within the follow
     {%- set tc = tc.function %}
 {%- endif %}
 {{ '\n<tool_call>' + tc.name }}
-{% set _args = tc.arguments %}
-{%- if _args is mapping -%}{% for k, v in _args|items %}
+{% set _args = tc.arguments %}{% if _args is mapping %}
+{% for k, v in _args|items %}
 <arg_key>{{ k }}</arg_key>
 <arg_value>{{ v | tojson|string if v is not string else v }}</arg_value>
-{% endfor %}{% endif %}
+{% endfor %}{%- endif %}
 </tool_call>{% endfor %}
 {% endif %}
 {%- elif m.role == 'tool' -%}

tokenizer_config.json

@@ -326,5 +326,5 @@
   "remove_space": false,
   "tokenizer_class": "PreTrainedTokenizerFast",
   "unk_token": null,
-  "chat_template": "{# Unsloth template fixes #}\n[gMASK]<sop>\n{%- if tools -%}\n<|system|>\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{% for tool in tools %}\n{{ tool | tojson|string }}\n{% endfor %}\n</tools>\n\nFor each function call, output the function name and arguments within the following XML format:\n<tool_call>{function-name}\n<arg_key>{arg-key-1}</arg_key>\n<arg_value>{arg-value-1}</arg_value>\n<arg_key>{arg-key-2}</arg_key>\n<arg_value>{arg-value-2}</arg_value>\n...\n</tool_call>{%- endif -%}\n{%- macro visible_text(content) -%}\n    {%- if content is string -%}\n        {{- content }}\n    {%- elif content is iterable and content is not mapping -%}\n        {%- for item in content -%}\n            {%- if item is mapping and item.type == 'text' -%}\n                {{- item.text }}\n            {%- elif item is mapping and (item.type == 'image' or 'image' in item) -%}\n                <|begin_of_image|><|image|><|end_of_image|>\n            {%- elif item is mapping and (item.type == 'video' or 'video' in item) -%}\n                <|begin_of_video|><|video|><|end_of_video|>\n            {%- elif item is string -%}\n                {{- item }}\n            {%- endif -%}\n        {%- endfor -%}\n    {%- else -%}\n        {{- content }}\n    {%- endif -%}\n{%- endmacro -%}\n{%- set ns = namespace(last_user_index=-1) %}\n{%- for m in messages %}\n    {%- if m.role == 'user' %}\n        {% set ns.last_user_index = loop.index0 -%}\n    {%- endif %}\n{%- endfor %}\n{% for m in messages %}\n{%- if m.role == 'user' -%}<|user|>\n{% if m.content is string %}\n{{ m.content }}\n{%- else %}\n{%- for item in m.content %}\n{% if item.type == 'video' or 'video' in item %}\n<|begin_of_video|><|video|><|end_of_video|>{% elif item.type == 'image' or 'image' in item %}\n<|begin_of_image|><|image|><|end_of_image|>{% elif item.type == 'text' %}\n{{ item.text }}\n{%- endif %}\n{%- endfor %}\n{%- endif %}\n{{- '/nothink' if (enable_thinking is defined and not enable_thinking and not visible_text(m.content).endswith(\"/nothink\")) else '' -}}\n{%- elif m.role == 'assistant' -%}\n<|assistant|>\n{%- set reasoning_content = '' %}\n{%- set content = visible_text(m.content) %}\n{%- if m.reasoning_content is string %}\n    {%- set reasoning_content = m.reasoning_content %}\n{%- else %}\n    {%- if '</think>' in content %}\n        {%- set reasoning_content = ((content.split('</think>')|first).rstrip('\\n').split('<think>')|last).lstrip('\\n') %}\n        {%- set content = (content.split('</think>')|last).lstrip('\\n') %}\n    {%- endif %}\n{%- endif %}\n{%- if loop.index0 > ns.last_user_index and reasoning_content -%}\n{{ '\\n<think>' + reasoning_content.strip() +  '</think>'}}\n{%- else -%}\n{{ '\\n<think></think>' }}\n{%- endif -%}\n{%- if content.strip() -%}\n{{ '\\n' + content.strip() }}\n{%- endif -%}\n{% if m.tool_calls %}\n{% for tc in m.tool_calls %}\n{%- if tc.function %}\n    {%- set tc = tc.function %}\n{%- endif %}\n{{ '\\n<tool_call>' + tc.name }}\n{% set _args = tc.arguments %}\n{%- if _args is mapping -%}{% for k, v in _args|items %}\n<arg_key>{{ k }}</arg_key>\n<arg_value>{{ v | tojson|string if v is not string else v }}</arg_value>\n{% endfor %}{% endif %}\n</tool_call>{% endfor %}\n{% endif %}\n{%- elif m.role == 'tool' -%}\n{%- if m.content is string -%}\n{%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n    {{- '<|observation|>' }}\n{%- endif %}\n{{- '\\n<tool_response>\\n' }}\n{{- m.content }}\n{{- '\\n</tool_response>' }}\n{% elif m.content is iterable and m.content is not mapping %}\n{%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n{{- '<|observation|>' }}\n{%- endif %}\n{{- '\\n<tool_response>\\n' }}\n{%- for tr in m.content -%}\n  {%- if tr is mapping and tr.type is defined -%}\n    {%- set t = tr.type | lower -%}\n    {%- if t == 'text' and tr.text is defined -%}\n{{ tr.text }}\n    {%- elif t in ['image', 'image_url'] -%}\n<|begin_of_image|><|image|><|end_of_image|>\n    {%- elif t in ['video', 'video_url'] -%}\n<|begin_of_video|><|video|><|end_of_video|>\n    {%- else -%}\n{{ tr | tojson|string }}\n    {%- endif -%}\n  {%- else -%}\n{{ tr.output if tr.output is defined else tr }}\n  {%- endif -%}\n{%- endfor -%}\n{{- '\\n</tool_response>' }}\n{%- else -%}\n<|observation|>{% for tr in m.content %}\n\n<tool_response>\n{{ tr.output if tr.output is defined else tr }}\n</tool_response>{% endfor -%}\n{% endif -%}\n{%- elif m.role == 'system' -%}\n<|system|>\n{{ visible_text(m.content) }}\n{%- endif -%}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n<|assistant|>\n{{'<think></think>\\n' if (enable_thinking is defined and not enable_thinking) else ''}}\n{%- endif -%}\n{# Copyright 2025-present Unsloth. Apache 2.0 License. #}"
+  "chat_template": "{# Unsloth template fixes #}\n[gMASK]<sop>\n{%- if tools -%}\n<|system|>\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{% for tool in tools %}\n{{ tool | tojson|string }}\n{% endfor %}\n</tools>\n\nFor each function call, output the function name and arguments within the following XML format:\n<tool_call>{function-name}\n<arg_key>{arg-key-1}</arg_key>\n<arg_value>{arg-value-1}</arg_value>\n<arg_key>{arg-key-2}</arg_key>\n<arg_value>{arg-value-2}</arg_value>\n...\n</tool_call>{%- endif -%}\n{%- macro visible_text(content) -%}\n    {%- if content is string -%}\n        {{- content }}\n    {%- elif content is iterable and content is not mapping -%}\n        {%- for item in content -%}\n            {%- if item is mapping and item.type == 'text' -%}\n                {{- item.text }}\n            {%- elif item is mapping and (item.type == 'image' or 'image' in item) -%}\n                <|begin_of_image|><|image|><|end_of_image|>\n            {%- elif item is mapping and (item.type == 'video' or 'video' in item) -%}\n                <|begin_of_video|><|video|><|end_of_video|>\n            {%- elif item is string -%}\n                {{- item }}\n            {%- endif -%}\n        {%- endfor -%}\n    {%- else -%}\n        {{- content }}\n    {%- endif -%}\n{%- endmacro -%}\n{%- set ns = namespace(last_user_index=-1) %}\n{%- for m in messages %}\n    {%- if m.role == 'user' %}\n        {% set ns.last_user_index = loop.index0 -%}\n    {%- endif %}\n{%- endfor %}\n{% for m in messages %}\n{%- if m.role == 'user' -%}<|user|>\n{% if m.content is string %}\n{{ m.content }}\n{%- else %}\n{%- for item in m.content %}\n{% if item.type == 'video' or 'video' in item %}\n<|begin_of_video|><|video|><|end_of_video|>{% elif item.type == 'image' or 'image' in item %}\n<|begin_of_image|><|image|><|end_of_image|>{% elif item.type == 'text' %}\n{{ item.text }}\n{%- endif %}\n{%- endfor %}\n{%- endif %}\n{{- '/nothink' if (enable_thinking is defined and not enable_thinking and not visible_text(m.content).endswith(\"/nothink\")) else '' -}}\n{%- elif m.role == 'assistant' -%}\n<|assistant|>\n{%- set reasoning_content = '' %}\n{%- set content = visible_text(m.content) %}\n{%- if m.reasoning_content is string %}\n    {%- set reasoning_content = m.reasoning_content %}\n{%- else %}\n    {%- if '</think>' in content %}\n        {%- set reasoning_content = ((content.split('</think>')|first).rstrip('\\n').split('<think>')|last).lstrip('\\n') %}\n        {%- set content = (content.split('</think>')|last).lstrip('\\n') %}\n    {%- endif %}\n{%- endif %}\n{%- if loop.index0 > ns.last_user_index and reasoning_content -%}\n{{ '\\n<think>' + reasoning_content.strip() +  '</think>'}}\n{%- else -%}\n{{ '\\n<think></think>' }}\n{%- endif -%}\n{%- if content.strip() -%}\n{{ '\\n' + content.strip() }}\n{%- endif -%}\n{% if m.tool_calls %}\n{% for tc in m.tool_calls %}\n{%- if tc.function %}\n    {%- set tc = tc.function %}\n{%- endif %}\n{{ '\\n<tool_call>' + tc.name }}\n{% set _args = tc.arguments %}{% if _args is mapping %}\n{% for k, v in _args|items %}\n<arg_key>{{ k }}</arg_key>\n<arg_value>{{ v | tojson|string if v is not string else v }}</arg_value>\n{% endfor %}{%- endif %}\n</tool_call>{% endfor %}\n{% endif %}\n{%- elif m.role == 'tool' -%}\n{%- if m.content is string -%}\n{%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n    {{- '<|observation|>' }}\n{%- endif %}\n{{- '\\n<tool_response>\\n' }}\n{{- m.content }}\n{{- '\\n</tool_response>' }}\n{% elif m.content is iterable and m.content is not mapping %}\n{%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n{{- '<|observation|>' }}\n{%- endif %}\n{{- '\\n<tool_response>\\n' }}\n{%- for tr in m.content -%}\n  {%- if tr is mapping and tr.type is defined -%}\n    {%- set t = tr.type | lower -%}\n    {%- if t == 'text' and tr.text is defined -%}\n{{ tr.text }}\n    {%- elif t in ['image', 'image_url'] -%}\n<|begin_of_image|><|image|><|end_of_image|>\n    {%- elif t in ['video', 'video_url'] -%}\n<|begin_of_video|><|video|><|end_of_video|>\n    {%- else -%}\n{{ tr | tojson|string }}\n    {%- endif -%}\n  {%- else -%}\n{{ tr.output if tr.output is defined else tr }}\n  {%- endif -%}\n{%- endfor -%}\n{{- '\\n</tool_response>' }}\n{%- else -%}\n<|observation|>{% for tr in m.content %}\n\n<tool_response>\n{{ tr.output if tr.output is defined else tr }}\n</tool_response>{% endfor -%}\n{% endif -%}\n{%- elif m.role == 'system' -%}\n<|system|>\n{{ visible_text(m.content) }}\n{%- endif -%}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n<|assistant|>\n{{'<think></think>\\n' if (enable_thinking is defined and not enable_thinking) else ''}}\n{%- endif -%}\n{# Copyright 2025-present Unsloth. Apache 2.0 License. #}"
 }