aaa

Dockerfile

@@ -12,16 +12,11 @@ RUN python3 -c 'from huggingface_hub import hf_hub_download; \
     repo="uberkie/Qwen3-4B-Thinking-4-gguf"; \
     hf_hub_download(repo_id=repo, filename="qwen3-4B.Q4_K_M.gguf", local_dir="/app"); \
     hf_hub_download(repo_id=repo, filename="config.json", local_dir="/app")'
-COPY chat_template.jinja /app/chat_template.jinja
 CMD ["--server", \
      "-m", "/app/qwen3-4B.Q4_K_M.gguf", \
      "--host", "0.0.0.0", \
      "--port", "7860", \
      "-t", "8", \
      "-np", "1", \
-     "-c", "8096", \
-     "-n", "1024", \
-     "--n-gpu-layers", "16", \
-     "--reasoning-format", "none", \
-     "--jinja", \
-     "--chat-template-file", "/app/chat_template.jinja"]
+     "-c", "4096", \
+     "-n", "1024"]

app.py

@@ -97,12 +97,6 @@ except Exception:
     # Windows
     logger.warning("Windows, cant run time.tzset()")
 
-try:
-    time.tzset()  # type: ignore # pylint: disable=no-member
-except Exception:
-    # Windows
-    logger.warning("Windows, cant run time.tzset()")
-
 if True:
     run_cmd(
         "ls -rtl /home/user/.pyenv/versions/3.10.13/lib/python3.10/site-packages/bitsandbytes"
@@ -127,16 +121,16 @@ if True:
 if not torch.cuda.is_available():
     raise gr.Error("torch.cuda.is_available() is False, cant continue...")
 
-model_name = "uberkie/Qwen3-4B-Thinking-4-gguf"  # try
+model_name = "uberkie/qwen3-4B-self-thinking_4bit"  # try
 # model_name = "Qwen/Qwen-7B-Chat"  # gone!
 tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
 
-n_gpus = torch.cuda.device_count()
-try:
-    _ = f"{int(torch.cuda.mem_get_info()[0]/1024**3)-2}GB"
-except AssertionError:
-    _ = 0
-max_memory = {i: _ for i in range(n_gpus)}
+# n_gpus = torch.cuda.device_count()
+# try:
+#     _ = f"{int(torch.cuda.mem_get_info()[0]/1024**3)-2}GB"
+# except AssertionError:
+#     _ = 0
+# max_memory = {i: _ for i in range(n_gpus)}
 
 del sys
 # logger.remove()  # to turn on trace
@@ -372,7 +366,6 @@ with gr.Blocks(
     config = asdict(stats.value.config)
 
     def bot_stream_state(chat_history):
-        chat_history = extract_response(chat_history)
         logger.trace(f"{chat_history=}")
         yield from bot_stream(chat_history, **config)
 
@@ -634,4 +627,3 @@ if __name__ == "__main__":
     # """
 
     block.queue(max_size=2).launch(debug=True)
-

chat_template.jinja

@@ -1 +0,0 @@
-{%- set image_count = namespace(value=0) %} {%- set video_count = namespace(value=0) %} {%- macro render_content(content, do_vision_count, is_system_content=false) %} {%- if content is string %} {{- content }} {%- elif content is iterable and content is not mapping %} {%- for item in content %} {%- if 'image' in item or 'image_url' in item or item.type == 'image' %} {%- if is_system_content %} {{- raise_exception('System message cannot contain images.') }} {%- endif %} {%- if do_vision_count %} {%- set image_count.value = image_count.value + 1 %} {%- endif %} {%- if add_vision_id %} {{- 'Picture ' ~ image_count.value ~ ': ' }} {%- endif %} {{- '<|vision_start|><|image_pad|><|vision_end|>' }} {%- elif 'video' in item or item.type == 'video' %} {%- if is_system_content %} {{- raise_exception('System message cannot contain videos.') }} {%- endif %} {%- if do_vision_count %} {%- set video_count.value = video_count.value + 1 %} {%- endif %} {%- if add_vision_id %} {{- 'Video ' ~ video_count.value ~ ': ' }} {%- endif %} {{- '<|vision_start|><|video_pad|><|vision_end|>' }} {%- elif 'text' in item %} {{- item.text }} {%- else %} {{- raise_exception('Unexpected item type in content.') }} {%- endif %} {%- endfor %} {%- elif content is none or content is undefined %} {{- '' }} {%- else %} {{- raise_exception('Unexpected content type.') }} {%- endif %} {%- endmacro %} {%- if not messages %} {{- raise_exception('No messages provided.') }} {%- endif %} {%- set num_sys = 0 %} {%- set merged_system = '' %} {%- if messages[0].role == 'system' or messages[0].role == 'developer' %} {%- set first = render_content(messages[0].content, false, true)|trim %} {%- if messages|length > 1 and (messages[1].role == 'system' or messages[1].role == 'developer') %} {%- set second = render_content(messages[1].content, false, true)|trim %} {%- set merged_system = first + '\n' + second %} {%- set num_sys = 2 %} {%- else %} {%- set merged_system = first %} {%- set num_sys = 1 %} {%- endif %} {%- endif %} {%- if tools and tools is iterable and tools is not mapping %} {{- '<|im_start|>system\n' }} {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }} {%- for tool in tools %} {{- "\n" }} {{- tool | tojson }} {%- endfor %} {{- "\n</tools>" }} {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }} {%- if merged_system %} {{- '\n\n' + merged_system }} {%- endif %} {{- '<|im_end|>\n' }} {%- else %} {%- if merged_system %} {{- '<|im_start|>system\n' + merged_system + '<|im_end|>\n' }} {%- endif %} {%- endif %} {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %} {%- for message in messages[::-1] %} {%- set index = (messages|length - 1) - loop.index0 %} {%- if ns.multi_step_tool and message.role == "user" %} {%- set content = render_content(message.content, false)|trim %} {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %} {%- set ns.multi_step_tool = false %} {%- set ns.last_query_index = index %} {%- endif %} {%- endif %} {%- endfor %} {%- for message in messages %} {%- if loop.index0 >= num_sys and message.role != "system" and message.role != "developer" %} {%- set content = render_content(message.content, true)|trim %} {%- if message.role == "user" %} {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }} {%- elif message.role == "assistant" %} {%- set reasoning_content = '' %} {%- if message.reasoning_content is string %} {%- set reasoning_content = message.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 %} {%- set reasoning_content = reasoning_content|trim %} {%- if (preserve_thinking is defined and preserve_thinking is true) or (loop.index0 > ns.last_query_index) %} {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }} {%- else %} {{- '<|im_start|>' + message.role + '\n' + content }} {%- endif %} {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %} {%- for tool_call in message.tool_calls %} {%- if tool_call.function is defined %} {%- set tool_call = tool_call.function %} {%- endif %} {%- if loop.first %} {%- if content|trim %} {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }} {%- else %} {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }} {%- endif %} {%- else %} {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }} {%- endif %} {%- if tool_call.arguments is mapping %} {%- for args_name in tool_call.arguments %} {%- set args_value = tool_call.arguments[args_name] %} {{- '<parameter=' + args_name + '>\n' }} {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %} {{- args_value }} {{- '\n</parameter>\n' }} {%- endfor %} {%- endif %} {{- '</function>\n</tool_call>' }} {%- endfor %} {%- endif %} {{- '<|im_end|>\n' }} {%- elif message.role == "tool" %} {%- if loop.previtem and loop.previtem.role != "tool" %} {{- '<|im_start|>user' }} {%- endif %} {{- '\n<tool_response>\n' }} {{- content }} {{- '\n</tool_response>' }} {%- if not loop.last and loop.nextitem.role != "tool" %} {{- '<|im_end|>\n' }} {%- elif loop.last %} {{- '<|im_end|>\n' }} {%- endif %} {%- endif %} {%- endif %} {%- endfor %} {%- if add_generation_prompt %} {{- '<|im_start|>assistant\n' }} {%- if enable_thinking is defined and enable_thinking is false %} {{- '<think>\n\n</think>\n\n' }} {%- else %} {{- '<think>\n' }} {%- endif %} {%- endif %} {#- Unsloth fixes - developer role, tool calling #}