Text Generation
Transformers
Safetensors
qwen3
triton
kernel-generation
reinforcement-learning
code
conversational
text-generation-inference
Instructions to use hkust-nlp/drkernel-14b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use hkust-nlp/drkernel-14b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="hkust-nlp/drkernel-14b") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("hkust-nlp/drkernel-14b") model = AutoModelForCausalLM.from_pretrained("hkust-nlp/drkernel-14b") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use hkust-nlp/drkernel-14b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "hkust-nlp/drkernel-14b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "hkust-nlp/drkernel-14b", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/hkust-nlp/drkernel-14b
- SGLang
How to use hkust-nlp/drkernel-14b with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "hkust-nlp/drkernel-14b" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "hkust-nlp/drkernel-14b", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "hkust-nlp/drkernel-14b" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "hkust-nlp/drkernel-14b", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use hkust-nlp/drkernel-14b with Docker Model Runner:
docker model run hf.co/hkust-nlp/drkernel-14b
| {% macro render_extra_keys(json_dict, handled_keys) %} | |
| {%- if json_dict is mapping %} | |
| {%- for json_key in json_dict if json_key not in handled_keys %} | |
| {%- if json_dict[json_key] is mapping %} | |
| {{- ' | |
| <' ~ json_key ~ '>' ~ (json_dict[json_key] | tojson | safe) ~ '</' ~ json_key ~ '>' }} | |
| {%- else %} | |
| {{-' | |
| <' ~ json_key ~ '>' ~ (json_dict[json_key] | string) ~ '</' ~ json_key ~ '>' }} | |
| {%- endif %} | |
| {%- endfor %} | |
| {%- endif %} | |
| {% endmacro %} | |
| {%- if messages[0]["role"] == "system" %} | |
| {%- set system_message = messages[0]["content"] %} | |
| {%- set loop_messages = messages[1:] %} | |
| {%- else %} | |
| {%- set loop_messages = messages %} | |
| {%- endif %} | |
| {%- if not tools is defined %} | |
| {%- set tools = [] %} | |
| {%- endif %} | |
| {%- if system_message is defined %} | |
| {{- "<|im_start|>system | |
| " + system_message }} | |
| {%- else %} | |
| {%- if tools is iterable and tools | length > 0 %} | |
| {{- "<|im_start|>system | |
| You are Qwen, a helpful AI assistant that can interact with a computer to solve tasks." }} | |
| {%- endif %} | |
| {%- endif %} | |
| {%- if tools is iterable and tools | length > 0 %} | |
| {{- " | |
| You have access to the following functions: | |
| " }} | |
| {{- "<tools>" }} | |
| {%- for tool in tools %} | |
| {%- if tool.function is defined %} | |
| {%- set tool = tool.function %} | |
| {%- endif %} | |
| {{- " | |
| <function> | |
| <name>" ~ tool.name ~ "</name>" }} | |
| {%- if tool.description is defined %} | |
| {{- ' | |
| <description>' ~ (tool.description | trim) ~ '</description>' }} | |
| {%- endif %} | |
| {{- ' | |
| <parameters>' }} | |
| {%- if tool.parameters is defined and tool.parameters is mapping and tool.parameters.properties is defined and tool.parameters.properties is mapping %} | |
| {%- for param_name, param_fields in tool.parameters.properties|items %} | |
| {{- ' | |
| <parameter>' }} | |
| {{- ' | |
| <name>' ~ param_name ~ '</name>' }} | |
| {%- if param_fields.type is defined %} | |
| {{- ' | |
| <type>' ~ (param_fields.type | string) ~ '</type>' }} | |
| {%- endif %} | |
| {%- if param_fields.description is defined %} | |
| {{- ' | |
| <description>' ~ (param_fields.description | trim) ~ '</description>' }} | |
| {%- endif %} | |
| {%- set handled_keys = ['name', 'type', 'description'] %} | |
| {{- render_extra_keys(param_fields, handled_keys) }} | |
| {{- ' | |
| </parameter>' }} | |
| {%- endfor %} | |
| {%- endif %} | |
| {% set handled_keys = ['type', 'properties'] %} | |
| {{- render_extra_keys(tool.parameters, handled_keys) }} | |
| {{- ' | |
| </parameters>' }} | |
| {%- set handled_keys = ['type', 'name', 'description', 'parameters'] %} | |
| {{- render_extra_keys(tool, handled_keys) }} | |
| {{- ' | |
| </function>' }} | |
| {%- endfor %} | |
| {{- " | |
| </tools>" }} | |
| {{- ' | |
| If you choose to call a function ONLY reply in the following format with NO suffix: | |
| <tool_call> | |
| <function=example_function_name> | |
| <parameter=example_parameter_1> | |
| value_1 | |
| </parameter> | |
| <parameter=example_parameter_2> | |
| This is the value for the second parameter | |
| that can span | |
| multiple lines | |
| </parameter> | |
| </function> | |
| </tool_call> | |
| <IMPORTANT> | |
| Reminder: | |
| - Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags | |
| - Required parameters MUST be specified | |
| - You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after | |
| - 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 | |
| </IMPORTANT>' }} | |
| {%- endif %} | |
| {%- if system_message is defined %} | |
| {{- '<|im_end|> | |
| ' }} | |
| {%- else %} | |
| {%- if tools is iterable and tools | length > 0 %} | |
| {{- '<|im_end|> | |
| ' }} | |
| {%- endif %} | |
| {%- endif %} | |
| {%- for message in loop_messages %} | |
| {%- if message.role == "assistant" and message.tool_calls is defined and message.tool_calls is iterable and message.tool_calls | length > 0 %} | |
| {{- '<|im_start|>' + message.role }} | |
| {%- if message.content is defined and message.content is string and message.content | trim | length > 0 %} | |
| {{- ' | |
| ' + message.content | trim + ' | |
| ' }} | |
| {%- endif %} | |
| {%- for tool_call in message.tool_calls %} | |
| {%- if tool_call.function is defined %} | |
| {%- set tool_call = tool_call.function %} | |
| {%- endif %} | |
| {{- ' | |
| <tool_call> | |
| <function=' + tool_call.name + '> | |
| ' }} | |
| {%- if tool_call.arguments is defined %} | |
| {%- for args_name, args_value in tool_call.arguments|items %} | |
| {{- '<parameter=' + args_name + '> | |
| ' }} | |
| {%- set args_value = args_value | tojson | safe if args_value is mapping else args_value | string %} | |
| {{- args_value }} | |
| {{- ' | |
| </parameter> | |
| ' }} | |
| {%- endfor %} | |
| {%- endif %} | |
| {{- '</function> | |
| </tool_call>' }} | |
| {%- endfor %} | |
| {{- '<|im_end|> | |
| ' }} | |
| {%- elif message.role == "user" or message.role == "system" or message.role == "assistant" %} | |
| {{- '<|im_start|>' + message.role + ' | |
| ' + message.content + '<|im_end|>' + ' | |
| ' }} | |
| {%- elif message.role == "tool" %} | |
| {%- if loop.previtem and loop.previtem.role != "tool" %} | |
| {{- '<|im_start|>user | |
| ' }} | |
| {%- endif %} | |
| {{- '<tool_response> | |
| ' }} | |
| {{- message.content }} | |
| {{- ' | |
| </tool_response> | |
| ' }} | |
| {%- if not loop.last and loop.nextitem.role != "tool" %} | |
| {{- '<|im_end|> | |
| ' }} | |
| {%- elif loop.last %} | |
| {{- '<|im_end|> | |
| ' }} | |
| {%- endif %} | |
| {%- else %} | |
| {{- '<|im_start|>' + message.role + ' | |
| ' + message.content + '<|im_end|> | |
| ' }} | |
| {%- endif %} | |
| {%- endfor %} | |
| {%- if add_generation_prompt %} | |
| {{- '<|im_start|>assistant | |
| ' }} | |
| {%- endif %} | |