Instructions to use Coloss/Qwen3-8B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Coloss/Qwen3-8B-Instruct with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Coloss/Qwen3-8B-Instruct") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Coloss/Qwen3-8B-Instruct") model = AutoModelForCausalLM.from_pretrained("Coloss/Qwen3-8B-Instruct") 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]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use Coloss/Qwen3-8B-Instruct with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Coloss/Qwen3-8B-Instruct" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Coloss/Qwen3-8B-Instruct", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Coloss/Qwen3-8B-Instruct
- SGLang
How to use Coloss/Qwen3-8B-Instruct 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 "Coloss/Qwen3-8B-Instruct" \ --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": "Coloss/Qwen3-8B-Instruct", "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 "Coloss/Qwen3-8B-Instruct" \ --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": "Coloss/Qwen3-8B-Instruct", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Coloss/Qwen3-8B-Instruct with Docker Model Runner:
docker model run hf.co/Coloss/Qwen3-8B-Instruct
Delete chat_template.jinja
Browse files- chat_template.jinja +0 -89
chat_template.jinja
DELETED
|
@@ -1,89 +0,0 @@
|
|
| 1 |
-
{%- if tools %}
|
| 2 |
-
{{- '<|im_start|>system\n' }}
|
| 3 |
-
{%- if messages[0].role == 'system' %}
|
| 4 |
-
{{- messages[0].content + '\n\n' }}
|
| 5 |
-
{%- endif %}
|
| 6 |
-
{{- "# 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>" }}
|
| 7 |
-
{%- for tool in tools %}
|
| 8 |
-
{{- "\n" }}
|
| 9 |
-
{{- tool | tojson }}
|
| 10 |
-
{%- endfor %}
|
| 11 |
-
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 12 |
-
{%- else %}
|
| 13 |
-
{%- if messages[0].role == 'system' %}
|
| 14 |
-
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
| 15 |
-
{%- endif %}
|
| 16 |
-
{%- endif %}
|
| 17 |
-
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 18 |
-
{%- for message in messages[::-1] %}
|
| 19 |
-
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 20 |
-
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
| 21 |
-
{%- set ns.multi_step_tool = false %}
|
| 22 |
-
{%- set ns.last_query_index = index %}
|
| 23 |
-
{%- endif %}
|
| 24 |
-
{%- endfor %}
|
| 25 |
-
{%- for message in messages %}
|
| 26 |
-
{%- if message.content is string %}
|
| 27 |
-
{%- set content = message.content %}
|
| 28 |
-
{%- else %}
|
| 29 |
-
{%- set content = '' %}
|
| 30 |
-
{%- endif %}
|
| 31 |
-
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 32 |
-
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 33 |
-
{%- elif message.role == "assistant" %}
|
| 34 |
-
{%- set reasoning_content = '' %}
|
| 35 |
-
{%- if message.reasoning_content is string %}
|
| 36 |
-
{%- set reasoning_content = message.reasoning_content %}
|
| 37 |
-
{%- else %}
|
| 38 |
-
{%- if '</think>' in content %}
|
| 39 |
-
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 40 |
-
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 41 |
-
{%- endif %}
|
| 42 |
-
{%- endif %}
|
| 43 |
-
{%- if loop.index0 > ns.last_query_index %}
|
| 44 |
-
{%- if loop.last or (not loop.last and reasoning_content) %}
|
| 45 |
-
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
| 46 |
-
{%- else %}
|
| 47 |
-
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 48 |
-
{%- endif %}
|
| 49 |
-
{%- else %}
|
| 50 |
-
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 51 |
-
{%- endif %}
|
| 52 |
-
{%- if message.tool_calls %}
|
| 53 |
-
{%- for tool_call in message.tool_calls %}
|
| 54 |
-
{%- if (loop.first and content) or (not loop.first) %}
|
| 55 |
-
{{- '\n' }}
|
| 56 |
-
{%- endif %}
|
| 57 |
-
{%- if tool_call.function %}
|
| 58 |
-
{%- set tool_call = tool_call.function %}
|
| 59 |
-
{%- endif %}
|
| 60 |
-
{{- '<tool_call>\n{"name": "' }}
|
| 61 |
-
{{- tool_call.name }}
|
| 62 |
-
{{- '", "arguments": ' }}
|
| 63 |
-
{%- if tool_call.arguments is string %}
|
| 64 |
-
{{- tool_call.arguments }}
|
| 65 |
-
{%- else %}
|
| 66 |
-
{{- tool_call.arguments | tojson }}
|
| 67 |
-
{%- endif %}
|
| 68 |
-
{{- '}\n</tool_call>' }}
|
| 69 |
-
{%- endfor %}
|
| 70 |
-
{%- endif %}
|
| 71 |
-
{{- '<|im_end|>\n' }}
|
| 72 |
-
{%- elif message.role == "tool" %}
|
| 73 |
-
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 74 |
-
{{- '<|im_start|>user' }}
|
| 75 |
-
{%- endif %}
|
| 76 |
-
{{- '\n<tool_response>\n' }}
|
| 77 |
-
{{- content }}
|
| 78 |
-
{{- '\n</tool_response>' }}
|
| 79 |
-
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 80 |
-
{{- '<|im_end|>\n' }}
|
| 81 |
-
{%- endif %}
|
| 82 |
-
{%- endif %}
|
| 83 |
-
{%- endfor %}
|
| 84 |
-
{%- if add_generation_prompt %}
|
| 85 |
-
{{- '<|im_start|>assistant\n' }}
|
| 86 |
-
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 87 |
-
{{- '<think>\n\n</think>\n\n' }}
|
| 88 |
-
{%- endif %}
|
| 89 |
-
{%- endif %}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|