Text Generation
Transformers
Safetensors
qwen3
conversational
text-generation-inference
8-bit precision
compressed-tensors
Instructions to use medimed/MNLP_M2_quantized_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use medimed/MNLP_M2_quantized_model with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="medimed/MNLP_M2_quantized_model") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("medimed/MNLP_M2_quantized_model") model = AutoModelForCausalLM.from_pretrained("medimed/MNLP_M2_quantized_model") 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 medimed/MNLP_M2_quantized_model with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "medimed/MNLP_M2_quantized_model" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "medimed/MNLP_M2_quantized_model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/medimed/MNLP_M2_quantized_model
- SGLang
How to use medimed/MNLP_M2_quantized_model 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 "medimed/MNLP_M2_quantized_model" \ --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": "medimed/MNLP_M2_quantized_model", "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 "medimed/MNLP_M2_quantized_model" \ --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": "medimed/MNLP_M2_quantized_model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use medimed/MNLP_M2_quantized_model with Docker Model Runner:
docker model run hf.co/medimed/MNLP_M2_quantized_model
File size: 4,718 Bytes
efc56e5 c6a4778 efc56e5 c6a4778 efc56e5 c6a4778 efc56e5 c6a4778 efc56e5 c6a4778 efc56e5 c6a4778 efc56e5 c6a4778 efc56e5 c6a4778 efc56e5 c6a4778 efc56e5 c6a4778 efc56e5 c6a4778 efc56e5 c6a4778 efc56e5 c6a4778 efc56e5 c6a4778 efc56e5 c6a4778 efc56e5 c6a4778 efc56e5 c6a4778 efc56e5 c6a4778 efc56e5 c6a4778 efc56e5 c6a4778 efc56e5 c6a4778 efc56e5 c6a4778 efc56e5 c6a4778 efc56e5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 |
{%- if tools %}
{{- '<|im_start|>system
' }}
{%- if messages[0].role == 'system' %}
{{- messages[0].content + '
' }}
{%- endif %}
{{- "# 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 }}
{%- endfor %}
{{- "
</tools>
For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
<tool_call>
{\"name\": <function-name>, \"arguments\": <args-json-object>}
</tool_call><|im_end|>
" }}
{%- else %}
{%- if messages[0].role == 'system' %}
{{- '<|im_start|>system
' + messages[0].content + '<|im_end|>
' }}
{%- endif %}
{%- endif %}
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
{%- for forward_message in messages %}
{%- set index = (messages|length - 1) - loop.index0 %}
{%- set message = messages[index] %}
{%- set current_content = message.content if message.content is not none else '' %}
{%- set tool_start = '<tool_response>' %}
{%- set tool_start_length = tool_start|length %}
{%- set start_of_message = current_content[:tool_start_length] %}
{%- set tool_end = '</tool_response>' %}
{%- set tool_end_length = tool_end|length %}
{%- set start_pos = (current_content|length) - tool_end_length %}
{%- if start_pos < 0 %}
{%- set start_pos = 0 %}
{%- endif %}
{%- set end_of_message = current_content[start_pos:] %}
{%- if ns.multi_step_tool and message.role == "user" and not(start_of_message == tool_start and end_of_message == tool_end) %}
{%- set ns.multi_step_tool = false %}
{%- set ns.last_query_index = index %}
{%- endif %}
{%- endfor %}
{%- for message in messages %}
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
{{- '<|im_start|>' + message.role + '
' + message.content + '<|im_end|>' + '
' }}
{%- elif message.role == "assistant" %}
{%- set content = message.content %}
{%- set reasoning_content = '' %}
{%- if message.reasoning_content is defined and message.reasoning_content is not none %}
{%- set reasoning_content = message.reasoning_content %}
{%- else %}
{%- if '</think>' in message.content %}
{%- set content = (message.content.split('</think>')|last).lstrip('
') %}
{%- set reasoning_content = (message.content.split('</think>')|first).rstrip('
') %}
{%- set reasoning_content = (reasoning_content.split('<think>')|last).lstrip('
') %}
{%- endif %}
{%- endif %}
{%- if loop.index0 > ns.last_query_index %}
{%- if loop.last or (not loop.last and reasoning_content) %}
{{- '<|im_start|>' + message.role + '
<think>
' + reasoning_content.strip('
') + '
</think>
' + content.lstrip('
') }}
{%- else %}
{{- '<|im_start|>' + message.role + '
' + content }}
{%- endif %}
{%- else %}
{{- '<|im_start|>' + message.role + '
' + content }}
{%- endif %}
{%- if message.tool_calls %}
{%- for tool_call in message.tool_calls %}
{%- if (loop.first and content) or (not loop.first) %}
{{- '
' }}
{%- endif %}
{%- if tool_call.function %}
{%- set tool_call = tool_call.function %}
{%- endif %}
{{- '<tool_call>
{"name": "' }}
{{- tool_call.name }}
{{- '", "arguments": ' }}
{%- if tool_call.arguments is string %}
{{- tool_call.arguments }}
{%- else %}
{{- tool_call.arguments | tojson }}
{%- endif %}
{{- '}
</tool_call>' }}
{%- endfor %}
{%- endif %}
{{- '<|im_end|>
' }}
{%- elif message.role == "tool" %}
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
{{- '<|im_start|>user' }}
{%- endif %}
{{- '
<tool_response>
' }}
{{- message.content }}
{{- '
</tool_response>' }}
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
{{- '<|im_end|>
' }}
{%- endif %}
{%- endif %}
{%- endfor %}
{%- if add_generation_prompt %}
{{- '<|im_start|>assistant
' }}
{%- if enable_thinking is defined and enable_thinking is false %}
{{- '<think>
</think>
' }}
{%- endif %}
{%- endif %}
|