Instructions to use mjschock/SmolVLM2-500M-Video-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use mjschock/SmolVLM2-500M-Video-Instruct with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="mjschock/SmolVLM2-500M-Video-Instruct", filename="SmolVLM2-500M-Video-Instruct-Q8_0.gguf", )
llm.create_chat_completion( messages = "No input example has been defined for this model task." )
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- llama.cpp
How to use mjschock/SmolVLM2-500M-Video-Instruct with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf mjschock/SmolVLM2-500M-Video-Instruct:Q8_0 # Run inference directly in the terminal: llama-cli -hf mjschock/SmolVLM2-500M-Video-Instruct:Q8_0
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf mjschock/SmolVLM2-500M-Video-Instruct:Q8_0 # Run inference directly in the terminal: llama-cli -hf mjschock/SmolVLM2-500M-Video-Instruct:Q8_0
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf mjschock/SmolVLM2-500M-Video-Instruct:Q8_0 # Run inference directly in the terminal: ./llama-cli -hf mjschock/SmolVLM2-500M-Video-Instruct:Q8_0
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf mjschock/SmolVLM2-500M-Video-Instruct:Q8_0 # Run inference directly in the terminal: ./build/bin/llama-cli -hf mjschock/SmolVLM2-500M-Video-Instruct:Q8_0
Use Docker
docker model run hf.co/mjschock/SmolVLM2-500M-Video-Instruct:Q8_0
- LM Studio
- Jan
- Ollama
How to use mjschock/SmolVLM2-500M-Video-Instruct with Ollama:
ollama run hf.co/mjschock/SmolVLM2-500M-Video-Instruct:Q8_0
- Unsloth Studio
How to use mjschock/SmolVLM2-500M-Video-Instruct with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for mjschock/SmolVLM2-500M-Video-Instruct to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for mjschock/SmolVLM2-500M-Video-Instruct to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for mjschock/SmolVLM2-500M-Video-Instruct to start chatting
- Docker Model Runner
How to use mjschock/SmolVLM2-500M-Video-Instruct with Docker Model Runner:
docker model run hf.co/mjschock/SmolVLM2-500M-Video-Instruct:Q8_0
- Lemonade
How to use mjschock/SmolVLM2-500M-Video-Instruct with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull mjschock/SmolVLM2-500M-Video-Instruct:Q8_0
Run and chat with the model
lemonade run user.SmolVLM2-500M-Video-Instruct-Q8_0
List all available models
lemonade list
Add base model with custom chat template
Browse files- chat_template.jinja +4 -1
chat_template.jinja
CHANGED
|
@@ -1,4 +1,7 @@
|
|
| 1 |
<|im_start|>{% for message in messages %}{% if message['role'] == 'system' %}System: {% for line in message['content'] %}{% if line['type'] == 'text' %}{{line['text']}}{% endif %}{% endfor %}<|im_end|>
|
| 2 |
{% elif message['role'] == 'tool' %}Tool: {% for line in message['content'] %}{% if line['type'] == 'text' %}{{line['text']}}{% endif %}{% endfor %}<end_of_utterance>
|
| 3 |
-
{%
|
|
|
|
|
|
|
|
|
|
| 4 |
{% endif %}{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}
|
|
|
|
| 1 |
<|im_start|>{% for message in messages %}{% if message['role'] == 'system' %}System: {% for line in message['content'] %}{% if line['type'] == 'text' %}{{line['text']}}{% endif %}{% endfor %}<|im_end|>
|
| 2 |
{% elif message['role'] == 'tool' %}Tool: {% for line in message['content'] %}{% if line['type'] == 'text' %}{{line['text']}}{% endif %}{% endfor %}<end_of_utterance>
|
| 3 |
+
{% elif message['role'] == 'assistant' and message.get('tool_calls') %}{{message['role'] | capitalize}}: {% for line in message['content'] %}{% if line['type'] == 'text' %}{{line['text']}}{% elif line['type'] == 'image' %}{{ '<image>' }}{% endif %}{% endfor %}{% if message['tool_calls'] %}<tool_calls>
|
| 4 |
+
{% for tool_call in message['tool_calls'] %}{"id": "{{tool_call['id']}}", "type": "{{tool_call['type']}}", "function": {"name": "{{tool_call['function']['name']}}", "arguments": "{{tool_call['function']['arguments']}}"}}
|
| 5 |
+
{% endfor %}</tool_calls>{% endif %}<end_of_utterance>
|
| 6 |
+
{% else %}{{message['role'] | capitalize}}{% if message['content'][0]['type'] == 'image' %}{{':'}}{% else %}{{': '}}{% endif %}{% if message['role'] == 'assistant' %}{% generation %}{% for line in message['content'] %}{% if line['type'] == 'text' %}{{line['text']}}{% elif line['type'] == 'image' %}{{ '<image>' }}{% endif %}{% endfor %}{% endgeneration %}{% else %}{% for line in message['content'] %}{% if line['type'] == 'text' %}{{line['text']}}{% elif line['type'] == 'image' %}{{ '<image>' }}{% endif %}{% endfor %}{% endif %}<end_of_utterance>
|
| 7 |
{% endif %}{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}
|