Instructions to use NaruseShiroha/capybara-math-smol-WebCoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use NaruseShiroha/capybara-math-smol-WebCoder with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="NaruseShiroha/capybara-math-smol-WebCoder") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("NaruseShiroha/capybara-math-smol-WebCoder") model = AutoModelForCausalLM.from_pretrained("NaruseShiroha/capybara-math-smol-WebCoder") 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]:])) - llama-cpp-python
How to use NaruseShiroha/capybara-math-smol-WebCoder with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="NaruseShiroha/capybara-math-smol-WebCoder", filename="unsloth.F16.gguf", )
llm.create_chat_completion( messages = [ { "role": "user", "content": "What is the capital of France?" } ] ) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use NaruseShiroha/capybara-math-smol-WebCoder with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf NaruseShiroha/capybara-math-smol-WebCoder:Q4_K_M # Run inference directly in the terminal: llama cli -hf NaruseShiroha/capybara-math-smol-WebCoder:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf NaruseShiroha/capybara-math-smol-WebCoder:Q4_K_M # Run inference directly in the terminal: llama cli -hf NaruseShiroha/capybara-math-smol-WebCoder:Q4_K_M
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 NaruseShiroha/capybara-math-smol-WebCoder:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf NaruseShiroha/capybara-math-smol-WebCoder:Q4_K_M
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 NaruseShiroha/capybara-math-smol-WebCoder:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf NaruseShiroha/capybara-math-smol-WebCoder:Q4_K_M
Use Docker
docker model run hf.co/NaruseShiroha/capybara-math-smol-WebCoder:Q4_K_M
- LM Studio
- Jan
- vLLM
How to use NaruseShiroha/capybara-math-smol-WebCoder with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "NaruseShiroha/capybara-math-smol-WebCoder" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "NaruseShiroha/capybara-math-smol-WebCoder", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/NaruseShiroha/capybara-math-smol-WebCoder:Q4_K_M
- SGLang
How to use NaruseShiroha/capybara-math-smol-WebCoder 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 "NaruseShiroha/capybara-math-smol-WebCoder" \ --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": "NaruseShiroha/capybara-math-smol-WebCoder", "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 "NaruseShiroha/capybara-math-smol-WebCoder" \ --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": "NaruseShiroha/capybara-math-smol-WebCoder", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Ollama
How to use NaruseShiroha/capybara-math-smol-WebCoder with Ollama:
ollama run hf.co/NaruseShiroha/capybara-math-smol-WebCoder:Q4_K_M
- Unsloth Studio
How to use NaruseShiroha/capybara-math-smol-WebCoder 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 NaruseShiroha/capybara-math-smol-WebCoder 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 NaruseShiroha/capybara-math-smol-WebCoder to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for NaruseShiroha/capybara-math-smol-WebCoder to start chatting
- Pi
How to use NaruseShiroha/capybara-math-smol-WebCoder with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf NaruseShiroha/capybara-math-smol-WebCoder:Q4_K_M
Configure the model in Pi
# Install Pi: npm install -g @mariozechner/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "NaruseShiroha/capybara-math-smol-WebCoder:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use NaruseShiroha/capybara-math-smol-WebCoder with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf NaruseShiroha/capybara-math-smol-WebCoder:Q4_K_M
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:8080/v1 hermes config set model.default NaruseShiroha/capybara-math-smol-WebCoder:Q4_K_M
Run Hermes
hermes
- Atomic Chat new
- OpenClaw new
How to use NaruseShiroha/capybara-math-smol-WebCoder with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf NaruseShiroha/capybara-math-smol-WebCoder:Q4_K_M
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:8080/v1 \ --custom-model-id "NaruseShiroha/capybara-math-smol-WebCoder:Q4_K_M" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
- Docker Model Runner
How to use NaruseShiroha/capybara-math-smol-WebCoder with Docker Model Runner:
docker model run hf.co/NaruseShiroha/capybara-math-smol-WebCoder:Q4_K_M
- Lemonade
How to use NaruseShiroha/capybara-math-smol-WebCoder with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull NaruseShiroha/capybara-math-smol-WebCoder:Q4_K_M
Run and chat with the model
lemonade run user.capybara-math-smol-WebCoder-Q4_K_M
List all available models
lemonade list
| {%- set default_syscontent = "<|start_sysinfo|>Name: CapybaraR1-WebDev (ultrasmol edition). Developed by: Pablonara Labs. Knowledge Cutoff: June 2024. Reasoning effort: Medium<|end_sysinfo|> | |
| system | |
| " -%} | |
| {%- if tools %} | |
| {{- '<|im_start|>system | |
| ' }} | |
| {%- if messages and messages[0].role == 'system' %} | |
| {{- messages[0].content + ' | |
| ' }} | |
| {%- else %} | |
| {{- default_syscontent+' | |
| ' }} | |
| {%- 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. The tool call and its JSON object must be on a single line. | |
| <tool_call>{"name": "function_name", "arguments": {"arg": "value"}}</tool_call><|im_end|> | |
| {%- else %} | |
| {{- '<|im_start|>system | |
| ' }} | |
| {%- if messages and messages[0].role == 'system' %} | |
| {{- messages[0].content }} | |
| {%- else %} | |
| {{- default_syscontent }} | |
| {%- endif %} | |
| {{- '<|im_end|> | |
| ' }} | |
| {# MODIFICATION END #} | |
| {%- 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" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %} | |
| {%- set ns.multi_step_tool = false %} | |
| {%- set ns.last_query_index = index %} | |
| {%- endif %} | |
| {%- endfor %} | |
| {%- for message in messages %} | |
| {%- if message.content is string %} | |
| {%- set content = message.content %} | |
| {%- else %} | |
| {%- set content = '' %} | |
| {%- endif %} | |
| {%- if (message.role == "user") or (message.role == "system" and not loop.first) %} | |
| {{- '<|im_start|>' + message.role + ' | |
| ' + content + '<|im_end|>' + ' | |
| ' }} | |
| {%- elif message.role == "assistant" %} | |
| {%- set reasoning_content = '' %} | |
| {%- if message.reasoning_content is string %} | |
| {%- set reasoning_content = message.reasoning_content %} | |
| {%- else %} | |
| {%- if '</reasoning>' in content %} | |
| {%- set temp_parts = content.split('</reasoning>') %} | |
| {%- set potential_reasoning = temp_parts[0] %} | |
| {%- set content = temp_parts[1] %} | |
| {# ADDED CHECK: Only split for reasoning if the opening tag also exists #} | |
| {%- if '<reasoning>' in potential_reasoning %} | |
| {%- set reasoning_parts = potential_reasoning.split('<reasoning>') %} | |
| {%- if reasoning_parts|length > 1 %} | |
| {%- set reasoning_content = reasoning_parts[1] %} | |
| {%- endif %} | |
| {%- endif %} | |
| {%- endif %} | |
| {%- endif %} | |
| {%- if loop.index0 > ns.last_query_index %} | |
| {%- if loop.last or (not loop.last and reasoning_content) %} | |
| {{- '<|im_start|>' + message.role + ' | |
| <reasoning> | |
| ' + reasoning_content.strip(' | |
| ') + ' | |
| </reasoning> | |
| ' + 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> | |
| ' }} | |
| {{- 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 | |
| <reasoning> | |
| ' }} | |
| {%- endif %} |