Instructions to use smalinin/DeepSeek-V4.1-Flash-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use smalinin/DeepSeek-V4.1-Flash-GGUF 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 smalinin/DeepSeek-V4.1-Flash-GGUF:IQ3_XS # Run inference directly in the terminal: llama cli -hf smalinin/DeepSeek-V4.1-Flash-GGUF:IQ3_XS
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf smalinin/DeepSeek-V4.1-Flash-GGUF:IQ3_XS # Run inference directly in the terminal: llama cli -hf smalinin/DeepSeek-V4.1-Flash-GGUF:IQ3_XS
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 smalinin/DeepSeek-V4.1-Flash-GGUF:IQ3_XS # Run inference directly in the terminal: ./llama-cli -hf smalinin/DeepSeek-V4.1-Flash-GGUF:IQ3_XS
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 smalinin/DeepSeek-V4.1-Flash-GGUF:IQ3_XS # Run inference directly in the terminal: ./build/bin/llama-cli -hf smalinin/DeepSeek-V4.1-Flash-GGUF:IQ3_XS
Use Docker
docker model run hf.co/smalinin/DeepSeek-V4.1-Flash-GGUF:IQ3_XS
- LM Studio
- Jan
- vLLM
How to use smalinin/DeepSeek-V4.1-Flash-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "smalinin/DeepSeek-V4.1-Flash-GGUF" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "smalinin/DeepSeek-V4.1-Flash-GGUF", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/smalinin/DeepSeek-V4.1-Flash-GGUF:IQ3_XS
- Ollama
How to use smalinin/DeepSeek-V4.1-Flash-GGUF with Ollama:
ollama run hf.co/smalinin/DeepSeek-V4.1-Flash-GGUF:IQ3_XS
- Unsloth Desktop
- Pi
How to use smalinin/DeepSeek-V4.1-Flash-GGUF with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf smalinin/DeepSeek-V4.1-Flash-GGUF:IQ3_XS
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "smalinin/DeepSeek-V4.1-Flash-GGUF:IQ3_XS" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use smalinin/DeepSeek-V4.1-Flash-GGUF with Docker Model Runner:
docker model run hf.co/smalinin/DeepSeek-V4.1-Flash-GGUF:IQ3_XS
- Lemonade
How to use smalinin/DeepSeek-V4.1-Flash-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull smalinin/DeepSeek-V4.1-Flash-GGUF:IQ3_XS
Run and chat with the model
lemonade run user.DeepSeek-V4.1-Flash-GGUF-IQ3_XS
List all available models
lemonade list
- Hermes Agent
How to use smalinin/DeepSeek-V4.1-Flash-GGUF with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf smalinin/DeepSeek-V4.1-Flash-GGUF:IQ3_XS
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 smalinin/DeepSeek-V4.1-Flash-GGUF:IQ3_XS
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use smalinin/DeepSeek-V4.1-Flash-GGUF with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf smalinin/DeepSeek-V4.1-Flash-GGUF:IQ3_XS
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 "smalinin/DeepSeek-V4.1-Flash-GGUF:IQ3_XS" \ --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"
Upload deepseek-ai-DeepSeek-V4.1.jinja
Browse files- deepseek-ai-DeepSeek-V4.1.jinja +156 -0
deepseek-ai-DeepSeek-V4.1.jinja
ADDED
|
@@ -0,0 +1,156 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if not add_generation_prompt is defined -%}
|
| 2 |
+
{%- set add_generation_prompt = false -%}
|
| 3 |
+
{%- endif -%}
|
| 4 |
+
{%- if not thinking is defined -%}
|
| 5 |
+
{%- if enable_thinking is defined -%}
|
| 6 |
+
{%- set thinking = enable_thinking -%}
|
| 7 |
+
{%- else -%}
|
| 8 |
+
{%- set thinking = true -%}
|
| 9 |
+
{%- endif -%}
|
| 10 |
+
{%- endif -%}
|
| 11 |
+
{%- if not drop_thinking is defined -%}
|
| 12 |
+
{%- set drop_thinking = true -%}
|
| 13 |
+
{%- endif -%}
|
| 14 |
+
{%- set dsml_token = '|DSML|' -%}
|
| 15 |
+
{#- tool_calls_block_name: V4.1 -#}
|
| 16 |
+
{%- set thinking_start_token = '<think>' -%}
|
| 17 |
+
{%- set thinking_end_token = '</think>' -%}
|
| 18 |
+
{%- set system_token = '<|System|>' -%}
|
| 19 |
+
{%- set reasoning_effort_text = '' -%}
|
| 20 |
+
{%- if thinking -%}
|
| 21 |
+
{%- if not reasoning_effort is defined or reasoning_effort is none -%}
|
| 22 |
+
{%- set reasoning_budget = 75 -%}
|
| 23 |
+
{%- elif reasoning_effort is integer and reasoning_effort >= 1 and reasoning_effort <= 100 -%}
|
| 24 |
+
{%- set reasoning_budget = reasoning_effort -%}
|
| 25 |
+
{%- elif reasoning_effort == 'low' -%}
|
| 26 |
+
{%- set reasoning_budget = 50 -%}
|
| 27 |
+
{%- elif reasoning_effort == 'high' -%}
|
| 28 |
+
{%- set reasoning_budget = 75 -%}
|
| 29 |
+
{%- elif reasoning_effort == 'max' -%}
|
| 30 |
+
{%- set reasoning_budget = 100 -%}
|
| 31 |
+
{%- else -%}
|
| 32 |
+
{{- raise_exception('DeepSeek-V4.1 reasoning_effort must be low, high, max, or an integer within [1, 100]') -}}
|
| 33 |
+
{%- endif -%}
|
| 34 |
+
{%- set reasoning_effort_text = 'Reasoning Effort: ' + (reasoning_budget | string) + ' (range 1-100, the higher the value, the more thorough the reasoning)\n\n' -%}
|
| 35 |
+
{%- endif -%}
|
| 36 |
+
{%- set response_format_template = '## Response Format:\n\nYou MUST strictly adhere to the following schema to reply:\n' -%}
|
| 37 |
+
{%- set tools_header = '## Tools\n\nYou have access to a set of tools to help answer the user\'s question. You can invoke tools by writing a "<' + dsml_token + ' calls>" block like the following:\n\n<' + dsml_token + ' calls>\n<' + dsml_token + ' invoke name="$TOOL_NAME">\n<' + dsml_token + ' parameter name="$PARAMETER_NAME" string="true|false">$PARAMETER_VALUE</' + dsml_token + ' parameter>\n...\n</' + dsml_token + ' invoke>\n<' + dsml_token + ' invoke name="$TOOL_NAME2">\n...\n</' + dsml_token + ' invoke>\n</' + dsml_token + ' calls>\n\nString parameters should be specified as is and set `string="true"`. For all other types (numbers, booleans, arrays, objects), pass the value in JSON format and set `string="false"`.\n\nIf thinking_mode is enabled (triggered by ' + thinking_start_token + '), you MUST output your complete reasoning inside ' + thinking_start_token + '...' + thinking_end_token + ' BEFORE any tool calls or final response.\n\nOtherwise, output directly after ' + thinking_end_token + ' with tool calls or final response.\n\n### Available Tool Schemas\n\n' -%}
|
| 38 |
+
{%- set tools_footer = '\nYou MUST strictly follow the above defined tool name and parameter schemas to invoke tool calls.\n' -%}
|
| 39 |
+
{%- set has_tools = tools is defined and tools -%}
|
| 40 |
+
{%- set first_is_system = messages and messages[0]['role'] == 'system' -%}
|
| 41 |
+
{{- bos_token -}}
|
| 42 |
+
{%- if thinking or first_is_system or has_tools -%}
|
| 43 |
+
{{- system_token -}}
|
| 44 |
+
{{- reasoning_effort_text -}}
|
| 45 |
+
{%- if first_is_system -%}
|
| 46 |
+
{{- messages[0]['content'] or '' -}}
|
| 47 |
+
{%- endif -%}
|
| 48 |
+
{%- if has_tools -%}
|
| 49 |
+
{%- if first_is_system and messages[0]['content'] -%}
|
| 50 |
+
{{- '\n\n' -}}
|
| 51 |
+
{%- endif -%}
|
| 52 |
+
{{- tools_header -}}
|
| 53 |
+
{%- for tool in tools -%}
|
| 54 |
+
{%- if tool['type'] == 'function' -%}
|
| 55 |
+
{{- tool['function'] | tojson -}}
|
| 56 |
+
{{- '\n' -}}
|
| 57 |
+
{%- endif -%}
|
| 58 |
+
{%- endfor -%}
|
| 59 |
+
{{- tools_footer -}}
|
| 60 |
+
{%- endif -%}
|
| 61 |
+
{%- endif -%}
|
| 62 |
+
{%- if response_format is defined -%}
|
| 63 |
+
{{- '\n\n' + response_format_template + (response_format | tojson) -}}
|
| 64 |
+
{%- endif -%}
|
| 65 |
+
{%- set last_user_idx = namespace(value=-1) -%}
|
| 66 |
+
{%- set state = namespace(in_user=false, has_tool_results=false) -%}
|
| 67 |
+
{%- for message in messages -%}
|
| 68 |
+
{%- if message['role'] == 'user' or message['role'] == 'developer' or (message['role'] == 'system' and loop.index0 > 0) -%}
|
| 69 |
+
{%- set last_user_idx.value = loop.index0 -%}
|
| 70 |
+
{%- endif -%}
|
| 71 |
+
{%- if message['role'] == 'tool' -%}
|
| 72 |
+
{%- set state.has_tool_results = true -%}
|
| 73 |
+
{%- endif -%}
|
| 74 |
+
{%- endfor -%}
|
| 75 |
+
{%- for message in messages -%}
|
| 76 |
+
{%- if message['role'] == 'system' and loop.index0 == 0 -%}
|
| 77 |
+
{%- elif message['role'] == 'system' -%}
|
| 78 |
+
{%- set state.in_user = false -%}
|
| 79 |
+
{{- system_token + (message['content'] or '') -}}
|
| 80 |
+
{%- elif message['role'] == 'latest_reminder' -%}
|
| 81 |
+
{{- '<|latest_reminder|>' + (message['content'] or '') -}}
|
| 82 |
+
{%- elif message['role'] == 'user' or message['role'] == 'developer' -%}
|
| 83 |
+
{%- if state.in_user -%}
|
| 84 |
+
{{- '\n\n' -}}
|
| 85 |
+
{%- else -%}
|
| 86 |
+
{{- '<|User|>' -}}
|
| 87 |
+
{%- set state.in_user = true -%}
|
| 88 |
+
{%- endif -%}
|
| 89 |
+
{{- message['content'] or '' -}}
|
| 90 |
+
{%- elif message['role'] == 'tool' -%}
|
| 91 |
+
{%- if state.in_user -%}
|
| 92 |
+
{{- '\n\n' -}}
|
| 93 |
+
{%- else -%}
|
| 94 |
+
{{- '<|User|>' -}}
|
| 95 |
+
{%- set state.in_user = true -%}
|
| 96 |
+
{%- endif -%}
|
| 97 |
+
{{- '<tool_result>' + (message['content'] or '') + '</tool_result>' -}}
|
| 98 |
+
{%- elif message['role'] == 'assistant' -%}
|
| 99 |
+
{%- set state.in_user = false -%}
|
| 100 |
+
{{- '<|Assistant|>' -}}
|
| 101 |
+
{%- set is_after_last_user = loop.index0 > last_user_idx.value -%}
|
| 102 |
+
{%- set keep_reasoning = thinking and ((not drop_thinking) or has_tools or is_after_last_user or state.has_tool_results) -%}
|
| 103 |
+
{%- if keep_reasoning -%}
|
| 104 |
+
{{- thinking_start_token -}}
|
| 105 |
+
{%- if message['reasoning_content'] is defined and message['reasoning_content'] -%}
|
| 106 |
+
{{- message['reasoning_content'] -}}
|
| 107 |
+
{%- endif -%}
|
| 108 |
+
{{- thinking_end_token -}}
|
| 109 |
+
{%- else -%}
|
| 110 |
+
{{- thinking_end_token -}}
|
| 111 |
+
{%- endif -%}
|
| 112 |
+
{%- if message['content'] is defined and message['content'] -%}
|
| 113 |
+
{{- message['content'] -}}
|
| 114 |
+
{%- endif -%}
|
| 115 |
+
{%- if message['tool_calls'] -%}
|
| 116 |
+
{{- '\n\n<' + dsml_token + ' calls>\n' -}}
|
| 117 |
+
{%- for tool in message['tool_calls'] -%}
|
| 118 |
+
{%- set func = tool['function'] -%}
|
| 119 |
+
{%- set tool_name = func['name'] -%}
|
| 120 |
+
{%- if tool['namespace'] is defined and tool['namespace'] -%}
|
| 121 |
+
{%- set tool_name = tool['namespace'] + '::' + tool_name -%}
|
| 122 |
+
{%- elif func['namespace'] is defined and func['namespace'] -%}
|
| 123 |
+
{%- set tool_name = func['namespace'] + '::' + tool_name -%}
|
| 124 |
+
{%- endif -%}
|
| 125 |
+
{{- '<' + dsml_token + ' invoke name="' + tool_name + '">\n' -}}
|
| 126 |
+
{%- set args = func['arguments'] -%}
|
| 127 |
+
{%- if args is string -%}
|
| 128 |
+
{%- set args = args | from_json -%}
|
| 129 |
+
{%- endif -%}
|
| 130 |
+
{%- for key, val in args.items() -%}
|
| 131 |
+
{%- if val is string -%}
|
| 132 |
+
{{- '<' + dsml_token + ' parameter name="' + key + '" string="true">' + val + '</' + dsml_token + ' parameter>\n' -}}
|
| 133 |
+
{%- else -%}
|
| 134 |
+
{{- '<' + dsml_token + ' parameter name="' + key + '" string="false">' + (val | tojson) + '</' + dsml_token + ' parameter>\n' -}}
|
| 135 |
+
{%- endif -%}
|
| 136 |
+
{%- endfor -%}
|
| 137 |
+
{%- if not args -%}
|
| 138 |
+
{{- '\n' -}}
|
| 139 |
+
{%- endif -%}
|
| 140 |
+
{{- '</' + dsml_token + ' invoke>\n' -}}
|
| 141 |
+
{%- endfor -%}
|
| 142 |
+
{{- '</' + dsml_token + ' calls>' -}}
|
| 143 |
+
{%- endif -%}
|
| 144 |
+
{{- eos_token -}}
|
| 145 |
+
{%- else -%}
|
| 146 |
+
{{- raise_exception('Unsupported DeepSeek-V4.1 message role: ' + (message['role'] | string)) -}}
|
| 147 |
+
{%- endif -%}
|
| 148 |
+
{%- endfor -%}
|
| 149 |
+
{%- if add_generation_prompt -%}
|
| 150 |
+
{{- '<|Assistant|>' -}}
|
| 151 |
+
{%- if thinking -%}
|
| 152 |
+
{{- thinking_start_token -}}
|
| 153 |
+
{%- else -%}
|
| 154 |
+
{{- thinking_end_token -}}
|
| 155 |
+
{%- endif -%}
|
| 156 |
+
{%- endif -%}
|