Instructions to use saidutta69/Parable-Granite-4.1-3B-Claude-Fable-5-heretic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use saidutta69/Parable-Granite-4.1-3B-Claude-Fable-5-heretic with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="saidutta69/Parable-Granite-4.1-3B-Claude-Fable-5-heretic") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("saidutta69/Parable-Granite-4.1-3B-Claude-Fable-5-heretic") model = AutoModelForCausalLM.from_pretrained("saidutta69/Parable-Granite-4.1-3B-Claude-Fable-5-heretic", device_map="auto") 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=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use saidutta69/Parable-Granite-4.1-3B-Claude-Fable-5-heretic 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 saidutta69/Parable-Granite-4.1-3B-Claude-Fable-5-heretic:Q4_K_M # Run inference directly in the terminal: llama cli -hf saidutta69/Parable-Granite-4.1-3B-Claude-Fable-5-heretic:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf saidutta69/Parable-Granite-4.1-3B-Claude-Fable-5-heretic:Q4_K_M # Run inference directly in the terminal: llama cli -hf saidutta69/Parable-Granite-4.1-3B-Claude-Fable-5-heretic: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 saidutta69/Parable-Granite-4.1-3B-Claude-Fable-5-heretic:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf saidutta69/Parable-Granite-4.1-3B-Claude-Fable-5-heretic: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 saidutta69/Parable-Granite-4.1-3B-Claude-Fable-5-heretic:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf saidutta69/Parable-Granite-4.1-3B-Claude-Fable-5-heretic:Q4_K_M
Use Docker
docker model run hf.co/saidutta69/Parable-Granite-4.1-3B-Claude-Fable-5-heretic:Q4_K_M
- LM Studio
- Jan
- vLLM
How to use saidutta69/Parable-Granite-4.1-3B-Claude-Fable-5-heretic with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "saidutta69/Parable-Granite-4.1-3B-Claude-Fable-5-heretic" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "saidutta69/Parable-Granite-4.1-3B-Claude-Fable-5-heretic", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/saidutta69/Parable-Granite-4.1-3B-Claude-Fable-5-heretic:Q4_K_M
- SGLang
How to use saidutta69/Parable-Granite-4.1-3B-Claude-Fable-5-heretic 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 "saidutta69/Parable-Granite-4.1-3B-Claude-Fable-5-heretic" \ --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": "saidutta69/Parable-Granite-4.1-3B-Claude-Fable-5-heretic", "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 "saidutta69/Parable-Granite-4.1-3B-Claude-Fable-5-heretic" \ --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": "saidutta69/Parable-Granite-4.1-3B-Claude-Fable-5-heretic", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Ollama
How to use saidutta69/Parable-Granite-4.1-3B-Claude-Fable-5-heretic with Ollama:
ollama run hf.co/saidutta69/Parable-Granite-4.1-3B-Claude-Fable-5-heretic:Q4_K_M
- Unsloth Desktop
- Pi
How to use saidutta69/Parable-Granite-4.1-3B-Claude-Fable-5-heretic with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf saidutta69/Parable-Granite-4.1-3B-Claude-Fable-5-heretic:Q4_K_M
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": "saidutta69/Parable-Granite-4.1-3B-Claude-Fable-5-heretic:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use saidutta69/Parable-Granite-4.1-3B-Claude-Fable-5-heretic with Docker Model Runner:
docker model run hf.co/saidutta69/Parable-Granite-4.1-3B-Claude-Fable-5-heretic:Q4_K_M
- Lemonade
How to use saidutta69/Parable-Granite-4.1-3B-Claude-Fable-5-heretic with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull saidutta69/Parable-Granite-4.1-3B-Claude-Fable-5-heretic:Q4_K_M
Run and chat with the model
lemonade run user.Parable-Granite-4.1-3B-Claude-Fable-5-heretic-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use saidutta69/Parable-Granite-4.1-3B-Claude-Fable-5-heretic with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf saidutta69/Parable-Granite-4.1-3B-Claude-Fable-5-heretic: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 saidutta69/Parable-Granite-4.1-3B-Claude-Fable-5-heretic:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use saidutta69/Parable-Granite-4.1-3B-Claude-Fable-5-heretic with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf saidutta69/Parable-Granite-4.1-3B-Claude-Fable-5-heretic: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 "saidutta69/Parable-Granite-4.1-3B-Claude-Fable-5-heretic: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"
Upload tokenizer
Browse files- chat_template.jinja +114 -0
- tokenizer.json +0 -0
- tokenizer_config.json +14 -0
|
@@ -0,0 +1,114 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- set tools_system_message_prefix = 'You are a helpful assistant with access to the following tools. You may call one or more tools to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>' %}
|
| 2 |
+
{%- set tools_system_message_suffix = '\n</tools>\n\nFor each tool 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>. If a tool does not exist in the provided list of tools, notify the user that you do not have the ability to fulfill the request.' %}
|
| 3 |
+
{%- set documents_system_message_prefix = 'You are a helpful assistant with access to the following documents. You may use one or more documents to assist with the user query.\n\nYou are given a list of documents within <documents></documents> XML tags:\n<documents>' %}
|
| 4 |
+
{%- set documents_system_message_suffix = '\n</documents>\n\nWrite the response to the user\'s input by strictly aligning with the facts in the provided documents. If the information needed to answer the question is not available in the documents, inform the user that the question cannot be answered based on the available data.' %}
|
| 5 |
+
{%- if available_tools is defined and available_tools %}
|
| 6 |
+
{%- set tools = available_tools %}
|
| 7 |
+
{%- endif %}
|
| 8 |
+
{%- set ns = namespace(tools_system_message=tools_system_message_prefix,
|
| 9 |
+
documents_system_message=documents_system_message_prefix,
|
| 10 |
+
system_message=''
|
| 11 |
+
) %}
|
| 12 |
+
{%- if tools %}
|
| 13 |
+
{%- for tool in tools %}
|
| 14 |
+
{%- set ns.tools_system_message = ns.tools_system_message + '\n' + (tool | tojson) %}
|
| 15 |
+
{%- endfor %}
|
| 16 |
+
{%- set ns.tools_system_message = ns.tools_system_message + tools_system_message_suffix %}
|
| 17 |
+
{%- else %}
|
| 18 |
+
{%- set ns.tools_system_message = '' %}
|
| 19 |
+
{%- endif %}
|
| 20 |
+
{%- if documents %}
|
| 21 |
+
{%- for document in documents %}
|
| 22 |
+
{%- set ns.documents_system_message = ns.documents_system_message + '\n' + (document | tojson) %}
|
| 23 |
+
{%- endfor %}
|
| 24 |
+
{%- set ns.documents_system_message = ns.documents_system_message + documents_system_message_suffix %}
|
| 25 |
+
{%- else %}
|
| 26 |
+
{%- set ns.documents_system_message = '' %}
|
| 27 |
+
{%- endif %}
|
| 28 |
+
{%- if messages[0].role == 'system' %}
|
| 29 |
+
{%- if messages[0].content is string %}
|
| 30 |
+
{%- set ns.system_message = messages[0].content %}
|
| 31 |
+
{%- elif messages[0].content is iterable %}
|
| 32 |
+
{%- for entry in messages[0].content %}
|
| 33 |
+
{%- if entry.type== 'text' %}
|
| 34 |
+
{%- if ns.system_message != '' %}
|
| 35 |
+
{%- set ns.system_message = ns.system_message + '\n' %}
|
| 36 |
+
{%- endif %}
|
| 37 |
+
{%- set ns.system_message = ns.system_message + entry.text %}
|
| 38 |
+
{%- endif %}
|
| 39 |
+
{%- endfor %}
|
| 40 |
+
{%- endif %}
|
| 41 |
+
{%- if tools and documents %}
|
| 42 |
+
{%- set ns.system_message = ns.system_message + '\n\n' + ns.tools_system_message + '\n\n' + ns.documents_system_message %}
|
| 43 |
+
{%- elif tools %}
|
| 44 |
+
{%- set ns.system_message = ns.system_message + '\n\n' + ns.tools_system_message %}
|
| 45 |
+
{%- elif documents %}
|
| 46 |
+
{%- set ns.system_message = ns.system_message + '\n\n' + ns.documents_system_message %}
|
| 47 |
+
{%- endif %}
|
| 48 |
+
{%- else %}
|
| 49 |
+
{%- if tools and documents %}
|
| 50 |
+
{%- set ns.system_message = ns.tools_system_message + '\n\n' + ns.documents_system_message %}
|
| 51 |
+
{%- elif tools %}
|
| 52 |
+
{%- set ns.system_message = ns.tools_system_message %}
|
| 53 |
+
{%- elif documents %}
|
| 54 |
+
{%- set ns.system_message = ns.documents_system_message %}
|
| 55 |
+
{%- endif %}
|
| 56 |
+
{%- endif %}
|
| 57 |
+
{%- if ns.system_message %}
|
| 58 |
+
{{- '<|start_of_role|>system<|end_of_role|>' + ns.system_message + '<|end_of_text|>\n' }}
|
| 59 |
+
{%- endif %}
|
| 60 |
+
{%- for message in messages %}
|
| 61 |
+
{%- set content = namespace(val='') %}
|
| 62 |
+
{%- if message.content is string %}
|
| 63 |
+
{%- set content.val = message.content %}
|
| 64 |
+
{%- else %}
|
| 65 |
+
{%- if message.content is iterable %}
|
| 66 |
+
{%- for entry in message.content %}
|
| 67 |
+
{%- if entry.type== 'text' %}
|
| 68 |
+
{%- if content.val != '' %}
|
| 69 |
+
{%- set content.val = content.val + '\n' %}
|
| 70 |
+
{%- endif %}
|
| 71 |
+
{%- set content.val = content.val + entry.text %}
|
| 72 |
+
{%- endif %}
|
| 73 |
+
{%- endfor %}
|
| 74 |
+
{%- endif %}
|
| 75 |
+
{%- endif %}
|
| 76 |
+
{%- if (message.role == 'user') or (message.role == 'system' and not loop.first) %}
|
| 77 |
+
{{- '<|start_of_role|>' + message.role + '<|end_of_role|>' + content.val + '<|end_of_text|>\n' }}
|
| 78 |
+
{%- elif message.role == 'assistant' %}
|
| 79 |
+
{{- '<|start_of_role|>' + message.role + '<|end_of_role|>' + content.val }}
|
| 80 |
+
{%- if message.tool_calls %}
|
| 81 |
+
{%- for tool_call in message.tool_calls %}
|
| 82 |
+
{%- if (loop.first and content.val) or (not loop.first) %}
|
| 83 |
+
{{- '\n' }}
|
| 84 |
+
{%- endif %}
|
| 85 |
+
{%- if tool_call.function %}
|
| 86 |
+
{%- set tool_call = tool_call.function %}
|
| 87 |
+
{%- endif %}
|
| 88 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 89 |
+
{{- tool_call.name }}
|
| 90 |
+
{{- '", "arguments": ' }}
|
| 91 |
+
{%- if tool_call.arguments is string %}
|
| 92 |
+
{{- tool_call.arguments }}
|
| 93 |
+
{%- else %}
|
| 94 |
+
{{- tool_call.arguments | tojson }}
|
| 95 |
+
{%- endif %}
|
| 96 |
+
{{- '}\n</tool_call>' }}
|
| 97 |
+
{%- endfor %}
|
| 98 |
+
{%- endif %}
|
| 99 |
+
{{- '<|end_of_text|>\n' }}
|
| 100 |
+
{%- elif message.role == 'tool' %}
|
| 101 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != 'tool') %}
|
| 102 |
+
{{- '<|start_of_role|>user<|end_of_role|>' }}
|
| 103 |
+
{%- endif %}
|
| 104 |
+
{{- '\n<tool_response>\n' }}
|
| 105 |
+
{{- content.val }}
|
| 106 |
+
{{- '\n</tool_response>' }}
|
| 107 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != 'tool') %}
|
| 108 |
+
{{- '<|end_of_text|>\n' }}
|
| 109 |
+
{%- endif %}
|
| 110 |
+
{%- endif %}
|
| 111 |
+
{%- endfor %}
|
| 112 |
+
{%- if add_generation_prompt %}
|
| 113 |
+
{{- '<|start_of_role|>assistant<|end_of_role|>' }}
|
| 114 |
+
{%- endif %}
|
|
The diff for this file is too large to render.
See raw diff
|
|
|
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "<|end_of_text|>",
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "<|end_of_text|>",
|
| 7 |
+
"is_local": false,
|
| 8 |
+
"local_files_only": false,
|
| 9 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 10 |
+
"pad_token": "<|pad|>",
|
| 11 |
+
"padding_side": "left",
|
| 12 |
+
"tokenizer_class": "TokenizersBackend",
|
| 13 |
+
"unk_token": "<|unk|>"
|
| 14 |
+
}
|