Instructions to use Luimas/claim-extractor-qwen3b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Luimas/claim-extractor-qwen3b 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 Luimas/claim-extractor-qwen3b:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Luimas/claim-extractor-qwen3b:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Luimas/claim-extractor-qwen3b:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Luimas/claim-extractor-qwen3b: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 Luimas/claim-extractor-qwen3b:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Luimas/claim-extractor-qwen3b: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 Luimas/claim-extractor-qwen3b:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Luimas/claim-extractor-qwen3b:Q4_K_M

Use Docker

docker model run hf.co/Luimas/claim-extractor-qwen3b:Q4_K_M

LM Studio
Jan
Ollama
How to use Luimas/claim-extractor-qwen3b with Ollama:
```
ollama run hf.co/Luimas/claim-extractor-qwen3b:Q4_K_M
```
Unsloth Desktop

How to use Luimas/claim-extractor-qwen3b with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Luimas/claim-extractor-qwen3b: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": "Luimas/claim-extractor-qwen3b:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Luimas/claim-extractor-qwen3b with Docker Model Runner:
```
docker model run hf.co/Luimas/claim-extractor-qwen3b:Q4_K_M
```

Lemonade

How to use Luimas/claim-extractor-qwen3b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Luimas/claim-extractor-qwen3b:Q4_K_M

Run and chat with the model

lemonade run user.claim-extractor-qwen3b-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Luimas/claim-extractor-qwen3b with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Luimas/claim-extractor-qwen3b: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 Luimas/claim-extractor-qwen3b:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Luimas/claim-extractor-qwen3b with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Luimas/claim-extractor-qwen3b: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 "Luimas/claim-extractor-qwen3b: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"

claim-extractor-qwen3b / claim.gbnf

Luimas

Upload claim.gbnf with huggingface_hub

b116331 verified 3 months ago

Raw

History Blame Contribute Delete

1.46 kB


	root ::= "{" ws "\"summary\"" ws ":" ws string ws "," ws "\"publication_date\"" ws ":" ws datev ws "," ws "\"keywords\"" ws ":" ws strarray ws "," ws "\"claims\"" ws ":" ws claimarr ws "," ws "\"contradictions\"" ws ":" ws conarr ws "}" ws
	datev ::= string \| "null"
	strarray ::= "[" ws ( string ( ws "," ws string )* )? ws "]"
	claimarr ::= "[" ws ( claim ( ws "," ws claim )* )? ws "]"
	claim ::= "{" ws "\"id\"" ws ":" ws int ws "," ws "\"claim\"" ws ":" ws string ws "," ws "\"claim_type\"" ws ":" ws ctype ws "," ws "\"category\"" ws ":" ws string ws "," ws "\"importance\"" ws ":" ws imp ws "," ws "\"stance\"" ws ":" ws stance ws "," ws "\"evidence_span\"" ws ":" ws string ws "," ws "\"confidence\"" ws ":" ws number ws "}"
	conarr ::= "[" ws ( con ( ws "," ws con )* )? ws "]"
	con ::= "{" ws "\"claim_a\"" ws ":" ws int ws "," ws "\"claim_b\"" ws ":" ws int ws "," ws "\"relation\"" ws ":" ws rel ws "," ws "\"explanation\"" ws ":" ws string ws "}"
	ctype ::= "\"fact\"" \| "\"statistic\"" \| "\"opinion\"" \| "\"prediction\"" \| "\"speculation\"" \| "\"rhetoric\"" \| "\"other\""
	imp ::= "\"high\"" \| "\"medium\"" \| "\"low\""
	stance ::= "\"asserted\"" \| "\"denied\"" \| "\"hedged\"" \| "\"attributed\""
	rel ::= "\"contradiction\"" \| "\"tension\""
	int ::= [0-9]+
	number ::= ("0" \| "1") ("." [0-9]+)?
	string ::= "\"" ( [^"\\] \| "\\" ["\\/bfnrt] )* "\""
	ws ::= [ \t\n]*