Instructions to use deepquillapp/trait-verifier with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deepquillapp/trait-verifier with Laya:

# No code snippets available yet for this library.

# To use this model, check the repository files and the library's documentation.

# Want to help? PRs adding snippets are welcome at:
# https://github.com/huggingface/huggingface.js

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use deepquillapp/trait-verifier 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 deepquillapp/trait-verifier:Q8_0
# Run inference directly in the terminal:
llama cli -hf deepquillapp/trait-verifier:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf deepquillapp/trait-verifier:Q8_0
# Run inference directly in the terminal:
llama cli -hf deepquillapp/trait-verifier: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 deepquillapp/trait-verifier:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf deepquillapp/trait-verifier: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 deepquillapp/trait-verifier:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf deepquillapp/trait-verifier:Q8_0

Use Docker

docker model run hf.co/deepquillapp/trait-verifier:Q8_0

Llama new
LM Studio
Jan
Ollama
How to use deepquillapp/trait-verifier with Ollama:
```
ollama run hf.co/deepquillapp/trait-verifier:Q8_0
```
Unsloth Desktop

How to use deepquillapp/trait-verifier with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf deepquillapp/trait-verifier:Q8_0

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": "deepquillapp/trait-verifier:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use deepquillapp/trait-verifier with Docker Model Runner:
```
docker model run hf.co/deepquillapp/trait-verifier:Q8_0
```

Lemonade

How to use deepquillapp/trait-verifier with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull deepquillapp/trait-verifier:Q8_0

Run and chat with the model

lemonade run user.trait-verifier-Q8_0

List all available models

lemonade list

Hermes Agent

How to use deepquillapp/trait-verifier with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf deepquillapp/trait-verifier:Q8_0

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 deepquillapp/trait-verifier:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use deepquillapp/trait-verifier with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf deepquillapp/trait-verifier:Q8_0

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 "deepquillapp/trait-verifier:Q8_0" \
  --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"

partnerinflight commited on 25 days ago

Commit

506cf3a

verified ·

1 Parent(s): be0cfad

Round 3: adds LLM Validation (is this a character / location?); traits keep-F1 0.761, interactions macro-F1 0.480/0.653; config schema v3

Browse files

Files changed (2) hide show

model.w8.onnx +2 -2
verifier_config.json +32 -4

model.w8.onnx CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43da4b57e197d176563db9398f2a3bf63d516b206cf17bef8666798664a4fae4
-size 643661234

 version https://git-lfs.github.com/spec/v1
+oid sha256:b6186a6cd75d837f1a83e8b3732fd0b7696eaec2004d61d2549a4536fd1897f5
+size 643636914

verifier_config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "schema": "deepquill-laya-verifier-v2",
   "checks": [
     "aboutTarget",
     "lasting",
@@ -75,7 +75,7 @@
   "max_len": 512,
   "head_max_len": 192,
   "option_max_tokens": 48,
-  "temperature": 1.0257667303085327,
   "threshold": 0.5,
   "interaction": {
     "types": [
@@ -99,9 +99,37 @@
       "passage"
     ],
     "qtype": 0,
-    "temperature": 1.4447057247161865,
     "max_len": 768,
-    "bias": null
   },
   "inputs": [
     "input_ids",

 {
+  "schema": "deepquill-laya-verifier-v3",
   "checks": [
     "aboutTarget",
     "lasting",
   "max_len": 512,
   "head_max_len": 192,
   "option_max_tokens": 48,
+  "temperature": 1.54689359664917,
   "threshold": 0.5,
   "interaction": {
     "types": [
       "passage"
     ],
     "qtype": 0,
+    "temperature": 1.4507882595062256,
     "max_len": 768,
+    "bias": [
+      0.5,
+      0.1,
+      0.0,
+      0.0,
+      1.0
+    ]
+  },
+  "validation": {
+    "types": {
+      "character": {
+        "ins": "NAME refers to a character: one specific individual in the story who acts, speaks, thinks, is addressed, or is talked about as that individual.",
+        "true": "a person, being or named animal of the story, including minor or off-stage ones, or a title used as one person's name",
+        "false": "an allusion or comparison to someone outside the story, a group or nationality, a concept, thing or place, or a cut or padded name"
+      },
+      "location": {
+        "ins": "NAME is the proper name of a specific place in the story: a city, region, country, street, building, estate or fictional place, used as a place.",
+        "true": "a named place in the story's world",
+        "false": "a person's name, a nationality, an organisation, a common noun, an abstraction, or a cut or padded name"
+      }
+    },
+    "state_keys": [
+      "name",
+      "passage"
+    ],
+    "qtype": 2,
+    "temperature": 1.54689359664917,
+    "threshold": 0.5,
+    "max_len": 512
   },
   "inputs": [
     "input_ids",