Instructions to use AaryanK/ModelGate with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AaryanK/ModelGate with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="AaryanK/ModelGate",
	filename="ModelGate-Router.Q8_0.gguf",
)

llm.create_chat_completion(
	messages = "\"I like you. I love you\""
)

llama-cpp-python

How to use AaryanK/ModelGate with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="AaryanK/ModelGate",
	filename="ModelGate-Router.Q8_0.gguf",
)

llm.create_chat_completion(
	messages = "\"I like you. I love you\""
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use AaryanK/ModelGate with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf AaryanK/ModelGate:Q8_0
# Run inference directly in the terminal:
llama-cli -hf AaryanK/ModelGate:Q8_0

Install from WinGet (Windows)

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

Use Docker

docker model run hf.co/AaryanK/ModelGate:Q8_0

LM Studio
Jan
Ollama
How to use AaryanK/ModelGate with Ollama:
```
ollama run hf.co/AaryanK/ModelGate:Q8_0
```

Unsloth Studio new

How to use AaryanK/ModelGate 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 AaryanK/ModelGate 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 AaryanK/ModelGate to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for AaryanK/ModelGate to start chatting

Pi new

How to use AaryanK/ModelGate with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf AaryanK/ModelGate:Q8_0

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": "AaryanK/ModelGate:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use AaryanK/ModelGate with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf AaryanK/ModelGate: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 AaryanK/ModelGate:Q8_0

Run Hermes

hermes

Docker Model Runner
How to use AaryanK/ModelGate with Docker Model Runner:
```
docker model run hf.co/AaryanK/ModelGate:Q8_0
```

Lemonade

How to use AaryanK/ModelGate with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull AaryanK/ModelGate:Q8_0

Run and chat with the model

lemonade run user.ModelGate-Q8_0

List all available models

lemonade list

AaryanK commited on Mar 22

Commit

fe74938

verified ·

1 Parent(s): dd94c69

Change to MIT consistent with Git

Browse files

Files changed (1) hide show

README.md +32 -32

README.md CHANGED Viewed

@@ -1,44 +1,44 @@
 ---
 language:
-  - en
-license: apache-2.0
 library_name: llama-cpp-python
 base_model: katanemo/Arch-Router-1.5B
 tags:
-  - routing
-  - grpo
-  - reinforcement-learning
-  - gguf
-  - lora
-  - unsloth
-  - trl
-  - qwen2
-  - llama-cpp
-  - contract-aware
-  - cost-optimization
-  - query-classification
 model_type: qwen2
 pipeline_tag: text-classification
 datasets:
-  - custom
 metrics:
-  - accuracy
 model-index:
-  - name: ModelGate-Router
-    results:
-      - task:
-          type: text-classification
-          name: Query Complexity Classification
-        metrics:
-          - type: accuracy
-            value: 83.3
-            name: Overall Accuracy (held-out, GGUF Q8_0)
-          - type: accuracy
-            value: 85.7
-            name: Medium Tier Accuracy
-          - type: latency
-            value: 62
-            name: Avg Latency (ms, CUDA)
 ---
 <p align="center">
@@ -257,4 +257,4 @@ scripts/
   bench_mmlu.py            # MMLU benchmark runner
   mmlu_questions.json      # 60 real MMLU questions from HuggingFace
   start.sh                 # One-command startup
-```

 ---
 language:
+- en
+license: mit
 library_name: llama-cpp-python
 base_model: katanemo/Arch-Router-1.5B
 tags:
+- routing
+- grpo
+- reinforcement-learning
+- gguf
+- lora
+- unsloth
+- trl
+- qwen2
+- llama-cpp
+- contract-aware
+- cost-optimization
+- query-classification
 model_type: qwen2
 pipeline_tag: text-classification
 datasets:
+- custom
 metrics:
+- accuracy
 model-index:
+- name: ModelGate-Router
+  results:
+  - task:
+      type: text-classification
+      name: Query Complexity Classification
+    metrics:
+    - type: accuracy
+      value: 83.3
+      name: Overall Accuracy (held-out, GGUF Q8_0)
+    - type: accuracy
+      value: 85.7
+      name: Medium Tier Accuracy
+    - type: latency
+      value: 62
+      name: Avg Latency (ms, CUDA)
 ---
 <p align="center">
   bench_mmlu.py            # MMLU benchmark runner
   mmlu_questions.json      # 60 real MMLU questions from HuggingFace
   start.sh                 # One-command startup
+```