Instructions to use TensorVizion/Loi-LLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use TensorVizion/Loi-LLM 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 TensorVizion/Loi-LLM
# Run inference directly in the terminal:
llama cli -hf TensorVizion/Loi-LLM

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf TensorVizion/Loi-LLM
# Run inference directly in the terminal:
llama cli -hf TensorVizion/Loi-LLM

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 TensorVizion/Loi-LLM
# Run inference directly in the terminal:
./llama-cli -hf TensorVizion/Loi-LLM

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 TensorVizion/Loi-LLM
# Run inference directly in the terminal:
./build/bin/llama-cli -hf TensorVizion/Loi-LLM

Use Docker

docker model run hf.co/TensorVizion/Loi-LLM

LM Studio
Jan
Ollama
How to use TensorVizion/Loi-LLM with Ollama:
```
ollama run hf.co/TensorVizion/Loi-LLM
```
Unsloth Desktop

How to use TensorVizion/Loi-LLM with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf TensorVizion/Loi-LLM

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": "TensorVizion/Loi-LLM"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use TensorVizion/Loi-LLM with Docker Model Runner:
```
docker model run hf.co/TensorVizion/Loi-LLM
```

Lemonade

How to use TensorVizion/Loi-LLM with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull TensorVizion/Loi-LLM

Run and chat with the model

lemonade run user.Loi-LLM-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use TensorVizion/Loi-LLM with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf TensorVizion/Loi-LLM

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 TensorVizion/Loi-LLM

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use TensorVizion/Loi-LLM with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf TensorVizion/Loi-LLM

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 "TensorVizion/Loi-LLM" \
  --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"

TensorVizion commited on 16 days ago

Commit

c3fa31e

verified ·

1 Parent(s): a01e851

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -16

README.md CHANGED Viewed

@@ -8,7 +8,7 @@ license: llama3.2
 ## Model Overview
-Vector AI is a conversational language model fine-tuned from Llama 3.2 3B Instruct using QLoRA (4-bit quantized low-rank adaptation). It is designed for general chat and assistant tasks, with training focused on improving conversational coherence, instruction following, and response quality at the 3B parameter scale.
 | Property | Value |
 | --- | --- |
@@ -60,22 +60,10 @@ This repository includes four files for different use cases:
 Download either GGUF file and load directly in LM Studio, Ollama, or llama.cpp:
     # Q6 — recommended for quality (requires ~3.5 GB RAM)
-    llama-cli -m vector-ai-q6.gguf -p "You are Vector AI." --chat-template llama3
     # Q4 — recommended for speed / lower memory (~2.5 GB RAM)
-    llama-cli -m vector-ai-q4.gguf -p "You are Vector AI." --chat-template llama3
-* * *
-## Chat Template
-Vector AI uses the standard Llama 3.2 Instruct chat template:
-    <|begin_of_text|><|start_header_id|>system<|end_header_id|>
-    You are Vector AI, a helpful assistant.<|eot_id|>
-    <|start_header_id|>user<|end_header_id|>
-    {your message here}<|eot_id|>
-    <|start_header_id|>assistant<|end_header_id|>
 * * *
@@ -111,7 +99,7 @@ For more deterministic / factual responses, lower temperature to `0.3–0.5`.
 * English only. Performance on other languages is untested.
 * 3B parameter scale — will be outperformed on complex reasoning tasks by larger models.
 * Not trained for code generation, mathematics, or domain-specific professional tasks.
-* Like all language models, Vector AI can produce inaccurate or hallucinated responses. Always verify important information.
 * Not aligned for safety-critical or high-stakes applications.
 * * *

 ## Model Overview
+### Loi AI is a conversational language model fine-tuned from Llama 3.2 3B Instruct using QLoRA (4-bit quantized low-rank adaptation). It is designed for general chat and assistant tasks, with training focused on improving conversational coherence, instruction following, and response quality at the 3B parameter scale.
 | Property | Value |
 | --- | --- |
 Download either GGUF file and load directly in LM Studio, Ollama, or llama.cpp:
     # Q6 — recommended for quality (requires ~3.5 GB RAM)
+    llama-cli -m vector-ai-q6.gguf -p "You are Loi AI." --chat-template llama3
     # Q4 — recommended for speed / lower memory (~2.5 GB RAM)
+    llama-cli -m vector-ai-q4.gguf -p "You are Loi AI." --chat-template llama3
 * * *
 * English only. Performance on other languages is untested.
 * 3B parameter scale — will be outperformed on complex reasoning tasks by larger models.
 * Not trained for code generation, mathematics, or domain-specific professional tasks.
+* Like all language models, Loi AI can produce inaccurate or hallucinated responses. Always verify important information.
 * Not aligned for safety-critical or high-stakes applications.
 * * *