Instructions to use THARX/THAR.0X with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use THARX/THAR.0X with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="THARX/THAR.0X",
	filename="THAR.0X-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = "\"The answer to the universe is undefined.\""
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use THARX/THAR.0X with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf THARX/THAR.0X:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf THARX/THAR.0X:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf THARX/THAR.0X:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf THARX/THAR.0X: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 THARX/THAR.0X:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf THARX/THAR.0X: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 THARX/THAR.0X:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf THARX/THAR.0X:Q4_K_M

Use Docker

docker model run hf.co/THARX/THAR.0X:Q4_K_M

LM Studio
Jan
Ollama
How to use THARX/THAR.0X with Ollama:
```
ollama run hf.co/THARX/THAR.0X:Q4_K_M
```

Unsloth Studio

How to use THARX/THAR.0X 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 THARX/THAR.0X 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 THARX/THAR.0X to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for THARX/THAR.0X to start chatting

How to use THARX/THAR.0X with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf THARX/THAR.0X:Q4_K_M

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": "THARX/THAR.0X:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use THARX/THAR.0X with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf THARX/THAR.0X: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 THARX/THAR.0X:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use THARX/THAR.0X with Docker Model Runner:
```
docker model run hf.co/THARX/THAR.0X:Q4_K_M
```

Lemonade

How to use THARX/THAR.0X with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull THARX/THAR.0X:Q4_K_M

Run and chat with the model

lemonade run user.THAR.0X-Q4_K_M

List all available models

lemonade list

THARX commited on 15 days ago

Commit

3067009

1 Parent(s): 8e6dc17

docs: clean up all external model listings for pure standalone THAR.0X identity

Browse files

Files changed (3) hide show

Modelfile +0 -8
README.md +1 -29
config.json +0 -9

Modelfile CHANGED Viewed

@@ -6,14 +6,6 @@
 # ║  1. Install Ollama:  curl -fsSL https://ollama.com/install.sh | sh  ║
 # ║  2. Build model:     ollama create THAR.0X -f Modelfile     ║
 # ║  3. Run:             ollama run THAR.0X                     ║
-# ║                                                             ║
-# ║  Change the FROM line to use a different base model:        ║
-# ║    Best quality:   FROM qwen2.5:32b                        ║
-# ║    Recommended:    FROM qwen2.5:14b                        ║
-# ║    Default/Fast:   FROM llama3.2                           ║
-# ║    Creative:       FROM mistral                            ║
-# ║    Coding:         FROM qwen2.5-coder:14b                  ║
-# ║    Ultra-light:    FROM llama3.2:1b                        ║
 # ╚══════════════════════════════════════════════════════════════╝
 FROM llama3.2

 # ║  1. Install Ollama:  curl -fsSL https://ollama.com/install.sh | sh  ║
 # ║  2. Build model:     ollama create THAR.0X -f Modelfile     ║
 # ║  3. Run:             ollama run THAR.0X                     ║
 # ╚══════════════════════════════════════════════════════════════╝
 FROM llama3.2

README.md CHANGED Viewed

@@ -44,12 +44,9 @@ ollama create THAR.0X -f Modelfile
 # Run it
 ollama run THAR.0X
-# Use a more powerful base:
-# Edit the first line of Modelfile to: FROM qwen2.5:14b
-# Then rebuild: ollama create THAR.0X -f Modelfile
 ```
 **Available via API after creating:**
 ```bash
 curl http://localhost:11434/api/chat -d '{
@@ -69,12 +66,6 @@ curl http://localhost:11434/api/chat -d '{
 5. Set parameters from `config.json` → inference section
 6. Chat — THAR.0X is now the active persona
-**Best models to use in LM Studio:**
-- `Qwen2.5-14B-Instruct-Q5_K_M.gguf` — best balance
-- `Qwen2.5-32B-Instruct-Q4_K_M.gguf` — highest quality
-- `Llama-3.2-3B-Instruct-Q8_0.gguf` — fastest
-- `Mistral-7B-Instruct-v0.3-Q5_K_M.gguf` — creative tasks
 ---
 ### 3. llama.cpp
@@ -203,25 +194,6 @@ def chat(message):
 print(chat("Who are you?"))
 ```
----
-## Recommended Base Models
-| Model | Size | Best For | Speed |
-|---|---|---|---|
-| `qwen2.5:32b` | 32B | Highest quality reasoning | Slow |
-| `qwen2.5:14b` | 14B | Best balance | Medium |
-| `llama3.2` | 3B | Fast, always available | Fast |
-| `mistral:7b` | 7B | Creative + conversational | Medium |
-| `qwen2.5-coder:14b` | 14B | Code + technical | Medium |
-| `llama3.2:1b` | 1B | Minimal hardware (4GB RAM) | Very fast |
-**Rule of thumb:** Use the largest model your hardware can run at full context (8192 tokens).
-- 8GB RAM → llama3.2 or mistral:7b
-- 16GB RAM → qwen2.5:14b
-- 32GB+ RAM → qwen2.5:32b
 ---
 ## What Makes THAR.0X Different

 # Run it
 ollama run THAR.0X
 ```
 **Available via API after creating:**
 ```bash
 curl http://localhost:11434/api/chat -d '{
 5. Set parameters from `config.json` → inference section
 6. Chat — THAR.0X is now the active persona
 ---
 ### 3. llama.cpp
 print(chat("Who are you?"))
 ```
 ---
 ## What Makes THAR.0X Different

config.json CHANGED Viewed

@@ -24,15 +24,6 @@
     "eos_token": "<|end_of_text|>"
   },
-  "recommended_base_models": [
-    { "model": "qwen2.5:32b",        "reason": "Best reasoning, most powerful" },
-    { "model": "qwen2.5:14b",        "reason": "Best speed/quality balance" },
-    { "model": "llama3.2",           "reason": "Default, always available" },
-    { "model": "mistral",            "reason": "Rich language generation" },
-    { "model": "qwen2.5-coder:14b",  "reason": "Technical and coding tasks" },
-    { "model": "llama3.2:1b",        "reason": "Minimal hardware" }
-  ],
   "lm_studio": {
     "preset": "custom",
     "notes": "Paste contents of system_prompt.txt into the System Prompt field in LM Studio. Use the inference parameters above in the model settings."

     "eos_token": "<|end_of_text|>"
   },
   "lm_studio": {
     "preset": "custom",
     "notes": "Paste contents of system_prompt.txt into the System Prompt field in LM Studio. Use the inference parameters above in the model settings."