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

Libraries

How to use psxog/SARG with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit")
model = PeftModel.from_pretrained(base_model, "psxog/SARG")

Transformers

How to use psxog/SARG with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="psxog/SARG")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("psxog/SARG", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use psxog/SARG 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 psxog/SARG:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf psxog/SARG:Q4_K_M

Install from WinGet (Windows)

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

Use Docker

docker model run hf.co/psxog/SARG:Q4_K_M

LM Studio
Jan

vLLM

How to use psxog/SARG with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "psxog/SARG"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "psxog/SARG",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/psxog/SARG:Q4_K_M

SGLang

How to use psxog/SARG with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "psxog/SARG" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "psxog/SARG",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "psxog/SARG" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "psxog/SARG",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use psxog/SARG with Ollama:
```
ollama run hf.co/psxog/SARG:Q4_K_M
```
Unsloth Desktop

How to use psxog/SARG with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf psxog/SARG: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": "psxog/SARG:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use psxog/SARG with Docker Model Runner:
```
docker model run hf.co/psxog/SARG:Q4_K_M
```

Lemonade

How to use psxog/SARG with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull psxog/SARG:Q4_K_M

Run and chat with the model

lemonade run user.SARG-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use psxog/SARG with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf psxog/SARG: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 psxog/SARG:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use psxog/SARG with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf psxog/SARG: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 "psxog/SARG: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"

psxog commited on 9 days ago

Commit

4966ecf

verified ·

1 Parent(s): 6ee80c7

Upload Modelfile

Browse files

Files changed (1) hide show

Modelfile +30 -0

Modelfile ADDED Viewed

	@@ -0,0 +1,30 @@

+FROM ./Meta-Llama-3.1-8B-Instruct.Q4_K_M.gguf
+PARAMETER temperature 0.2
+PARAMETER top_p 0.9
+PARAMETER stop "<|im_start|>"
+PARAMETER stop "<|im_end|>"
+TEMPLATE """<|im_start|>system
+{{ .System }}<|im_end|>
+<|im_start|>user
+{{ .Prompt }}<|im_end|>
+<|im_start|>assistant
+"""
+SYSTEM """You are SahayakAI, a teaching assistant for CBSE schools in rural and semi-rural North Bengal, West Bengal. Answer in English.
+Use ONLY the facts given in the CONTEXT below. Do not invent wages, prices, yields, rainfall figures, names or syllabus points. Respect the stated classroom constraints.
+CONTEXT
+board: CBSE | grade: 12 | subject: Economics | medium: English
+state: West Bengal | region: North Bengal | district: Uttar Dinajpur
+terrain: Plains (Old Alluvial Flat) | setting: rural | classroom: single_grade
+infra: no_projector, shared_textbook
+livelihood: maize, jute, mustard, paddy
+local_facts: mgnrega_wage_INR_per_day=250.0, annual_rainfall_mm_per_year=1650.0, electricity_hours_hours_per_day=15.0, household_size_persons=4.5, currency=INR
+local_examples: Rice, Kuliks fish, Asian Openbill Stork (in sanctuary), Pond heron, kulik stork sanctuary
+season: Jute retting season"""