Instructions to use ramgovindv/health_function_call_llama3.2_3b_gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use ramgovindv/health_function_call_llama3.2_3b_gguf with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="ramgovindv/health_function_call_llama3.2_3b_gguf", filename="Llama-3.2-3B-Instruct.Q4_K_M.gguf", )
llm.create_chat_completion( messages = "No input example has been defined for this model task." )
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use ramgovindv/health_function_call_llama3.2_3b_gguf with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf ramgovindv/health_function_call_llama3.2_3b_gguf:Q4_K_M # Run inference directly in the terminal: llama-cli -hf ramgovindv/health_function_call_llama3.2_3b_gguf:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf ramgovindv/health_function_call_llama3.2_3b_gguf:Q4_K_M # Run inference directly in the terminal: llama-cli -hf ramgovindv/health_function_call_llama3.2_3b_gguf: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 ramgovindv/health_function_call_llama3.2_3b_gguf:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf ramgovindv/health_function_call_llama3.2_3b_gguf: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 ramgovindv/health_function_call_llama3.2_3b_gguf:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf ramgovindv/health_function_call_llama3.2_3b_gguf:Q4_K_M
Use Docker
docker model run hf.co/ramgovindv/health_function_call_llama3.2_3b_gguf:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use ramgovindv/health_function_call_llama3.2_3b_gguf with Ollama:
ollama run hf.co/ramgovindv/health_function_call_llama3.2_3b_gguf:Q4_K_M
- Unsloth Studio
How to use ramgovindv/health_function_call_llama3.2_3b_gguf 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 ramgovindv/health_function_call_llama3.2_3b_gguf 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 ramgovindv/health_function_call_llama3.2_3b_gguf to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for ramgovindv/health_function_call_llama3.2_3b_gguf to start chatting
- Pi
How to use ramgovindv/health_function_call_llama3.2_3b_gguf with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama-server -hf ramgovindv/health_function_call_llama3.2_3b_gguf: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": "ramgovindv/health_function_call_llama3.2_3b_gguf:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use ramgovindv/health_function_call_llama3.2_3b_gguf with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama-server -hf ramgovindv/health_function_call_llama3.2_3b_gguf: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 ramgovindv/health_function_call_llama3.2_3b_gguf:Q4_K_M
Run Hermes
hermes
- Docker Model Runner
How to use ramgovindv/health_function_call_llama3.2_3b_gguf with Docker Model Runner:
docker model run hf.co/ramgovindv/health_function_call_llama3.2_3b_gguf:Q4_K_M
- Lemonade
How to use ramgovindv/health_function_call_llama3.2_3b_gguf with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull ramgovindv/health_function_call_llama3.2_3b_gguf:Q4_K_M
Run and chat with the model
lemonade run user.health_function_call_llama3.2_3b_gguf-Q4_K_M
List all available models
lemonade list
Create cli.py
Browse files- health_function_lm/cli.py +70 -0
health_function_lm/cli.py
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""
|
| 2 |
+
Command-line interface for health-function-lm.
|
| 3 |
+
|
| 4 |
+
Usage
|
| 5 |
+
-----
|
| 6 |
+
health-fn "Log my blood pressure as 120/80"
|
| 7 |
+
health-fn --pretty "What is my resting heart rate?"
|
| 8 |
+
echo "Log weight 70kg" | health-fn
|
| 9 |
+
"""
|
| 10 |
+
|
| 11 |
+
import argparse
|
| 12 |
+
import json
|
| 13 |
+
import sys
|
| 14 |
+
|
| 15 |
+
from .model import HealthFunctionLM
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
def main():
|
| 19 |
+
parser = argparse.ArgumentParser(
|
| 20 |
+
prog="health-fn",
|
| 21 |
+
description="Run a health query through the function-calling model.",
|
| 22 |
+
)
|
| 23 |
+
parser.add_argument(
|
| 24 |
+
"query",
|
| 25 |
+
nargs="?",
|
| 26 |
+
help="Natural-language health query. Reads from stdin if omitted.",
|
| 27 |
+
)
|
| 28 |
+
parser.add_argument(
|
| 29 |
+
"--pretty",
|
| 30 |
+
action="store_true",
|
| 31 |
+
default=True,
|
| 32 |
+
help="Pretty-print JSON output (default: on).",
|
| 33 |
+
)
|
| 34 |
+
parser.add_argument(
|
| 35 |
+
"--repo-id",
|
| 36 |
+
default="ramgovindv/health_function_call_llama3.2_3b_gguf",
|
| 37 |
+
help="Hugging Face repo ID.",
|
| 38 |
+
)
|
| 39 |
+
parser.add_argument(
|
| 40 |
+
"--filename",
|
| 41 |
+
default="Llama-3.2-3B-Instruct.Q4_K_M.gguf",
|
| 42 |
+
help="GGUF filename inside the repo.",
|
| 43 |
+
)
|
| 44 |
+
parser.add_argument(
|
| 45 |
+
"--n-ctx", type=int, default=2048, help="Context window size."
|
| 46 |
+
)
|
| 47 |
+
parser.add_argument(
|
| 48 |
+
"--n-threads", type=int, default=4, help="Number of CPU threads."
|
| 49 |
+
)
|
| 50 |
+
|
| 51 |
+
args = parser.parse_args()
|
| 52 |
+
|
| 53 |
+
query = args.query or sys.stdin.read().strip()
|
| 54 |
+
if not query:
|
| 55 |
+
parser.error("Provide a query as an argument or via stdin.")
|
| 56 |
+
|
| 57 |
+
lm = HealthFunctionLM(
|
| 58 |
+
repo_id=args.repo_id,
|
| 59 |
+
filename=args.filename,
|
| 60 |
+
n_ctx=args.n_ctx,
|
| 61 |
+
n_threads=args.n_threads,
|
| 62 |
+
)
|
| 63 |
+
|
| 64 |
+
result = lm.query(query)
|
| 65 |
+
indent = 2 if args.pretty else None
|
| 66 |
+
print(json.dumps(result, indent=indent))
|
| 67 |
+
|
| 68 |
+
|
| 69 |
+
if __name__ == "__main__":
|
| 70 |
+
main()
|