Instructions to use harshalmore31/naval_llama with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use harshalmore31/naval_llama with Transformers:

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

pipe = pipeline("text-generation", model="harshalmore31/naval_llama")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("harshalmore31/naval_llama", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use harshalmore31/naval_llama 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 harshalmore31/naval_llama:Q8_0
# Run inference directly in the terminal:
llama cli -hf harshalmore31/naval_llama:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf harshalmore31/naval_llama:Q8_0
# Run inference directly in the terminal:
llama cli -hf harshalmore31/naval_llama: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 harshalmore31/naval_llama:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf harshalmore31/naval_llama: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 harshalmore31/naval_llama:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf harshalmore31/naval_llama:Q8_0

Use Docker

docker model run hf.co/harshalmore31/naval_llama:Q8_0

LM Studio
Jan

vLLM

How to use harshalmore31/naval_llama with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "harshalmore31/naval_llama"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "harshalmore31/naval_llama",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/harshalmore31/naval_llama:Q8_0

SGLang

How to use harshalmore31/naval_llama 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 "harshalmore31/naval_llama" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "harshalmore31/naval_llama",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "harshalmore31/naval_llama" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "harshalmore31/naval_llama",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use harshalmore31/naval_llama with Ollama:
```
ollama run hf.co/harshalmore31/naval_llama:Q8_0
```

Unsloth Studio

How to use harshalmore31/naval_llama 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 harshalmore31/naval_llama 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 harshalmore31/naval_llama to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for harshalmore31/naval_llama to start chatting

Atomic Chat new
Docker Model Runner
How to use harshalmore31/naval_llama with Docker Model Runner:
```
docker model run hf.co/harshalmore31/naval_llama:Q8_0
```

Lemonade

How to use harshalmore31/naval_llama with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull harshalmore31/naval_llama:Q8_0

Run and chat with the model

lemonade run user.naval_llama-Q8_0

List all available models

lemonade list

Uploaded model

Developed by: harshalmore31
License: apache-2.0
Finetuned from model : unsloth/meta-llama-3.1-8b-unsloth-bnb-4bit

Overview

Naval Llama is a fine-tuned version of the Meta Llama 3.1 8B model, optimized for fast and efficient text generation. By leveraging advanced LoRA techniques with Unsloth and HuggingFace's TRL library, this model has been trained 2x faster while preserving the core wisdom of Eric Jorgenson’s The Almanack of Naval Ravikant. The model is available in GGUF format, making it ideal for both cloud-based and local text-generation inference.

Features

Fast Fine-Tuning: Achieved 2x faster training using Unsloth’s efficient LoRA implementation.
Efficient Quantization: Uses 4-bit quantization to minimize VRAM requirements while maintaining performance.
GGUF Format: The model is converted to GGUF format for optimized deployment with tools like llama.cpp.
Versatile Use Cases: Suitable for generating insightful responses, summarizing content, and creative text generation.
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.

Downloads last month: 23

GGUF

Model size

8B params

Architecture

llama

Hardware compatibility

8-bit

harshalmore31
/

naval_llama

Uploaded model

Overview

Dataset used to train harshalmore31/naval_llama