Instructions to use siacus/llama-2-7b-dv with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use siacus/llama-2-7b-dv with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="siacus/llama-2-7b-dv",
	filename="llama-2-7b-dv-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 siacus/llama-2-7b-dv 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 siacus/llama-2-7b-dv:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf siacus/llama-2-7b-dv:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf siacus/llama-2-7b-dv:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf siacus/llama-2-7b-dv: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 siacus/llama-2-7b-dv:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf siacus/llama-2-7b-dv: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 siacus/llama-2-7b-dv:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf siacus/llama-2-7b-dv:Q4_K_M

Use Docker

docker model run hf.co/siacus/llama-2-7b-dv:Q4_K_M

LM Studio
Jan
Ollama
How to use siacus/llama-2-7b-dv with Ollama:
```
ollama run hf.co/siacus/llama-2-7b-dv:Q4_K_M
```

Unsloth Studio

How to use siacus/llama-2-7b-dv 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 siacus/llama-2-7b-dv 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 siacus/llama-2-7b-dv to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for siacus/llama-2-7b-dv to start chatting

Atomic Chat new
Docker Model Runner
How to use siacus/llama-2-7b-dv with Docker Model Runner:
```
docker model run hf.co/siacus/llama-2-7b-dv:Q4_K_M
```

Lemonade

How to use siacus/llama-2-7b-dv with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull siacus/llama-2-7b-dv:Q4_K_M

Run and chat with the model

lemonade run user.llama-2-7b-dv-Q4_K_M

List all available models

lemonade list

The data used to train the model are on Huggingface under siacus/dv_subject

The small-dv version of the fine-tuned model works on a training-set of 5,000 randomly sampled data.

The large version works on the whole 76.1K training records.

The test set is of size 32.6K rows.

F16 version from merged weights created with llama.cpp on a CUDA GPU and the 4bit quantized version created on a Mac M2 Ultra Metal architecture. If you want to use the 4bit quantized version on CUDA, please quantize it directly from the F16 version.

For more information about this model refer the main repository for the supplementary material of the manuscript Rethinking Scale: The Efficacy of Fine-Tuned Open-Source LLMs in Large-Scale Reproducible Social Science Research.

Downloads last month: 3

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

4-bit

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for siacus/llama-2-7b-dv

Base model

meta-llama/Llama-2-7b-chat-hf

Quantized

(101)

this model

Dataset used to train siacus/llama-2-7b-dv

Paper for siacus/llama-2-7b-dv

Rethinking Scale: The Efficacy of Fine-Tuned Open-Source LLMs in Large-Scale Reproducible Social Science Research

Paper • 2411.00890 • Published Oct 31, 2024