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

Libraries

How to use modularai/llama-2 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="modularai/llama-2",
	filename="llama-2-7b-q4_0.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use modularai/llama-2 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf modularai/llama-2:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf modularai/llama-2:Q4_K_M

Install from WinGet (Windows)

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

Use Docker

docker model run hf.co/modularai/llama-2:Q4_K_M

LM Studio
Jan

vLLM

How to use modularai/llama-2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "modularai/llama-2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "modularai/llama-2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/modularai/llama-2:Q4_K_M

Ollama
How to use modularai/llama-2 with Ollama:
```
ollama run hf.co/modularai/llama-2:Q4_K_M
```

Unsloth Studio new

How to use modularai/llama-2 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 modularai/llama-2 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 modularai/llama-2 to start chatting

Using HuggingFace Spaces for Unsloth

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

Docker Model Runner
How to use modularai/llama-2 with Docker Model Runner:
```
docker model run hf.co/modularai/llama-2:Q4_K_M
```

Lemonade

How to use modularai/llama-2 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull modularai/llama-2:Q4_K_M

Run and chat with the model

lemonade run user.llama-2-Q4_K_M

List all available models

lemonade list

jackos commited on Sep 4, 2024

Commit

a59b22d

unverified ·

1 Parent(s): b3f7055

Standardize naming

Browse files

Files changed (4) hide show

README.md +2 -1
llama-2-7b.Q4_0.gguf → llama-2-7b-q4_0.gguf +0 -0
llama-2-7b.Q4_K_M.gguf → llama-2-7b-q4_k_m.gguf +0 -0
llama-2-7b.Q6_K.gguf → llama-2-7b-q6_k.gguf +0 -0

README.md CHANGED Viewed

@@ -21,9 +21,10 @@ quantized_by: TheBloke
 ---
 # Llama 2 7B - GGUF
 - Model creator: [Meta](https://huggingface.co/meta-llama)
 - Original model: [Llama 2 7B](https://huggingface.co/meta-llama/Llama-2-7b-hf)
-- GGUF models Quantized by: [TheBloke](https://huggingface.co/TheBloke) at [TheBloke/Llama-2-7B-GGUF](https://huggingface.co/TheBloke)
 - `stories15M.bin` and `tokenizer.bin` created by [Andrej Karparthy](https://github.com/karpathy) at [karparthy/llama.c](https://github.com/karpathy/llama2.c) and [karparthy/tinyllama](https://huggingface.co/karpathy/tinyllama) under license:
 ```

 ---
 # Llama 2 7B - GGUF
 - Model creator: [Meta](https://huggingface.co/meta-llama)
 - Original model: [Llama 2 7B](https://huggingface.co/meta-llama/Llama-2-7b-hf)
+- GGUF models quantized by: [TheBloke](https://huggingface.co/TheBloke) at [TheBloke/Llama-2-7B-GGUF](https://huggingface.co/TheBloke/Llama-2-7B-GGUF)
 - `stories15M.bin` and `tokenizer.bin` created by [Andrej Karparthy](https://github.com/karpathy) at [karparthy/llama.c](https://github.com/karpathy/llama2.c) and [karparthy/tinyllama](https://huggingface.co/karpathy/tinyllama) under license:
 ```

llama-2-7b.Q4_0.gguf → llama-2-7b-q4_0.gguf RENAMED Viewed

File without changes

llama-2-7b.Q4_K_M.gguf → llama-2-7b-q4_k_m.gguf RENAMED Viewed

File without changes

llama-2-7b.Q6_K.gguf → llama-2-7b-q6_k.gguf RENAMED Viewed

File without changes