Instructions to use YanaS/llama2-bg-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use YanaS/llama2-bg-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="YanaS/llama2-bg-GGUF")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("YanaS/llama2-bg-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use YanaS/llama2-bg-GGUF 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 YanaS/llama2-bg-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf YanaS/llama2-bg-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf YanaS/llama2-bg-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf YanaS/llama2-bg-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 YanaS/llama2-bg-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf YanaS/llama2-bg-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 YanaS/llama2-bg-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf YanaS/llama2-bg-GGUF:Q4_K_M

Use Docker

docker model run hf.co/YanaS/llama2-bg-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use YanaS/llama2-bg-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "YanaS/llama2-bg-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "YanaS/llama2-bg-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/YanaS/llama2-bg-GGUF:Q4_K_M

SGLang

How to use YanaS/llama2-bg-GGUF 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 "YanaS/llama2-bg-GGUF" \
    --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": "YanaS/llama2-bg-GGUF",
		"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 "YanaS/llama2-bg-GGUF" \
        --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": "YanaS/llama2-bg-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use YanaS/llama2-bg-GGUF with Ollama:
```
ollama run hf.co/YanaS/llama2-bg-GGUF:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use YanaS/llama2-bg-GGUF with Docker Model Runner:
```
docker model run hf.co/YanaS/llama2-bg-GGUF:Q4_K_M
```

Lemonade

How to use YanaS/llama2-bg-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull YanaS/llama2-bg-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.llama2-bg-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

llama2-bg-GGUF / README.md

YanaS

Update README.md

a7e3134 about 3 years ago

preview code

Raw History Blame Contribute Delete

2.75 kB

	---
	language:
	- bg
	license: mit
	library_name: transformers
	pipeline_tag: text-generation
	tags:
	- text-generation-inference
	---

	Description
	GGUF Format model files for [this project](https://huggingface.co/bogdan1/llama2-bg).

	From [@bogdan1](https://huggingface.co/bogdan1): Llama-2-7b-base fine-tuned on the Chitanka dataset and a dataset made of scraped news comments
	dating mostly from 2022/2023. Big Thank you :)


	About GGUF

	Introduction:

	GGUF was introduced by the llama.cpp team on August 21st, 2023, as a replacement for GGML, which is no longer supported.
	GGUF is a successor file format to GGML, GGMF, and GGJT. It is designed to provide a comprehensive solution for model loading,
	ensuring unambiguous data representation while offering extensibility to accommodate future enhancements. GGUF eliminates the need for disruptive changes,
	introduces support for various non-llama models such as falcon, rwkv, and bloom, and simplifies configuration settings by automating prompt format adjustments.

	Key Features:

	1. No More Breaking Changes: GGUF is engineered to prevent compatibility issues with older models, ensuring a seamless transition from previous file formats
	like GGML, GGMF, and GGJT.

	3. Support for Non-Llama Models: GGUF extends its compatibility to a wide range of models beyond llamas, including falcon, rwkv, bloom, and more.

	4. Streamlined Configuration: Say goodbye to complex settings like rope-freq-base, rope-freq-scale, gqa, and rms-norm-eps. GGUF simplifies the
	configuration process, making it more user-friendly.

	6. Automatic Prompt Format: GGUF introduces the ability to automatically set prompt formats, reducing the need for manual adjustments.

	7. Extensibility: GGUF is designed to accommodate future updates and enhancements, ensuring long-term compatibility and adaptability.

	8. Enhanced Tokenization: GGUF features improved tokenization code, including support for special tokens, which enhances overall performance,
	especially for models using new special tokens and custom prompt templates.

	Supported Clients and Libraries:

	GGUF is supported by a variety of clients and libraries, making it accessible and versatile for different use cases:

	1. [llama.cpp](https://github.com/ggerganov/llama.cpp).
	2. [text-generation-webui](https://github.com/oobabooga/text-generation-webui)
	3. [KoboldCpp](https://github.com/LostRuins/koboldcpp)
	4. [LM Studio](https://lmstudio.ai/)
	5. [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui)
	6. [ctransformers](https://github.com/marella/ctransformers)
	7. [llama-cpp-python](https://github.com/abetlen/llama-cpp-python)
	8. [candle](https://github.com/huggingface/candle)