Instructions to use backyardai/Esper-70B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use backyardai/Esper-70B-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="backyardai/Esper-70B-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("backyardai/Esper-70B-GGUF", dtype="auto")

llama-cpp-python

How to use backyardai/Esper-70B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="backyardai/Esper-70B-GGUF",
	filename="Esper-70b.F16-split-00001-of-00003.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use backyardai/Esper-70B-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf backyardai/Esper-70B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf backyardai/Esper-70B-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 backyardai/Esper-70B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf backyardai/Esper-70B-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 backyardai/Esper-70B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf backyardai/Esper-70B-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 backyardai/Esper-70B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf backyardai/Esper-70B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/backyardai/Esper-70B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use backyardai/Esper-70B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "backyardai/Esper-70B-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "backyardai/Esper-70B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/backyardai/Esper-70B-GGUF:Q4_K_M

SGLang

How to use backyardai/Esper-70B-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 "backyardai/Esper-70B-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "backyardai/Esper-70B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "backyardai/Esper-70B-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "backyardai/Esper-70B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use backyardai/Esper-70B-GGUF with Ollama:
```
ollama run hf.co/backyardai/Esper-70B-GGUF:Q4_K_M
```

Unsloth Studio new

How to use backyardai/Esper-70B-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 backyardai/Esper-70B-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 backyardai/Esper-70B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for backyardai/Esper-70B-GGUF to start chatting

Docker Model Runner
How to use backyardai/Esper-70B-GGUF with Docker Model Runner:
```
docker model run hf.co/backyardai/Esper-70B-GGUF:Q4_K_M
```

Lemonade

How to use backyardai/Esper-70B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull backyardai/Esper-70B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Esper-70B-GGUF-Q4_K_M

List all available models

lemonade list

The official library of GGUF format models for use in the local AI chat app, Backyard AI.

Download Backyard AI here to get started.

Request Additional models at r/LLM_Quants.

Esper 70b

Creator: ValiantLabs
Original: Esper 70b
Date Created: 2024-03-12
Trained Context: 4096 tokens
Description: Esper 70b is a CodeLlama-based assistant with a DevOps focus, specializing in scripted language code, Terraform files, Dockerfiles, YAML, and more. Not recommended for roleplay.

What is a GGUF?

GGUF is a large language model (LLM) format that can be split between CPU and GPU. GGUFs are compatible with applications based on llama.cpp, such as Backyard AI. Where other model formats require higher end GPUs with ample VRAM, GGUFs can be efficiently run on a wider variety of hardware. GGUF models are quantized to reduce resource usage, with a tradeoff of reduced coherence at lower quantizations. Quantization reduces the precision of the model weights by changing the number of bits used for each weight.

Backyard AI

Free, local AI chat application.
One-click installation on Mac and PC.
Automatically use GPU for maximum speed.
Built-in model manager.
High-quality character hub.
Zero-config desktop-to-mobile tethering. Backyard AI makes it easy to start chatting with AI using your own characters or one of the many found in the built-in character hub. The model manager helps you find the latest and greatest models without worrying about whether it's the correct format. Backyard AI supports advanced features such as lorebooks, author's note, text formatting, custom context size, sampler settings, grammars, local TTS, cloud inference, and tethering, all implemented in a way that is straightforward and reliable. Join us on Discord

Downloads last month: 1,262

GGUF

Model size

69B params

Architecture

llama

Hardware compatibility

1-bit

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for backyardai/Esper-70B-GGUF

Base model

ValiantLabs/CodeLlama-70B-Esper

Quantized

(4)

this model