Instructions to use heatball/Einstein-v4-7B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use heatball/Einstein-v4-7B-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 heatball/Einstein-v4-7B-GGUF:Q4_K_S
# Run inference directly in the terminal:
llama cli -hf heatball/Einstein-v4-7B-GGUF:Q4_K_S

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf heatball/Einstein-v4-7B-GGUF:Q4_K_S
# Run inference directly in the terminal:
llama cli -hf heatball/Einstein-v4-7B-GGUF:Q4_K_S

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 heatball/Einstein-v4-7B-GGUF:Q4_K_S
# Run inference directly in the terminal:
./llama-cli -hf heatball/Einstein-v4-7B-GGUF:Q4_K_S

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 heatball/Einstein-v4-7B-GGUF:Q4_K_S
# Run inference directly in the terminal:
./build/bin/llama-cli -hf heatball/Einstein-v4-7B-GGUF:Q4_K_S

Use Docker

docker model run hf.co/heatball/Einstein-v4-7B-GGUF:Q4_K_S

LM Studio
Jan
Ollama
How to use heatball/Einstein-v4-7B-GGUF with Ollama:
```
ollama run hf.co/heatball/Einstein-v4-7B-GGUF:Q4_K_S
```

Unsloth Studio

How to use heatball/Einstein-v4-7B-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 heatball/Einstein-v4-7B-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 heatball/Einstein-v4-7B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for heatball/Einstein-v4-7B-GGUF to start chatting

Docker Model Runner
How to use heatball/Einstein-v4-7B-GGUF with Docker Model Runner:
```
docker model run hf.co/heatball/Einstein-v4-7B-GGUF:Q4_K_S
```

Lemonade

How to use heatball/Einstein-v4-7B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull heatball/Einstein-v4-7B-GGUF:Q4_K_S

Run and chat with the model

lemonade run user.Einstein-v4-7B-GGUF-Q4_K_S

List all available models

lemonade list

Atomic Chat

This repository contains the GGUF quants for Weyaxi's Einstein-v4-7B

Downloads last month: 7

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

4-bit

6-bit

Inference Providers NEW

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

Model tree for heatball/Einstein-v4-7B-GGUF

Base model

mistralai/Mistral-7B-v0.1

Quantized

(193)

this model

Datasets used to train heatball/Einstein-v4-7B-GGUF

Evaluation results

normalized accuracy on AI2 Reasoning Challenge (25-Shot)
test set Open LLM Leaderboard

64.680
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

83.750
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

62.310
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

55.150
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

76.240
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

57.620