Instructions to use tensorblock/MergeBench_Llama-3.1-8B_coding-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tensorblock/MergeBench_Llama-3.1-8B_coding-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("tensorblock/MergeBench_Llama-3.1-8B_coding-GGUF", dtype="auto")

llama-cpp-python

How to use tensorblock/MergeBench_Llama-3.1-8B_coding-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="tensorblock/MergeBench_Llama-3.1-8B_coding-GGUF",
	filename="Llama-3.1-8B_coding-Q2_K.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 tensorblock/MergeBench_Llama-3.1-8B_coding-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf tensorblock/MergeBench_Llama-3.1-8B_coding-GGUF:Q2_K
# Run inference directly in the terminal:
llama-cli -hf tensorblock/MergeBench_Llama-3.1-8B_coding-GGUF:Q2_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf tensorblock/MergeBench_Llama-3.1-8B_coding-GGUF:Q2_K
# Run inference directly in the terminal:
llama-cli -hf tensorblock/MergeBench_Llama-3.1-8B_coding-GGUF:Q2_K

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 tensorblock/MergeBench_Llama-3.1-8B_coding-GGUF:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf tensorblock/MergeBench_Llama-3.1-8B_coding-GGUF:Q2_K

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 tensorblock/MergeBench_Llama-3.1-8B_coding-GGUF:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tensorblock/MergeBench_Llama-3.1-8B_coding-GGUF:Q2_K

Use Docker

docker model run hf.co/tensorblock/MergeBench_Llama-3.1-8B_coding-GGUF:Q2_K

LM Studio
Jan
Ollama
How to use tensorblock/MergeBench_Llama-3.1-8B_coding-GGUF with Ollama:
```
ollama run hf.co/tensorblock/MergeBench_Llama-3.1-8B_coding-GGUF:Q2_K
```

Unsloth Studio new

How to use tensorblock/MergeBench_Llama-3.1-8B_coding-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 tensorblock/MergeBench_Llama-3.1-8B_coding-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 tensorblock/MergeBench_Llama-3.1-8B_coding-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for tensorblock/MergeBench_Llama-3.1-8B_coding-GGUF to start chatting

Docker Model Runner
How to use tensorblock/MergeBench_Llama-3.1-8B_coding-GGUF with Docker Model Runner:
```
docker model run hf.co/tensorblock/MergeBench_Llama-3.1-8B_coding-GGUF:Q2_K
```

Lemonade

How to use tensorblock/MergeBench_Llama-3.1-8B_coding-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tensorblock/MergeBench_Llama-3.1-8B_coding-GGUF:Q2_K

Run and chat with the model

lemonade run user.MergeBench_Llama-3.1-8B_coding-GGUF-Q2_K

List all available models

lemonade list

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c9605f84150aefa2e13b177f410f4b6ff03c4b61abb8cf8b739cddf0b0608378
-size 4321956384

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:00bf85016e6df0142a32a08396d72253bd49c8cf79d7cf5b5180d74ecf56e48c
-size 3664499232

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:361c3af61a00efbf3a49ce91f3890fc62342c34081b7b939a9f0760bad16c551
-size 4661211680

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:89bd88f4a08d717c86b53a0810d263ce3f4e6bc1964fd028e2087c52e7d87848
-size 4920734240

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3093d1bb01860fb65b70c966e1df5e1129fdbab3020d8611a3cbffe0b1044015
-size 4692668960

tensorblock
/

MergeBench_Llama-3.1-8B_coding-GGUF

Keep Q2_K/Q3_K_M gguf only