Instructions to use Kernel/ganjar_4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Kernel/ganjar_4 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Kernel/ganjar_4",
	filename="ganjar_lite3.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 Kernel/ganjar_4 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Kernel/ganjar_4
# Run inference directly in the terminal:
llama-cli -hf Kernel/ganjar_4

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Kernel/ganjar_4
# Run inference directly in the terminal:
llama-cli -hf Kernel/ganjar_4

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 Kernel/ganjar_4
# Run inference directly in the terminal:
./llama-cli -hf Kernel/ganjar_4

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 Kernel/ganjar_4
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Kernel/ganjar_4

Use Docker

docker model run hf.co/Kernel/ganjar_4

LM Studio
Jan
Ollama
How to use Kernel/ganjar_4 with Ollama:
```
ollama run hf.co/Kernel/ganjar_4
```

Unsloth Studio new

How to use Kernel/ganjar_4 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 Kernel/ganjar_4 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 Kernel/ganjar_4 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Kernel/ganjar_4 to start chatting

Docker Model Runner
How to use Kernel/ganjar_4 with Docker Model Runner:
```
docker model run hf.co/Kernel/ganjar_4
```

Lemonade

How to use Kernel/ganjar_4 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Kernel/ganjar_4

Run and chat with the model

lemonade run user.ganjar_4-{{QUANT_TAG}}

List all available models

lemonade list

Kernel commited on Dec 15, 2023

Commit

8dbb4f4

1 Parent(s): 5668cb1

Upload mix_5.gguf with huggingface_hub

Browse files

Files changed (2) hide show

.gitattributes +1 -0
mix_5.gguf +3 -0

.gitattributes CHANGED Viewed

@@ -52,3 +52,4 @@ ganjar_lite3.gguf filter=lfs diff=lfs merge=lfs -text
 neyra_7b.gguf filter=lfs diff=lfs merge=lfs -text
 mix.gguf filter=lfs diff=lfs merge=lfs -text
 neyra.gguf filter=lfs diff=lfs merge=lfs -text

 neyra_7b.gguf filter=lfs diff=lfs merge=lfs -text
 mix.gguf filter=lfs diff=lfs merge=lfs -text
 neyra.gguf filter=lfs diff=lfs merge=lfs -text
+mix_5.gguf filter=lfs diff=lfs merge=lfs -text

mix_5.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:b2900be33b13ed8780bd68584ea98fe577d1cf3b3187019fe82b0371d2c0616e
+size 32229279040