Instructions to use mradermacher/CHEETAH-350M-Merged-FP16-i1-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mradermacher/CHEETAH-350M-Merged-FP16-i1-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="mradermacher/CHEETAH-350M-Merged-FP16-i1-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("mradermacher/CHEETAH-350M-Merged-FP16-i1-GGUF", dtype="auto")

llama-cpp-python

How to use mradermacher/CHEETAH-350M-Merged-FP16-i1-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="mradermacher/CHEETAH-350M-Merged-FP16-i1-GGUF",
	filename="CHEETAH-350M-Merged-FP16.i1-IQ1_M.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use mradermacher/CHEETAH-350M-Merged-FP16-i1-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 mradermacher/CHEETAH-350M-Merged-FP16-i1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf mradermacher/CHEETAH-350M-Merged-FP16-i1-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 mradermacher/CHEETAH-350M-Merged-FP16-i1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf mradermacher/CHEETAH-350M-Merged-FP16-i1-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 mradermacher/CHEETAH-350M-Merged-FP16-i1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf mradermacher/CHEETAH-350M-Merged-FP16-i1-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 mradermacher/CHEETAH-350M-Merged-FP16-i1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mradermacher/CHEETAH-350M-Merged-FP16-i1-GGUF:Q4_K_M

Use Docker

docker model run hf.co/mradermacher/CHEETAH-350M-Merged-FP16-i1-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use mradermacher/CHEETAH-350M-Merged-FP16-i1-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mradermacher/CHEETAH-350M-Merged-FP16-i1-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": "mradermacher/CHEETAH-350M-Merged-FP16-i1-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mradermacher/CHEETAH-350M-Merged-FP16-i1-GGUF:Q4_K_M

SGLang

How to use mradermacher/CHEETAH-350M-Merged-FP16-i1-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 "mradermacher/CHEETAH-350M-Merged-FP16-i1-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": "mradermacher/CHEETAH-350M-Merged-FP16-i1-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 "mradermacher/CHEETAH-350M-Merged-FP16-i1-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": "mradermacher/CHEETAH-350M-Merged-FP16-i1-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use mradermacher/CHEETAH-350M-Merged-FP16-i1-GGUF with Ollama:
```
ollama run hf.co/mradermacher/CHEETAH-350M-Merged-FP16-i1-GGUF:Q4_K_M
```

Unsloth Studio

How to use mradermacher/CHEETAH-350M-Merged-FP16-i1-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 mradermacher/CHEETAH-350M-Merged-FP16-i1-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 mradermacher/CHEETAH-350M-Merged-FP16-i1-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for mradermacher/CHEETAH-350M-Merged-FP16-i1-GGUF to start chatting

How to use mradermacher/CHEETAH-350M-Merged-FP16-i1-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mradermacher/CHEETAH-350M-Merged-FP16-i1-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "mradermacher/CHEETAH-350M-Merged-FP16-i1-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use mradermacher/CHEETAH-350M-Merged-FP16-i1-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mradermacher/CHEETAH-350M-Merged-FP16-i1-GGUF:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default mradermacher/CHEETAH-350M-Merged-FP16-i1-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use mradermacher/CHEETAH-350M-Merged-FP16-i1-GGUF with Docker Model Runner:
```
docker model run hf.co/mradermacher/CHEETAH-350M-Merged-FP16-i1-GGUF:Q4_K_M
```

Lemonade

How to use mradermacher/CHEETAH-350M-Merged-FP16-i1-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mradermacher/CHEETAH-350M-Merged-FP16-i1-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.CHEETAH-350M-Merged-FP16-i1-GGUF-Q4_K_M

List all available models

lemonade list

mradermacher commited on about 1 month ago

Commit

f5c7be6

verified ·

1 Parent(s): 6cb330a

uploaded from nico1

Browse files

Files changed (25) hide show

.gitattributes +24 -0
CHEETAH-350M-Merged-FP16.i1-IQ1_M.gguf +3 -0
CHEETAH-350M-Merged-FP16.i1-IQ1_S.gguf +3 -0
CHEETAH-350M-Merged-FP16.i1-IQ2_M.gguf +3 -0
CHEETAH-350M-Merged-FP16.i1-IQ2_S.gguf +3 -0
CHEETAH-350M-Merged-FP16.i1-IQ2_XS.gguf +3 -0
CHEETAH-350M-Merged-FP16.i1-IQ2_XXS.gguf +3 -0
CHEETAH-350M-Merged-FP16.i1-IQ3_M.gguf +3 -0
CHEETAH-350M-Merged-FP16.i1-IQ3_S.gguf +3 -0
CHEETAH-350M-Merged-FP16.i1-IQ3_XS.gguf +3 -0
CHEETAH-350M-Merged-FP16.i1-IQ3_XXS.gguf +3 -0
CHEETAH-350M-Merged-FP16.i1-IQ4_NL.gguf +3 -0
CHEETAH-350M-Merged-FP16.i1-IQ4_XS.gguf +3 -0
CHEETAH-350M-Merged-FP16.i1-Q2_K.gguf +3 -0
CHEETAH-350M-Merged-FP16.i1-Q2_K_S.gguf +3 -0
CHEETAH-350M-Merged-FP16.i1-Q3_K_L.gguf +3 -0
CHEETAH-350M-Merged-FP16.i1-Q3_K_M.gguf +3 -0
CHEETAH-350M-Merged-FP16.i1-Q3_K_S.gguf +3 -0
CHEETAH-350M-Merged-FP16.i1-Q4_0.gguf +3 -0
CHEETAH-350M-Merged-FP16.i1-Q4_1.gguf +3 -0
CHEETAH-350M-Merged-FP16.i1-Q4_K_M.gguf +3 -0
CHEETAH-350M-Merged-FP16.i1-Q4_K_S.gguf +3 -0
CHEETAH-350M-Merged-FP16.i1-Q5_K_M.gguf +3 -0
CHEETAH-350M-Merged-FP16.i1-Q5_K_S.gguf +3 -0
CHEETAH-350M-Merged-FP16.i1-Q6_K.gguf +3 -0

@@ -34,3 +34,27 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 CHEETAH-350M-Merged-FP16.imatrix.gguf filter=lfs diff=lfs merge=lfs -text

 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 CHEETAH-350M-Merged-FP16.imatrix.gguf filter=lfs diff=lfs merge=lfs -text
+CHEETAH-350M-Merged-FP16.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text
+CHEETAH-350M-Merged-FP16.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text
+CHEETAH-350M-Merged-FP16.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
+CHEETAH-350M-Merged-FP16.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text
+CHEETAH-350M-Merged-FP16.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text
+CHEETAH-350M-Merged-FP16.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text
+CHEETAH-350M-Merged-FP16.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
+CHEETAH-350M-Merged-FP16.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text
+CHEETAH-350M-Merged-FP16.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
+CHEETAH-350M-Merged-FP16.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
+CHEETAH-350M-Merged-FP16.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
+CHEETAH-350M-Merged-FP16.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+CHEETAH-350M-Merged-FP16.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+CHEETAH-350M-Merged-FP16.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+CHEETAH-350M-Merged-FP16.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+CHEETAH-350M-Merged-FP16.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+CHEETAH-350M-Merged-FP16.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+CHEETAH-350M-Merged-FP16.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+CHEETAH-350M-Merged-FP16.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+CHEETAH-350M-Merged-FP16.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+CHEETAH-350M-Merged-FP16.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+CHEETAH-350M-Merged-FP16.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+CHEETAH-350M-Merged-FP16.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+CHEETAH-350M-Merged-FP16.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text

+version https://git-lfs.github.com/spec/v1
+oid sha256:ca71cb1a19cef29779eca814f03d56b7757b473c24ff8bb72234b702618584e5
+size 113255680

+version https://git-lfs.github.com/spec/v1
+oid sha256:4837b6c806372fb5f6775f6574eefdd47fcb23d3bb67468d19535ab410b6e4b4
+size 106964224

+version https://git-lfs.github.com/spec/v1
+oid sha256:e6916f3673d0c20979bb45f2a48ac89bfff14374df9bfb43d8becca3f38d0bcb
+size 142877952

+version https://git-lfs.github.com/spec/v1
+oid sha256:d5106d21691e9a069310b9c49ad804f37e2275177370ced17b63556b1cb7aa23
+size 134489344

+version https://git-lfs.github.com/spec/v1
+oid sha256:a459db8eb75ef42e8b38b766e59ea890b62f23dbefb50c6db6e97912ca9994ca
+size 132326656

+version https://git-lfs.github.com/spec/v1
+oid sha256:3caf8e0841417dfc2f93152344ec8fdc40ce28a0f2e274c250e0577f3f0a0fe5
+size 123741440

+version https://git-lfs.github.com/spec/v1
+oid sha256:94cee135262e133a83b846aec68c9e98d825d2af823f4ae600e5fabb13411791
+size 183657728

+version https://git-lfs.github.com/spec/v1
+oid sha256:2440e9ee2689c26d4cb4412fa98b2c57c50501ce6d75fdc8ef68a22e98e03d0a
+size 181150976

+version https://git-lfs.github.com/spec/v1
+oid sha256:8379cecb55e6019b57345e1a3a8c96607133edfcd35d1750900b7299d4f2672b
+size 175400192

+version https://git-lfs.github.com/spec/v1
+oid sha256:59689a1b1a9d184515d2d05f2e325f26828beb4f322ba2be32369393b9cee97a
+size 158475520

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

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

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

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:cbd4a366d5b3c05146bbd353d392ec4ddecff158fef30b5e9580ff4bc2cabec2
+size 219309312

+version https://git-lfs.github.com/spec/v1
+oid sha256:47b718e79ccbcc1d906458e9e106f6934bb6439d5979b3c060e405b09e38b466
+size 210330880

+version https://git-lfs.github.com/spec/v1
+oid sha256:d38a9eb28fa99e1612d60dd70ac28791c6508f6577e30be4d8e8f3b6ee342c06
+size 160597248

+version https://git-lfs.github.com/spec/v1
+oid sha256:83632862390684961a0ddf4a8286b74463e1feaa52cdd4b30e421ef4956bfade
+size 154182912

+version https://git-lfs.github.com/spec/v1
+oid sha256:1aa9cfaa0bf8cd1bce784f0654e21b144ac7526251508f65faf9d98812ed6367
+size 203048192

+version https://git-lfs.github.com/spec/v1
+oid sha256:b5e89570fcf084747b3761cdb73c51de8a9a1ebde7f10de50f971848a9b21a38
+size 193152256

+version https://git-lfs.github.com/spec/v1
+oid sha256:3a41ce0f7328321fcabf908b64a7cde7b5e022495e09f66ecdc33c4aa09e3bf9
+size 219899136

+version https://git-lfs.github.com/spec/v1
+oid sha256:e7074858e48ccf8279a07e909f24f50e9e55d48093cd8dc2c3d55a696ff2cd0a
+size 237266176

+version https://git-lfs.github.com/spec/v1
+oid sha256:3c6e18a68b19d0d494544f4b13ffcd90f975d00e9e4fddb64527aedf073186a9
+size 229311744

+version https://git-lfs.github.com/spec/v1
+oid sha256:f61e2b37fc4d4de687464c7b5dd3784ad7053accad9332ffdbeb62226dfa6de9
+size 220751104

+version https://git-lfs.github.com/spec/v1
+oid sha256:58f1214b6a4f335e79e788e35f63563aa94dde3f3779050fc7bd119020cd294d
+size 260375808

+version https://git-lfs.github.com/spec/v1
+oid sha256:4e512c8dfa1a7b7188e9997963e4d3099d26c6d11b17f07e18745b4e6b81490c
+size 255223040

+version https://git-lfs.github.com/spec/v1
+oid sha256:8c7a5e275503c889c30c7628302b7e0e7f70cdd88e0138a816bbb6c27669247e
+size 293381376