Instructions to use Sunbird/Sunflower-14B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Sunbird/Sunflower-14B-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="Sunbird/Sunflower-14B-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Sunbird/Sunflower-14B-GGUF", dtype="auto")

llama-cpp-python

How to use Sunbird/Sunflower-14B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Sunbird/Sunflower-14B-GGUF",
	filename="sunflower-14B-f16.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 Sunbird/Sunflower-14B-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Sunbird/Sunflower-14B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Sunbird/Sunflower-14B-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 Sunbird/Sunflower-14B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Sunbird/Sunflower-14B-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 Sunbird/Sunflower-14B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Sunbird/Sunflower-14B-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 Sunbird/Sunflower-14B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Sunbird/Sunflower-14B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Sunbird/Sunflower-14B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use Sunbird/Sunflower-14B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Sunbird/Sunflower-14B-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": "Sunbird/Sunflower-14B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Sunbird/Sunflower-14B-GGUF:Q4_K_M

SGLang

How to use Sunbird/Sunflower-14B-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 "Sunbird/Sunflower-14B-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": "Sunbird/Sunflower-14B-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 "Sunbird/Sunflower-14B-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": "Sunbird/Sunflower-14B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use Sunbird/Sunflower-14B-GGUF with Ollama:
```
ollama run hf.co/Sunbird/Sunflower-14B-GGUF:Q4_K_M
```

Unsloth Studio new

How to use Sunbird/Sunflower-14B-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 Sunbird/Sunflower-14B-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 Sunbird/Sunflower-14B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Sunbird/Sunflower-14B-GGUF to start chatting

Pi new

How to use Sunbird/Sunflower-14B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Sunbird/Sunflower-14B-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": "Sunbird/Sunflower-14B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Sunbird/Sunflower-14B-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Sunbird/Sunflower-14B-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 Sunbird/Sunflower-14B-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use Sunbird/Sunflower-14B-GGUF with Docker Model Runner:
```
docker model run hf.co/Sunbird/Sunflower-14B-GGUF:Q4_K_M
```

Lemonade

How to use Sunbird/Sunflower-14B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Sunbird/Sunflower-14B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Sunflower-14B-GGUF-Q4_K_M

List all available models

lemonade list

patrickcmd commited on Oct 7, 2025

Commit

54680fd

verified ·

1 Parent(s): 6f89a1f

Update README.md

Browse files

Files changed (1) hide show

README.md +15 -15

README.md CHANGED Viewed

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: Sunbird/qwen3-14b-sunflower-merged
 tags:
 - quantized
 - gguf
@@ -22,7 +22,7 @@ GGUF quantized versions of the Sunflower model for Ugandan language translation
 ## Model Details
-- **Base Model**: [Sunbird/qwen3-14b-sunflower-merged](https://huggingface.co/Sunbird/qwen3-14b-sunflower-merged)
 - **Model Size**: 14B parameters
 - **Architecture**: Qwen2.5
 - **Quantization**: K-means quantization with importance matrix
@@ -34,12 +34,12 @@ GGUF quantized versions of the Sunflower model for Ugandan language translation
 | Filename | Quant type | File Size | Description |
 | -------- | ---------- | --------- | ----------- |
-| sunflower-merged-f16.gguf | F16 | 28GB | Original precision |
-| sunflower-q8_0.gguf | Q8_0 | 15GB | Highest quality quantized |
-| sunflower-q6_k.gguf | Q6_K | 12GB | High quality |
-| sunflower-q5_k_m.gguf | Q5_K_M | 9.8GB | Balanced quality/size |
-| sunflower-q5_k_s.gguf | Q5_K_S | 9.6GB | Smaller Q5 variant |
-| sunflower-q4_k_m.gguf | Q4_K_M | 8.4GB | **Recommended for most users** |
 ### Warning: Experimental Quantizations
@@ -47,9 +47,9 @@ The following quantizations achieve extreme compression but may significantly im
 | Filename | Quant type | File Size | Compression | Warning |
 | -------- | ---------- | --------- | ----------- | ------- |
-| sunflower-iq2_xxs.gguf | IQ2_XXS | 4.1GB | 85% smaller | May lose translation accuracy |
-| sunflower-tq1_0.gguf | TQ1_0 | 3.7GB | 87% smaller | Experimental ternary quantization |
-| sunflower-iq1_s.gguf | IQ1_S | 3.4GB | 88% smaller | **Extreme compression, quality heavily impacted** |
 **Note**: The experimental quantizations (IQ1_S, IQ2_XXS, TQ1_0) use advanced compression techniques that may not preserve the specialized knowledge for Ugandan language translation. Test thoroughly before production use.
@@ -65,10 +65,10 @@ The following quantizations achieve extreme compression but may significantly im
 ```bash
 # Download model
-huggingface-cli download Sunbird/Sunflower-14B-GGUF sunflower-q4_k_m.gguf --local-dir .
 # Run inference
-./llama-cli -m sunflower-q4_k_m.gguf -p "Translate to Luganda: Hello, how are you today?"
 ```
 ## Ollama Integration
@@ -208,7 +208,7 @@ curl http://localhost:11434/api/version
 ```python
 from llama_cpp import Llama
-llm = Llama(model_path="sunflower-q4_k_m.gguf")
 result = llm("Translate to Luganda: How are you?")
 print(result['choices'][0]['text'])
 ```
@@ -226,4 +226,4 @@ Quantized using llama.cpp with importance matrix calibration for optimal quality
 ## License
-Apache 2.0

 ---
 license: apache-2.0
+base_model: Sunbird/Sunflower-14B
 tags:
 - quantized
 - gguf
 ## Model Details
+- **Base Model**: [Sunbird/Sunflower-14B](https://huggingface.co/Sunbird/Sunflower-14B)
 - **Model Size**: 14B parameters
 - **Architecture**: Qwen2.5
 - **Quantization**: K-means quantization with importance matrix
 | Filename | Quant type | File Size | Description |
 | -------- | ---------- | --------- | ----------- |
+| sunflower-14B-f16.gguf | F16 | 28GB | Original precision |
+| sunflower-14B-q8_0.gguf | Q8_0 | 15GB | Highest quality quantized |
+| sunflower-14B-q6_k.gguf | Q6_K | 12GB | High quality |
+| sunflower-14B-q5_k_m.gguf | Q5_K_M | 9.8GB | Balanced quality/size |
+| sunflower-14B-q5_k_s.gguf | Q5_K_S | 9.6GB | Smaller Q5 variant |
+| sunflower-14B-q4_k_m.gguf | Q4_K_M | 8.4GB | **Recommended for most users** |
 ### Warning: Experimental Quantizations
 | Filename | Quant type | File Size | Compression | Warning |
 | -------- | ---------- | --------- | ----------- | ------- |
+| sunflower-14B-iq2_xxs.gguf | IQ2_XXS | 4.1GB | 85% smaller | May lose translation accuracy |
+| sunflower-14B-tq1_0.gguf | TQ1_0 | 3.7GB | 87% smaller | Experimental ternary quantization |
+| sunflower-14B-iq1_s.gguf | IQ1_S | 3.4GB | 88% smaller | **Extreme compression, quality heavily impacted** |
 **Note**: The experimental quantizations (IQ1_S, IQ2_XXS, TQ1_0) use advanced compression techniques that may not preserve the specialized knowledge for Ugandan language translation. Test thoroughly before production use.
 ```bash
 # Download model
+huggingface-cli download Sunbird/Sunflower-14B-GGUF sunflower-14B-q4_k_m.gguf --local-dir .
 # Run inference
+./llama-cli -m sunflower-14B-q4_k_m.gguf -p "Translate to Luganda: Hello, how are you today?"
 ```
 ## Ollama Integration
 ```python
 from llama_cpp import Llama
+llm = Llama(model_path="sunflower-14B-q4_k_m.gguf")
 result = llm("Translate to Luganda: How are you?")
 print(result['choices'][0]['text'])
 ```
 ## License
+Apache 2.0