Instructions to use Josephgflowers/Cinder-Phi-2-V1-F16-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Josephgflowers/Cinder-Phi-2-V1-F16-gguf with Transformers:

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

pipe = pipeline("text-generation", model="Josephgflowers/Cinder-Phi-2-V1-F16-gguf", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Josephgflowers/Cinder-Phi-2-V1-F16-gguf", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Josephgflowers/Cinder-Phi-2-V1-F16-gguf", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Josephgflowers/Cinder-Phi-2-V1-F16-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 Josephgflowers/Cinder-Phi-2-V1-F16-gguf:F16
# Run inference directly in the terminal:
llama cli -hf Josephgflowers/Cinder-Phi-2-V1-F16-gguf:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Josephgflowers/Cinder-Phi-2-V1-F16-gguf:F16
# Run inference directly in the terminal:
llama cli -hf Josephgflowers/Cinder-Phi-2-V1-F16-gguf:F16

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 Josephgflowers/Cinder-Phi-2-V1-F16-gguf:F16
# Run inference directly in the terminal:
./llama-cli -hf Josephgflowers/Cinder-Phi-2-V1-F16-gguf:F16

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 Josephgflowers/Cinder-Phi-2-V1-F16-gguf:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Josephgflowers/Cinder-Phi-2-V1-F16-gguf:F16

Use Docker

docker model run hf.co/Josephgflowers/Cinder-Phi-2-V1-F16-gguf:F16

LM Studio
Jan

vLLM

How to use Josephgflowers/Cinder-Phi-2-V1-F16-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Josephgflowers/Cinder-Phi-2-V1-F16-gguf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Josephgflowers/Cinder-Phi-2-V1-F16-gguf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Josephgflowers/Cinder-Phi-2-V1-F16-gguf:F16

SGLang

How to use Josephgflowers/Cinder-Phi-2-V1-F16-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 "Josephgflowers/Cinder-Phi-2-V1-F16-gguf" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Josephgflowers/Cinder-Phi-2-V1-F16-gguf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "Josephgflowers/Cinder-Phi-2-V1-F16-gguf" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Josephgflowers/Cinder-Phi-2-V1-F16-gguf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use Josephgflowers/Cinder-Phi-2-V1-F16-gguf with Ollama:
```
ollama run hf.co/Josephgflowers/Cinder-Phi-2-V1-F16-gguf:F16
```
Unsloth Desktop
Docker Model Runner
How to use Josephgflowers/Cinder-Phi-2-V1-F16-gguf with Docker Model Runner:
```
docker model run hf.co/Josephgflowers/Cinder-Phi-2-V1-F16-gguf:F16
```

Lemonade

How to use Josephgflowers/Cinder-Phi-2-V1-F16-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Josephgflowers/Cinder-Phi-2-V1-F16-gguf:F16

Run and chat with the model

lemonade run user.Cinder-Phi-2-V1-F16-gguf-F16

List all available models

lemonade list

Atomic Chat

I am really enjoying this version of Cinder. More information coming. Training data similar to openhermes2.5 with some added math, STEM, and reasoning mostly from OpenOrca. As well as Cinder character specific data, a mix of RAG generated Q and A of world knowledge, STEM topics, and Cinder Character data. I suplimented the Cinder character with an abreviated Samantha dataset edited for Cinder and removed a lot of the negative responses. Model Overview Cinder is an AI chatbot tailored for engaging users in scientific and educational conversations, offering companionship, and sparking imaginative exploration.

Chat example from LM Studio:

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	58.86
AI2 Reasoning Challenge (25-Shot)	58.28
HellaSwag (10-Shot)	74.04
MMLU (5-Shot)	54.46
TruthfulQA (0-shot)	44.50
Winogrande (5-shot)	74.66
GSM8k (5-shot)	47.23

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	10.86
IFEval (0-Shot)	23.57
BBH (3-Shot)	22.45
MATH Lvl 5 (4-Shot)	0.00
GPQA (0-shot)	4.25
MuSR (0-shot)	1.97
MMLU-PRO (5-shot)	12.90

Downloads last month: 211

Safetensors

Model size

3B params

Tensor type

F16

Evaluation results

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

58.280
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

74.040
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

54.460
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

44.500
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

74.660
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

47.230
strict accuracy on IFEval (0-Shot)
Open LLM Leaderboard

23.570
normalized accuracy on BBH (3-Shot)
Open LLM Leaderboard

22.450