Instructions to use Josephgflowers/TinyLlama-3T-Cinder-v1.3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Josephgflowers/TinyLlama-3T-Cinder-v1.3 with Transformers:

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

pipe = pipeline("text-generation", model="Josephgflowers/TinyLlama-3T-Cinder-v1.3")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Josephgflowers/TinyLlama-3T-Cinder-v1.3")
model = AutoModelForCausalLM.from_pretrained("Josephgflowers/TinyLlama-3T-Cinder-v1.3")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

llama-cpp-python

How to use Josephgflowers/TinyLlama-3T-Cinder-v1.3 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Josephgflowers/TinyLlama-3T-Cinder-v1.3",
	filename="TinyLlama-3T-Cinder-v1.3.Q8_0.gguf",
)

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

Inference
Local Apps Settings

llama.cpp

How to use Josephgflowers/TinyLlama-3T-Cinder-v1.3 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/TinyLlama-3T-Cinder-v1.3:Q8_0
# Run inference directly in the terminal:
llama cli -hf Josephgflowers/TinyLlama-3T-Cinder-v1.3:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Josephgflowers/TinyLlama-3T-Cinder-v1.3:Q8_0
# Run inference directly in the terminal:
llama cli -hf Josephgflowers/TinyLlama-3T-Cinder-v1.3:Q8_0

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/TinyLlama-3T-Cinder-v1.3:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf Josephgflowers/TinyLlama-3T-Cinder-v1.3:Q8_0

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/TinyLlama-3T-Cinder-v1.3:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Josephgflowers/TinyLlama-3T-Cinder-v1.3:Q8_0

Use Docker

docker model run hf.co/Josephgflowers/TinyLlama-3T-Cinder-v1.3:Q8_0

LM Studio
Jan

vLLM

How to use Josephgflowers/TinyLlama-3T-Cinder-v1.3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Josephgflowers/TinyLlama-3T-Cinder-v1.3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Josephgflowers/TinyLlama-3T-Cinder-v1.3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Josephgflowers/TinyLlama-3T-Cinder-v1.3:Q8_0

SGLang

How to use Josephgflowers/TinyLlama-3T-Cinder-v1.3 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/TinyLlama-3T-Cinder-v1.3" \
    --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": "Josephgflowers/TinyLlama-3T-Cinder-v1.3",
		"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 "Josephgflowers/TinyLlama-3T-Cinder-v1.3" \
        --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": "Josephgflowers/TinyLlama-3T-Cinder-v1.3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use Josephgflowers/TinyLlama-3T-Cinder-v1.3 with Ollama:
```
ollama run hf.co/Josephgflowers/TinyLlama-3T-Cinder-v1.3:Q8_0
```

Unsloth Studio

How to use Josephgflowers/TinyLlama-3T-Cinder-v1.3 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 Josephgflowers/TinyLlama-3T-Cinder-v1.3 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 Josephgflowers/TinyLlama-3T-Cinder-v1.3 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Josephgflowers/TinyLlama-3T-Cinder-v1.3 to start chatting

Atomic Chat new
Docker Model Runner
How to use Josephgflowers/TinyLlama-3T-Cinder-v1.3 with Docker Model Runner:
```
docker model run hf.co/Josephgflowers/TinyLlama-3T-Cinder-v1.3:Q8_0
```

Lemonade

How to use Josephgflowers/TinyLlama-3T-Cinder-v1.3 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Josephgflowers/TinyLlama-3T-Cinder-v1.3:Q8_0

Run and chat with the model

lemonade run user.TinyLlama-3T-Cinder-v1.3-Q8_0

List all available models

lemonade list

Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Overview Cinder is an AI chatbot tailored for engaging users in scientific and educational conversations, offering companionship, and sparking imaginative exploration. It is built on the TinyLlama 1.1B parameter model and trained on a unique combination of datasets.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	37.23
AI2 Reasoning Challenge (25-Shot)	33.96
HellaSwag (10-Shot)	58.14
MMLU (5-Shot)	25.41
TruthfulQA (0-shot)	38.13
Winogrande (5-shot)	63.93
GSM8k (5-shot)	3.79

Downloads last month: 185

Safetensors

Model size

1B params

Tensor type

F16

Model tree for Josephgflowers/TinyLlama-3T-Cinder-v1.3

Merges

1 model

Quantizations

2 models

Space using Josephgflowers/TinyLlama-3T-Cinder-v1.3 1

Evaluation results

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

33.960
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

58.140
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

25.410
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

38.130
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

63.930
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

3.790