Instructions to use Solshine/reflection-llama-3.1-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Solshine/reflection-llama-3.1-8B with Transformers:

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

pipe = pipeline("text-generation", model="Solshine/reflection-llama-3.1-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Solshine/reflection-llama-3.1-8B")
model = AutoModelForCausalLM.from_pretrained("Solshine/reflection-llama-3.1-8B")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Solshine/reflection-llama-3.1-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Solshine/reflection-llama-3.1-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Solshine/reflection-llama-3.1-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Solshine/reflection-llama-3.1-8B

SGLang

How to use Solshine/reflection-llama-3.1-8B 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 "Solshine/reflection-llama-3.1-8B" \
    --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": "Solshine/reflection-llama-3.1-8B",
		"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 "Solshine/reflection-llama-3.1-8B" \
        --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": "Solshine/reflection-llama-3.1-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use Solshine/reflection-llama-3.1-8B 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 Solshine/reflection-llama-3.1-8B 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 Solshine/reflection-llama-3.1-8B to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Solshine/reflection-llama-3.1-8B to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="Solshine/reflection-llama-3.1-8B",
    max_seq_length=2048,
)

Docker Model Runner
How to use Solshine/reflection-llama-3.1-8B with Docker Model Runner:
```
docker model run hf.co/Solshine/reflection-llama-3.1-8B
```

This model is TrainRound5, following Solshine/reflection-llama-3.1-8B-Solshine-trainround4-16bit in an iterative fine-tuning process

Not Officially Benchmarked Yet! (Please submit any benchmarking or eval results via the Community tab.)

Uploaded model

Developed by: Solshine (Caleb DeLeeuw)
License: llama 3.1
Finetuned from model : Solshine/reflection-llama-3.1-8B-Solshine-trainround4-16bit

This model, trained on chain of thoughts within the reinforcement learning, predates OpenAI's o1 model. Inspired by and featuring the Reflection Tuning technique pioneered by Matt Shumer (possibly earlier innovated by the team at Anthropic, and Mlabbone' Hermes.)

To the authors' knowledge, this is V5 of the first "reflection tuned" Llama 3.1 8B LLM

As per the inspiring model "mattshumer/Reflection-Llama-3.1-70B" (this mode was not used in the training process nor as a foundational model, but only served as inspiration) :

'''

During sampling, the model will start by outputting reasoning inside and tags, and then once it is satisfied with its reasoning, it will output the final answer inside and tags. Each of these tags are special tokens, trained into the model.

This enables the model to separate its internal thoughts and reasoning from its final answer, improving the experience for the user.

Inside the section, the model may output one or more tags, which signals the model has caught an error in its reasoning and will attempt to correct it before providing a final answer.

System Prompt: The system prompt used for training this model is:

You are a world-class AI system, capable of complex reasoning and reflection. Reason through the query inside tags, and then provide your final response inside tags. If you detect that you made a mistake in your reasoning at any point, correct yourself inside tags.

We recommend using this exact system prompt to get the best results from Reflection Llama-3.1 70B. You may also want to experiment combining this system prompt with your own custom instructions to customize the behavior of the model.

Chat Format: As mentioned above, the model uses the standard Llama 3.1 chat format. Here’s an example:

<|begin_of_text|><|start_header_id|>system<|end_header_id|>

'''

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.