Instructions to use fsaudm/Reflection-Llama-3.1-70B-Instruct-NF4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fsaudm/Reflection-Llama-3.1-70B-Instruct-NF4 with Transformers:

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

pipe = pipeline("text-generation", model="fsaudm/Reflection-Llama-3.1-70B-Instruct-NF4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("fsaudm/Reflection-Llama-3.1-70B-Instruct-NF4")
model = AutoModelForCausalLM.from_pretrained("fsaudm/Reflection-Llama-3.1-70B-Instruct-NF4")
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 fsaudm/Reflection-Llama-3.1-70B-Instruct-NF4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "fsaudm/Reflection-Llama-3.1-70B-Instruct-NF4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fsaudm/Reflection-Llama-3.1-70B-Instruct-NF4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/fsaudm/Reflection-Llama-3.1-70B-Instruct-NF4

SGLang

How to use fsaudm/Reflection-Llama-3.1-70B-Instruct-NF4 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 "fsaudm/Reflection-Llama-3.1-70B-Instruct-NF4" \
    --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": "fsaudm/Reflection-Llama-3.1-70B-Instruct-NF4",
		"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 "fsaudm/Reflection-Llama-3.1-70B-Instruct-NF4" \
        --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": "fsaudm/Reflection-Llama-3.1-70B-Instruct-NF4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use fsaudm/Reflection-Llama-3.1-70B-Instruct-NF4 with Docker Model Runner:
```
docker model run hf.co/fsaudm/Reflection-Llama-3.1-70B-Instruct-NF4
```

Model Card for Model ID

This is a quantized version of Reflection Llama 3.1 70B Instruct. Quantized to 4-bit using bistandbytes and accelerate.

Developed by: Farid Saud @ DSRS
Base Model: meta-llama/Meta-Llama-3.1-70B-Instruct

There is (currently) a lot of controversy with this model's legitimacy, use with caution.

Use this model

Use a pipeline as a high-level helper:

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

messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe = pipeline("text-generation", model="fsaudm/Reflection-Llama-3.1-70B-Instruct-NF4")
pipe(messages)

Load model directly

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("fsaudm/Reflection-Llama-3.1-70B-Instruct-NF4")
model = AutoModelForCausalLM.from_pretrained("fsaudm/Reflection-Llama-3.1-70B-Instruct-NF4")

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 <thinking> tags, and then provide your final response inside <output> tags. If you detect that you made a mistake in your reasoning at any point, correct yourself inside <reflection> tags.

We recommend using this exact system prompt to get the best results from Reflection 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|>

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

what is 2+2?<|eot_id|><|start_header_id|>assistant<|end_header_id|>

Tips for Performance

We are initially recommending a temperature of .7 and a top_p of .95.
For increased accuracy, append Think carefully. at the end of your messages.

Downloads last month: 1

Safetensors

Model size

73B params

Tensor type

F32

BF16

Model tree for fsaudm/Reflection-Llama-3.1-70B-Instruct-NF4

Base model

meta-llama/Llama-3.1-70B

Finetuned

meta-llama/Llama-3.1-70B-Instruct

Finetuned

mattshumer/ref_70_e3

Quantized

(10)

this model