Instructions to use mattshumer/ref_70_e3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mattshumer/ref_70_e3 with Transformers:

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

pipe = pipeline("text-generation", model="mattshumer/ref_70_e3")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mattshumer/ref_70_e3")
model = AutoModelForCausalLM.from_pretrained("mattshumer/ref_70_e3")
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 mattshumer/ref_70_e3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mattshumer/ref_70_e3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mattshumer/ref_70_e3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mattshumer/ref_70_e3

SGLang

How to use mattshumer/ref_70_e3 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 "mattshumer/ref_70_e3" \
    --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": "mattshumer/ref_70_e3",
		"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 "mattshumer/ref_70_e3" \
        --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": "mattshumer/ref_70_e3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use mattshumer/ref_70_e3 with Docker Model Runner:
```
docker model run hf.co/mattshumer/ref_70_e3
```

Effect of the fine-tuning

#12

by mmbela - opened Sep 10, 2024

Discussion

mmbela

Sep 10, 2024

Without quantization, testing ep2 and ep3 under the same conditions, they seem to have the same knowledge of the new feature (reflection), but the overall, original knowledge of ep3 is weaker, which is not unusual for finetuning. I think ep2 performs better, it would be worth trying ep1 as well.

ElevenGames

Sep 10, 2024

That is funny, because the model files of ep2 and ep3 are exactly the same. You can see that here in the community discussion "mattshumer/ref_70_e3 and mattshumer/Reflection-Llama-3.1-70B-ep2-working are the SAME." and you can even compare the hash values (SHA256) of all the model files uploaded. The hashes prove that the uploaded files of ep2 and ep3 are exactly the same files, identical in every single bit.
You just had more "luck" testing one over the other. Given that and the other technical fails on this repository here, I don't think the models uploaded here deserve the attention they are getting.

mmbela

Sep 13, 2024

You are right.

mmbela changed discussion status to closed Sep 13, 2024

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment