Instructions to use VitalContribution/Evangelion-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use VitalContribution/Evangelion-7B with Transformers:

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

pipe = pipeline("text-generation", model="VitalContribution/Evangelion-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("VitalContribution/Evangelion-7B")
model = AutoModelForCausalLM.from_pretrained("VitalContribution/Evangelion-7B")
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 Settings

vLLM

How to use VitalContribution/Evangelion-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "VitalContribution/Evangelion-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "VitalContribution/Evangelion-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/VitalContribution/Evangelion-7B

SGLang

How to use VitalContribution/Evangelion-7B 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 "VitalContribution/Evangelion-7B" \
    --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": "VitalContribution/Evangelion-7B",
		"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 "VitalContribution/Evangelion-7B" \
        --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": "VitalContribution/Evangelion-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use VitalContribution/Evangelion-7B with Docker Model Runner:
```
docker model run hf.co/VitalContribution/Evangelion-7B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

🌐 Company Website 🔗 Mozaic AI Solutions

✨ Overview

We were curious to see what happens if one uses:
$\text{{high-quality DPO dataset}} + \text{{merge of DPO optimized and non-DPO optimized model}}$

The underlying model used was:
/Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp

Dataset

Dataset: /argilla/distilabel-intel-orca-dpo-pairs

The dataset was roughly ~3000 samples but they were high quality (according to the chosen_score).
The following filters were applied to the original dataset:

dataset = dataset.filter(
    lambda r:
        r["status"] != "tie" and
        r["chosen_score"] >= 8 and
        not r["in_gsm8k_train"]
)

Chat Template

I decided to go with the ChatML which is used for OpenHermes2.5 By the way I integreated the chat template into the models tokenizer.

<|im_start|>system
{system}<|im_end|>
<|im_start|>user
{user}<|im_end|>
<|im_start|>assistant
{asistant}<|im_end|>

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	71.71
AI2 Reasoning Challenge (25-Shot)	68.94
HellaSwag (10-Shot)	86.45
MMLU (5-Shot)	63.97
TruthfulQA (0-shot)	64.01
Winogrande (5-shot)	79.95
GSM8k (5-shot)	66.94

Downloads last month: 97

Safetensors

Model size

7B params

Tensor type

F16

Model tree for VitalContribution/Evangelion-7B

Finetunes

1 model

Quantizations

7 models

Dataset used to train VitalContribution/Evangelion-7B

Spaces using VitalContribution/Evangelion-7B 8

Evaluation results

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

68.940
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

86.450
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

63.970
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

64.010
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

79.950
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

66.940