Instructions to use mightbe/EEVE-10.8B-Multiturn with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mightbe/EEVE-10.8B-Multiturn with Transformers:

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

pipe = pipeline("text-generation", model="mightbe/EEVE-10.8B-Multiturn")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mightbe/EEVE-10.8B-Multiturn")
model = AutoModelForCausalLM.from_pretrained("mightbe/EEVE-10.8B-Multiturn")
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 mightbe/EEVE-10.8B-Multiturn with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mightbe/EEVE-10.8B-Multiturn"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mightbe/EEVE-10.8B-Multiturn",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mightbe/EEVE-10.8B-Multiturn

SGLang

How to use mightbe/EEVE-10.8B-Multiturn 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 "mightbe/EEVE-10.8B-Multiturn" \
    --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": "mightbe/EEVE-10.8B-Multiturn",
		"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 "mightbe/EEVE-10.8B-Multiturn" \
        --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": "mightbe/EEVE-10.8B-Multiturn",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use mightbe/EEVE-10.8B-Multiturn with Docker Model Runner:
```
docker model run hf.co/mightbe/EEVE-10.8B-Multiturn
```

mightbe commited on Mar 20, 2024

Commit

2084ff3

verified ·

1 Parent(s): 107a7cd

Create README.md

Browse files

Files changed (1) hide show

README.md +35 -0

README.md ADDED Viewed

	@@ -0,0 +1,35 @@

+---
+license: apache-2.0
+---
+# EEVE-10.8B-Multiturn
+본 모델은 KoVast 데이터셋 및 argilla의 데이터셋으로 학습되었습니다.
+Jolteon 모델 학습과정에서 나온 부산물입니다.
+**주의**
+해당 모델은 완벽하게 학습이 되지 않은 초기모델입니다. 짧은 답변, 추론의 부재등의 문제가 발생 할 수 있습니다.
+## 프롬프트 포맷
+```
+Below is an instruction that describes a task. Write a response that appropriately completes the request.
+### Instruction: {instruction}
+### Response: {response}</s><|im_end|> ### Instruction: {instruction}
+### Response: {response}</s><|im_end|>
+```
+## License
+본 모델은 apache-2.0 라이센스를 따릅니다. 모델을 사용하여 생성된 데이터셋을 배포할 경우 모델 사용을 명시해 주시기를 권고드립니다.
+## Thanks to
+- A100 클러스터를 제공해주신, [Sionic AI](https://sionic.ai/)
+## Contact
+- [Discord Server Link](https://discord.gg/MrBt3PXdXc)