Instructions to use Zoyd/OpenLLM-Ro_RoMistral-7b-Instruct-6_0bpw_exl2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Zoyd/OpenLLM-Ro_RoMistral-7b-Instruct-6_0bpw_exl2 with Transformers:

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

pipe = pipeline("text-generation", model="Zoyd/OpenLLM-Ro_RoMistral-7b-Instruct-6_0bpw_exl2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Zoyd/OpenLLM-Ro_RoMistral-7b-Instruct-6_0bpw_exl2")
model = AutoModelForCausalLM.from_pretrained("Zoyd/OpenLLM-Ro_RoMistral-7b-Instruct-6_0bpw_exl2")
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 Zoyd/OpenLLM-Ro_RoMistral-7b-Instruct-6_0bpw_exl2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Zoyd/OpenLLM-Ro_RoMistral-7b-Instruct-6_0bpw_exl2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Zoyd/OpenLLM-Ro_RoMistral-7b-Instruct-6_0bpw_exl2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Zoyd/OpenLLM-Ro_RoMistral-7b-Instruct-6_0bpw_exl2

SGLang

How to use Zoyd/OpenLLM-Ro_RoMistral-7b-Instruct-6_0bpw_exl2 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 "Zoyd/OpenLLM-Ro_RoMistral-7b-Instruct-6_0bpw_exl2" \
    --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": "Zoyd/OpenLLM-Ro_RoMistral-7b-Instruct-6_0bpw_exl2",
		"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 "Zoyd/OpenLLM-Ro_RoMistral-7b-Instruct-6_0bpw_exl2" \
        --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": "Zoyd/OpenLLM-Ro_RoMistral-7b-Instruct-6_0bpw_exl2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Zoyd/OpenLLM-Ro_RoMistral-7b-Instruct-6_0bpw_exl2 with Docker Model Runner:
```
docker model run hf.co/Zoyd/OpenLLM-Ro_RoMistral-7b-Instruct-6_0bpw_exl2
```

Model Card for Model ID

RoMistral is a family of pretrained and fine-tuned generative text models for Romanian. This is the repository for the instruct 7B model. Links to other models can be found at the bottom of this page.

Model Details

Model Description

OpenLLM-Ro represents the first open-source effort to build a LLM specialized for Romanian. OpenLLM-Ro developed and publicly releases a collection of Romanian LLMs, both in the form of foundational model and instruct and chat variants.

Developed by: OpenLLM-Ro
Language(s): Romanian
License: cc-by-nc-4.0
Finetuned from model: Mistral-7B-v0.1

Model Sources

Repository: https://github.com/OpenLLM-Ro/llama-recipes
Paper: https://arxiv.org/abs/2405.07703

Intended Use

Intended Use Cases

RoMistral is intented for research use in Romanian. Base models can be adapted for a variety of natural language tasks while instruction and chat tuned models are intended for assistant-like chat.

Out-of-Scope Use

Use in any manner that violates the license, any applicable laws or regluations, use in languages other than Romanian.

How to Get Started with the Model

Use the code below to get started with the model.

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("OpenLLM-Ro/RoMistral-7b-Instruct")
model = AutoModelForCausalLM.from_pretrained("OpenLLM-Ro/RoMistral-7b-Instruct")

instruction = "Ce jocuri de societate pot juca cu prietenii mei?"
chat = [
        {"role": "user", "content": instruction},
        ]
prompt = tokenizer.apply_chat_template(chat, tokenize=False, system_message="")

inputs = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt")
outputs = model.generate(input_ids=inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0]))

Benchmarks

Model	Average	ARC	MMLU	Winogrande	HellaSwag	GSM8k	TruthfulQA
Mistral-7B-Instruct-v0.2	45.63	43.09	44.87	59.26	54.12	10.86	61.56
RoMistral-7b-Instruct	52.49	50.39	51.64	66.69	60.24	33.71	52.59

MT-Bench

Model	Average	1st turn	2nd turn
Mistral-7B-Instruct-v0.2	5.84	6.06	5.63
RoMistral-7b-Instruct	5.92	6.53	5.415

RoMistral Model Family

Model	Link
RoMistral-7b-Instruct	link

Downloads last month: 2

Paper for Zoyd/OpenLLM-Ro_RoMistral-7b-Instruct-6_0bpw_exl2

OpenLLM-Ro -- Technical Report on Open-source Romanian LLMs trained starting from Llama 2

Paper • 2405.07703 • Published May 13, 2024