Instructions to use occiglot/occiglot-7b-it-en-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use occiglot/occiglot-7b-it-en-instruct with Transformers:

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

pipe = pipeline("text-generation", model="occiglot/occiglot-7b-it-en-instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("occiglot/occiglot-7b-it-en-instruct")
model = AutoModelForCausalLM.from_pretrained("occiglot/occiglot-7b-it-en-instruct")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use occiglot/occiglot-7b-it-en-instruct with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/occiglot/occiglot-7b-it-en-instruct

SGLang

How to use occiglot/occiglot-7b-it-en-instruct 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 "occiglot/occiglot-7b-it-en-instruct" \
    --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": "occiglot/occiglot-7b-it-en-instruct",
		"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 "occiglot/occiglot-7b-it-en-instruct" \
        --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": "occiglot/occiglot-7b-it-en-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

Occiglot-7B-it-en-Instruct

A polyglot language model for the Occident.

Occiglot-7B-EU5-Instruct is a the instruct version of occiglot-7b-it-en, a generative language model with 7B parameters supporting the top-5 EU languages (English, Spanish, French, German, and Italian) and trained by the Occiglot Research Collective. It was trained on 160M tokens of additional multilingual and code instructions. Note that the model was not safety aligned and might generate problematic outputs.

This is the first release of an ongoing open research project for multilingual language models. If you want to train a model for your own language or are working on evaluations, please contact us or join our Discord server. We are open for collaborations!

Model details

Instruction tuned from: occiglot-7b-it-en
Model type: Causal decoder-only transformer language model
Languages: English, Italian, and code.
License: Apache 2.0
Compute resources: DFKI cluster
Contributors: Manuel Brack, Patrick Schramowski, Pedro Ortiz, Malte Ostendorff, Fabio Barth, Georg Rehm, Kristian Kersting
Research labs: Occiglot with support from SAINT and SLT
Contact: Discord

How to use

The model was trained using the chatml instruction template. You can use the transformers chat template feature for interaction. Since the generation relies on some randomness, we set a seed for reproducibility:

>>> from transformers import AutoTokenizer, MistralForCausalLM, set_seed
>>> tokenizer = AutoTokenizer.from_pretrained("occiglot/occiglot-7b-eu5-instruct")
>>> model = MistralForCausalLM.from_pretrained('occiglot/occiglot-7b-eu5-instruct')  # You may want to use bfloat16 and/or move to GPU here
>>> set_seed(42)
>>> messages = [
>>>    {"role": "system", 'content': 'You are a helpful assistant. Please give short and concise answers.'},
>>>    {"role": "user", "content": "chi è il primo ministro italiano?"},
>>> ]
>>> tokenized_chat = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_dict=False, return_tensors='pt',)
>>> set_seed(42)
>>> outputs = model.generate(tokenized_chat.to('cuda'), max_new_tokens=200,)
>>> tokenizer.decode(out[0][len(tokenized_chat[0]):])
'Il primo ministro italiano è attualmente Giorgia Meloni, presidente di Fratelli d'Italia, un partito politico di estrema destra.'

Dataset

The training data was split evenly amongst the 5 languages based on the total number of tokens. We would like to thank Disco Research and Björn Plüster for making their dataset available to us.

English and Code

Open-Hermes-2B

Italian

Quora-IT-Baize
Stackoverflow-IT-Vaize
Camoscio
OASST-2 (Italian subset)
Aya-Dataset (Italian subset)

Training settings

Full instruction fine-tuning on 8xH100.
0.6 - 4 training epochs (depending on dataset sampling).
Framework: axolotl
Precision: bf16
Optimizer: AdamW
Global batch size: 128 (with 8192 context length)
Cosine Annealing with Warmup

Tokenizer

Tokenizer is unchanged from Mistral-7B-v0.1.

Evaluation

Preliminary evaluation results can be found below. Please note that the non-English results are based on partially machine-translated datasets and English prompts (Belebele and Okapi framework) and thus should be interpreted with caution, e.g., biased towards English model performance. Currently, we are working on more suitable benchmarks for Spanish, French, German, and Italian.

Evaluation results

English

	arc_challenge	belebele	hellaswag	mmlu	truthfulqa	avg
occiglot/occiglot-7b-eu5	0.530717	0.726667	0.789882	0.531904	0.403678	0.59657
occiglot/occiglot-7b-eu5-instruct	0.558874	0.746667	0.799841	0.535109	0.449034	0.617905
occiglot/occiglot-7b-it-en	0.580205	0.774444	0.804222	0.578977	0.412786	0.630127
occiglot/occiglot-7b-it-en-instruct	0.609215	0.82	0.809301	0.578835	0.479562	0.659383
galatolo/cerbero-7b	0.613481	0.827778	0.810396	0.600484	0.480911	0.66661
mistralai/Mistral-7B-v0.1	0.612628	0.844444	0.834097	0.624555	0.426201	0.668385
mistralai/Mistral-7B-Instruct-v0.2	0.637372	0.824444	0.846345	0.59201	0.668116	0.713657

Italian

	arc_challenge_it	belebele_it	hellaswag_it	truthfulqa_it	avg
occiglot/occiglot-7b-eu5	0.501283	0.652222	0.700533	0.252874	0.421382
occiglot/occiglot-7b-eu5-instruct	0.516681	0.661111	0.71326	0.295019	0.437214
occiglot/occiglot-7b-it-en	0.536356	0.684444	0.694768	0.247765	0.432667
occiglot/occiglot-7b-it-en-instruct	0.545766	0.717778	0.713804	0.303959	0.456261
galatolo/cerbero-7b	0.522669	0.717778	0.631567	0.302682	0.434939
mistralai/Mistral-7B-v0.1	0.502139	0.734444	0.630371	0.264368	0.426264
mistralai/Mistral-7B-Instruct-v0.2	0.519247	0.703333	0.6394	0.349936	0.442383