Luciole-23B-Instruct-1.1 is a fine-tuned and aligned version of Luciole-23B-Base, an open-source, multilingual causal language model created by OpenLLM-France. Luciole-23B-Instruct-1.1 was developed by LINAGORA and the OpenLLM-France consortium as a part of the OpenLLM France project, funded by BPI France through the France 2030 program.
Training of Luciole-23B-Instruct-1.1 was conducted on Jean Zay in three phases: (i) a supervised fine-tuning (SFT) phase on instruction data with thinking traces, (ii) an SFT phase on instruction data without thinking traces, and (iii) a final preference alignment phase using Direct Preference Optimization (DPO). The training data covers topics in math, science, coding, general chat, RAG and translation.
Note that Luciole-23B-Instruct-1.1 is only the first iteration of post-trained models based on Luciole-23B-Base. Development of the Luciole models is an active, ongoing project and further iterations, including models trained on higher proportions of French data, are planned. In the spirit of open-source, we share the model weights and training recipes to facilitate research and to provide open source building blocks for other training projects.
If you are interested in contributing to the Luciole project, contact us at contact@openllm-france.fr.
Luciole-23B-Instruct-1.1 is the result of a first phase of fine-tuning and alignment to human preferences. Efforts to improve the model are active and ongoing and the model should be thoroughly tested for target use cases before being incorporated in industrial pipelines. Training has mostly focused on instruction following, and additional training would be necessary for tasks specifically focused on code generation or mathematical problem solving. It is also susceptible to hallucinations; that is, producing false answers that result from its training on massive amounts of diverse text.
Luciole-23B-Instruct-1.1 was post-trained almost entirely on English data (in contrast to its base model, OpenLLM-France/Luciole-23B-Base, which was trained on roughly 30% French data). Future post-training phases will focus specifically on increasing the proportion of French data and testing the impact that this has on model performance.
Due to its size, Luciole-23B-Instruct-1.1 is limited in the information that it can memorize; its ability to produce correct answers could be improved by implementing the model in a retrieval augmented generation pipeline.
Finally, Luciole-23B-Instruct-1.1 was trained on sequences of 16,384 tokens (in contrast to its base model, whose context window was extended to 131,000 tokens).
Recommendations
Further train Luciole-23B-Instruct-1.1 for specific use cases.
Integrate the model in a RAG pipeline to augment its knowledge base.
Extend training with longer sequences to increase context length.
Training details
Training data
The post-training data and dataset description is available here.
Instruction template
Luciole-23B-Instruct-1.1 was trained on the chat template inspired from Qwen3-1.7B. In our chat template, we also use a default system prompt.
An example:
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("OpenLLM-France/Luciole-23B-Instruct-1.1")
chat = [
{
"content": "Who was Molière?",
"role": "user"
},
{
"content": "Molière was a 17th-century French playwright, actor, and comedian.",
"role": "assistant"
},
{
"content": "What are his best-known works?",
"role": "user"
}
]
print(tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True))
gives the output
<|im_start|>system
You are a helpful AI assistant named Luciole, trained by LINAGORA and OpenLLM France.<|im_end|>
<|im_start|>user
Who was Molière?<|im_end|>
<|im_start|>assistant
Molière was a 17th-century French playwright, actor, and comedian.<|im_end|>
<|im_start|>user
What are his best-known works?<|im_end|>
<|im_start|>assistant
Training procedure
Luciole-23B-Instruct-1.1 was trained in three phases. The model was first finetuned on thinking data, and then on data without thinking traces. The resulting instruct model was aligned during a final DPO finetuning phase.
Overall, Luciole-23B-Instruct-1.1 performs comparably with other open source instruct models of the same size. The model performs particularly well on instruction following benchmarks. Its performance on French language instruction following (ifeval-fr) is notable since Luciole-23B-Instruct-1.1 was finetuned on mostly English language data. This is likely the effect of seeing a larger proportion of French data during pretraining.
Testing the model
Test with ollama
Note: for best performance, please use the GGUF files released officially by OpenLLM.
To test the deployed model, use the OpenAI Python client as follows:
python
1from openai import OpenAI
23# Initialize the client4client = OpenAI(base_url='http://localhost:8000/v1', api_key='empty')56# Define the input content7content ="Hello Luciole"89# Generate a response10chat_response = client.chat.completions.create(11 model="OpenLLM-France/Luciole-23B-Instruct-1.1",12 messages=[13{"role":"user","content": content}14],15)16print(chat_response.choices[0].message.content)
Citation
✍ Paper coming soon!
Acknowledgements
We gratefully acknowledge BPI France for funding the OpenLLM France project under the call "Communs numériques pour l’intelligence artificielle générative" ("Digital commons for generative artificial intelligence") as a part of the France 2030 program.
Training of Luciole-23B-Instruct-1.1 was made possible by computing AI and storage resources by GENCI at IDRIS thanks to the project A0181016189 on the supercomputer Jean Zay’s H100 partition. We gratefully acknowledge their support.
Luciole-23B-Instruct-1.1 was created by members of LINAGORA and the OpenLLM-France community, including in alphabetical order:
Particular thanks to the following OpenLLM France members for their valuable input: Clément Bénesse (Opsci), Christophe Cerisara (LORIA) and Gabriel Lauzzana (LORIA).
We thank the support teams from IDRIS and NVIDIA for technical guidance throughout the project.
We would also like to thank members of the Gaperon and Salamandra projects for sharing their insights with us. We also acknowledge the numerous open source actors whose resources have guided us throughout the training process, with particular thanks to Nvidia, HuggingFace and Allen AI.
Finally, we thank the entire OpenLLM-France community, whose members have helped in diverse ways.
