Arxiv:2503.12294 Base model:finetune:openllm-fr... Base model:openllm-france/luci... Conversational Dataset:ai2-adapt-dev/flan v2 ... Dataset:allenai/tulu-3-sft-per... Dataset:allenai/tulu-3-sft-per... Dataset:allenai/wildchat-1m Dataset:cmh/alpaca data cleane... Dataset:gael540/dataset ens su... Dataset:openllm-france/croissa... Dataset:teknium/openhermes-2.5 En Fr Instruct Llama Openllm-france Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/OpenLLM-France/Lucie-7B-Instruct-v1.1
Lucie 7B Instruct V1.1 Benchmarks
MMLU Pro: 9.6
GPQA: 4.25
MUSR: 3.84
BBH: 14.74
IFEval: 30.39 vs 88 (so35)-65.5%
MATH Lvl 5: 3.17
LLME Score: 0.27165
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Lucie 7B Instruct V1.1 Parameters and Internals
| LLM Name | Lucie 7B Instruct V1.1 |
| Repository 🤗 | https://huggingface.co/OpenLLM-France/Lucie-7B-Instruct-v1.1 |
| Base Model(s) | |
| Model Size | 7b |
| Required VRAM | 13.4 GB |
| Updated | 2025-08-23 |
| Maintainer | OpenLLM-France |
| Model Type | llama |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | fr en |
| Model Architecture | LlamaForCausalLM |
| License | apache-2.0 |
| Context Length | 32000 |
| Model Max Length | 32000 |
| Transformers Version | 4.46.3 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <pad> |
| Vocabulary Size | 65024 |
| Torch Data Type | bfloat16 |
Best Alternatives to Lucie 7B Instruct V1.1
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| A3.4 | 1024K / 16.1 GB | 13 | 0 |
| A5.4 | 1024K / 16.1 GB | 12 | 0 |
| A2.4 | 1024K / 16.1 GB | 12 | 0 |
| 124 | 1024K / 16.1 GB | 93 | 0 |
| ... Qwen2.5llamaify 7B V23.1 200K | 195K / 15.2 GB | 999 | 4 |
| SuperNeuralDreadDevil 8B | 128K / 16.1 GB | 77 | 1 |
| Falcon3 7B Instruct | 32K / 14.8 GB | 30075 | 72 |
| Falcon3 Jessi V0.4 7B Slerp | 32K / 14.9 GB | 6 | 9 |
| Jessi V0.4 Falcon3 7B Instruct | 32K / 14.8 GB | 5 | 0 |
| Jessi V0.6 Falcon3 7B Instruct | 32K / 14.8 GB | 6 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than OpenLLM-France/Lucie-7B-Instruct-v1.1 .
Rank the Lucie 7B Instruct V1.1 Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 50836 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124