metadata
license: apache-2.0
pipeline_tag: text-generation
language:
- fr
- en
tags:
- openllm-france
- TensorBlock
- GGUF
datasets:
- cmh/alpaca_data_cleaned_fr_52k
- OpenLLM-France/Croissant-Aligned-Instruct
- Gael540/dataSet_ens_sup_fr-v1
- ai2-adapt-dev/flan_v2_converted
- teknium/OpenHermes-2.5
- allenai/tulu-3-sft-personas-math
- allenai/tulu-3-sft-personas-math-grade
- allenai/WildChat-1M
base_model: OpenLLM-France/Lucie-7B-Instruct-v1.1
widget:
- text: |-
Quelle est la capitale de l'Espagne ? Madrid.
Quelle est la capitale de la France ?
example_title: Capital cities in French
group: 1-shot Question Answering
training_progress:
context_length: 32000
OpenLLM-France/Lucie-7B-Instruct-v1.1 - GGUF
This repo contains GGUF format model files for OpenLLM-France/Lucie-7B-Instruct-v1.1.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4882.
Our projects
| Awesome MCP Servers | TensorBlock Studio |
|---|---|
 |
 |
| A comprehensive collection of Model Context Protocol (MCP) servers. | A lightweight, open, and extensible multi-LLM interaction studio. |
| 👀 See what we built 👀 | 👀 See what we built 👀 |
<s><|start_header_id|>system<|end_header_id|>
{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
Model file specification
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| Lucie-7B-Instruct-v1.1-Q2_K.gguf | Q2_K | 2.584 GB | smallest, significant quality loss - not recommended for most purposes |
| Lucie-7B-Instruct-v1.1-Q3_K_S.gguf | Q3_K_S | 2.988 GB | very small, high quality loss |
| Lucie-7B-Instruct-v1.1-Q3_K_M.gguf | Q3_K_M | 3.305 GB | very small, high quality loss |
| Lucie-7B-Instruct-v1.1-Q3_K_L.gguf | Q3_K_L | 3.577 GB | small, substantial quality loss |
| Lucie-7B-Instruct-v1.1-Q4_0.gguf | Q4_0 | 3.844 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| Lucie-7B-Instruct-v1.1-Q4_K_S.gguf | Q4_K_S | 3.871 GB | small, greater quality loss |
| Lucie-7B-Instruct-v1.1-Q4_K_M.gguf | Q4_K_M | 4.069 GB | medium, balanced quality - recommended |
| Lucie-7B-Instruct-v1.1-Q5_0.gguf | Q5_0 | 4.649 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| Lucie-7B-Instruct-v1.1-Q5_K_S.gguf | Q5_K_S | 4.649 GB | large, low quality loss - recommended |
| Lucie-7B-Instruct-v1.1-Q5_K_M.gguf | Q5_K_M | 4.765 GB | large, very low quality loss - recommended |
| Lucie-7B-Instruct-v1.1-Q6_K.gguf | Q6_K | 5.504 GB | very large, extremely low quality loss |
| Lucie-7B-Instruct-v1.1-Q8_0.gguf | Q8_0 | 7.128 GB | very large, extremely low quality loss - not recommended |
Downloading instruction
Command line
Firstly, install Huggingface Client
pip install -U "huggingface_hub[cli]"
Then, downoad the individual model file the a local directory
huggingface-cli download tensorblock/Lucie-7B-Instruct-v1.1-GGUF --include "Lucie-7B-Instruct-v1.1-Q2_K.gguf" --local-dir MY_LOCAL_DIR
If you wanna download multiple model files with a pattern (e.g., *Q4_K*gguf), you can try:
huggingface-cli download tensorblock/Lucie-7B-Instruct-v1.1-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'