| license: apache-2.0 | |
| base_model: utter-project/EuroLLM-1.7B-Instruct | |
| base_model_relation: quantized | |
| language: | |
| - fr | |
| - en | |
| tags: | |
| - gguf | |
| - llama.cpp | |
| - translation | |
| # EuroLLM-1.7B-Instruct, Q4_0 GGUF | |
| Q4_0 quantization of [utter-project/EuroLLM-1.7B-Instruct](https://huggingface.co/utter-project/EuroLLM-1.7B-Instruct) (revision `a25c7fa65fc2a644e6270b8940dbe295b51da681`), used for on-device French <-> English translation in the Gaby Translator app. | |
| - Converted to f16 with `convert_hf_to_gguf.py`, then quantized with `llama-quantize` (llama.cpp tag `b11347`, commit `5fc4f3c8c7103ffd0b7ff5ee4855bcc78a3ed5cd`). No imatrix. | |
| - `eurollm-1.7b-instruct-q4_0.gguf`: 1002984736 bytes, SHA-256 `6a07547f180dc16e14df1605ae3ba92c555665bd7d7f30ebcf267ff3146f073f`. | |
| - Chat template: ChatML, end of turn `<|im_end|>`. | |
| Licensed under Apache-2.0, as the original model. All credit for the model goes to the EuroLLM authors. | |