Instructions to use tencent/HY-MT1.5-1.8B-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use tencent/HY-MT1.5-1.8B-FP8 with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "translation" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("translation", model="tencent/HY-MT1.5-1.8B-FP8")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("tencent/HY-MT1.5-1.8B-FP8") model = AutoModelForCausalLM.from_pretrained("tencent/HY-MT1.5-1.8B-FP8", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download model.safetensors from tencent/HY-MT1.5-1.8B-FP8: direct link, hf CLI and curl.
- Browser
- Download file 2.04 GB
-
https://huggingface.co/tencent/HY-MT1.5-1.8B-FP8/resolve/main/model.safetensors
- Command line
-
hf download hf://tencent/HY-MT1.5-1.8B-FP8/model.safetensors
-
curl -L -o model.safetensors https://huggingface.co/tencent/HY-MT1.5-1.8B-FP8/resolve/main/model.safetensors
2.04 GB
- Xet hash:
- 9e1d26755f9bee5f52c93b2e84304d94e2a12f8aeba0d5b07fb016be2133b42b
- Size of remote file:
- 2.04 GB
- SHA256:
- d318a9df24c583666fbb910c0d461edcc42847b9b1a27e06bd709c9a95eaf75c
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.