Translation
Transformers
Safetensors
Ukrainian
m2m_100
text2text-generation
surzhyk
ukrainian
text-normalization
seq2seq
nllb
qlora
Instructions to use vlddshk/SyrzykAI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use vlddshk/SyrzykAI 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="vlddshk/SyrzykAI")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("vlddshk/SyrzykAI") model = AutoModelForSeq2SeqLM.from_pretrained("vlddshk/SyrzykAI", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from vlddshk/SyrzykAI: direct link, hf CLI and curl.
- Browser
- Download file 880 Bytes
-
https://huggingface.co/vlddshk/SyrzykAI/resolve/main/config.json
- Command line
-
hf download hf://vlddshk/SyrzykAI/config.json
-
curl -L -o config.json https://huggingface.co/vlddshk/SyrzykAI/resolve/main/config.json
880 Bytes
| { | |
| "activation_dropout": 0.0, | |
| "activation_function": "relu", | |
| "architectures": [ | |
| "M2M100ForConditionalGeneration" | |
| ], | |
| "attention_dropout": 0.1, | |
| "bos_token_id": 0, | |
| "d_model": 1024, | |
| "decoder_attention_heads": 16, | |
| "decoder_ffn_dim": 4096, | |
| "decoder_layerdrop": 0, | |
| "decoder_layers": 12, | |
| "decoder_start_token_id": 2, | |
| "dropout": 0.1, | |
| "dtype": "bfloat16", | |
| "encoder_attention_heads": 16, | |
| "encoder_ffn_dim": 4096, | |
| "encoder_layerdrop": 0, | |
| "encoder_layers": 12, | |
| "eos_token_id": 2, | |
| "init_std": 0.02, | |
| "is_encoder_decoder": true, | |
| "max_position_embeddings": 1024, | |
| "model_type": "m2m_100", | |
| "num_hidden_layers": 12, | |
| "pad_token_id": 1, | |
| "scale_embedding": true, | |
| "tie_word_embeddings": false, | |
| "tokenizer_class": "NllbTokenizer", | |
| "transformers_version": "5.3.0", | |
| "use_cache": true, | |
| "vocab_size": 256206 | |
| } | |