Translation
Transformers
Safetensors
Akkadian
English
umt5
text2text-generation
multilingual
ancient-languages
akkadian
Eval Results (legacy)
Instructions to use Thalesian/AKK_300m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Thalesian/AKK_300m 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="Thalesian/AKK_300m")# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("Thalesian/AKK_300m") model = AutoModelForMultimodalLM.from_pretrained("Thalesian/AKK_300m") - Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": [ | |
| "UMT5ForConditionalGeneration" | |
| ], | |
| "bos_token_id": 2, | |
| "classifier_dropout": 0.0, | |
| "d_ff": 1024, | |
| "d_kv": 64, | |
| "d_model": 512, | |
| "decoder_start_token_id": 0, | |
| "dense_act_fn": "gelu_new", | |
| "dropout_rate": 0.1, | |
| "dtype": "float32", | |
| "eos_token_id": 1, | |
| "feed_forward_proj": "gated-gelu", | |
| "initializer_factor": 1.0, | |
| "is_encoder_decoder": true, | |
| "is_gated_act": true, | |
| "layer_norm_epsilon": 1e-06, | |
| "max_new_tokens": 64, | |
| "model_type": "umt5", | |
| "num_decoder_layers": 8, | |
| "num_heads": 6, | |
| "num_layers": 8, | |
| "pad_token_id": 0, | |
| "relative_attention_max_distance": 128, | |
| "relative_attention_num_buckets": 32, | |
| "scalable_attention": true, | |
| "tie_word_embeddings": false, | |
| "tokenizer_class": "T5Tokenizer", | |
| "transformers_version": "4.56.1", | |
| "use_cache": true, | |
| "vocab_size": 257090 | |
| } | |