Translation
Transformers
Safetensors
English
Chinese
llama
text-generation
text-generation-inference
Instructions to use Mxode/NanoTranslator-XS with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Mxode/NanoTranslator-XS 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="Mxode/NanoTranslator-XS")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Mxode/NanoTranslator-XS") model = AutoModelForCausalLM.from_pretrained("Mxode/NanoTranslator-XS") - Notebooks
- Google Colab
- Kaggle
| { | |
| "_name_or_path": "Mxode/NanoTranslator-S", | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "hidden_act": "silu", | |
| "hidden_size": 96, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 512, | |
| "max_position_embeddings": 2048, | |
| "mlp_bias": false, | |
| "model_type": "llama", | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 12, | |
| "num_key_value_heads": 4, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 10000.0, | |
| "tie_word_embeddings": true, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.42.4", | |
| "use_cache": true, | |
| "vocab_size": 2000 | |
| } | |