Instructions to use Mxode/NanoExperiment-Models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Mxode/NanoExperiment-Models 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/NanoExperiment-Models")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Mxode/NanoExperiment-Models", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "activation_function": "gelu_new", | |
| "architectures": [ | |
| "GPT2LMHeadModel" | |
| ], | |
| "attn_pdrop": 0.1, | |
| "bos_token_id": 50256, | |
| "embd_pdrop": 0.1, | |
| "eos_token_id": 50256, | |
| "hidden_act": "gelu", | |
| "initializer_range": 0.02, | |
| "intermediate_size": 1024, | |
| "layer_norm_epsilon": 1e-05, | |
| "model_type": "gpt2", | |
| "n_embd": 256, | |
| "n_head": 8, | |
| "n_inner": null, | |
| "n_layer": 2, | |
| "n_positions": 1024, | |
| "num_key_value_heads": 8, | |
| "reorder_and_upcast_attn": false, | |
| "resid_pdrop": 0.1, | |
| "scale_attn_by_inverse_layer_idx": false, | |
| "scale_attn_weights": true, | |
| "summary_activation": null, | |
| "summary_first_dropout": 0.1, | |
| "summary_proj_to_labels": true, | |
| "summary_type": "cls_index", | |
| "summary_use_proj": true, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.42.4", | |
| "use_cache": true, | |
| "vocab_size": 2000 | |
| } | |