Instructions to use bumblebee-testing/tiny-random-GPT2Model-sharded with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bumblebee-testing/tiny-random-GPT2Model-sharded with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="bumblebee-testing/tiny-random-GPT2Model-sharded")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("bumblebee-testing/tiny-random-GPT2Model-sharded") model = AutoModel.from_pretrained("bumblebee-testing/tiny-random-GPT2Model-sharded", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "metadata": { | |
| "total_size": 332644 | |
| }, | |
| "weight_map": { | |
| "h.0.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin", | |
| "h.0.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin", | |
| "h.0.attn.c_proj.bias": "pytorch_model-00002-of-00003.bin", | |
| "h.0.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "h.0.ln_1.bias": "pytorch_model-00002-of-00003.bin", | |
| "h.0.ln_1.weight": "pytorch_model-00002-of-00003.bin", | |
| "h.0.ln_2.bias": "pytorch_model-00002-of-00003.bin", | |
| "h.0.ln_2.weight": "pytorch_model-00002-of-00003.bin", | |
| "h.0.mlp.c_fc.bias": "pytorch_model-00002-of-00003.bin", | |
| "h.0.mlp.c_fc.weight": "pytorch_model-00002-of-00003.bin", | |
| "h.0.mlp.c_proj.bias": "pytorch_model-00002-of-00003.bin", | |
| "h.0.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "h.1.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin", | |
| "h.1.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin", | |
| "h.1.attn.c_proj.bias": "pytorch_model-00002-of-00003.bin", | |
| "h.1.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "h.1.ln_1.bias": "pytorch_model-00002-of-00003.bin", | |
| "h.1.ln_1.weight": "pytorch_model-00002-of-00003.bin", | |
| "h.1.ln_2.bias": "pytorch_model-00002-of-00003.bin", | |
| "h.1.ln_2.weight": "pytorch_model-00002-of-00003.bin", | |
| "h.1.mlp.c_fc.bias": "pytorch_model-00002-of-00003.bin", | |
| "h.1.mlp.c_fc.weight": "pytorch_model-00002-of-00003.bin", | |
| "h.1.mlp.c_proj.bias": "pytorch_model-00002-of-00003.bin", | |
| "h.1.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "h.2.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin", | |
| "h.2.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin", | |
| "h.2.attn.c_proj.bias": "pytorch_model-00002-of-00003.bin", | |
| "h.2.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "h.2.ln_1.bias": "pytorch_model-00002-of-00003.bin", | |
| "h.2.ln_1.weight": "pytorch_model-00002-of-00003.bin", | |
| "h.2.ln_2.bias": "pytorch_model-00002-of-00003.bin", | |
| "h.2.ln_2.weight": "pytorch_model-00002-of-00003.bin", | |
| "h.2.mlp.c_fc.bias": "pytorch_model-00002-of-00003.bin", | |
| "h.2.mlp.c_fc.weight": "pytorch_model-00002-of-00003.bin", | |
| "h.2.mlp.c_proj.bias": "pytorch_model-00002-of-00003.bin", | |
| "h.2.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin", | |
| "h.3.attn.c_attn.bias": "pytorch_model-00003-of-00003.bin", | |
| "h.3.attn.c_attn.weight": "pytorch_model-00003-of-00003.bin", | |
| "h.3.attn.c_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "h.3.attn.c_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "h.3.ln_1.bias": "pytorch_model-00002-of-00003.bin", | |
| "h.3.ln_1.weight": "pytorch_model-00002-of-00003.bin", | |
| "h.3.ln_2.bias": "pytorch_model-00003-of-00003.bin", | |
| "h.3.ln_2.weight": "pytorch_model-00003-of-00003.bin", | |
| "h.3.mlp.c_fc.bias": "pytorch_model-00003-of-00003.bin", | |
| "h.3.mlp.c_fc.weight": "pytorch_model-00003-of-00003.bin", | |
| "h.3.mlp.c_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "h.3.mlp.c_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "h.4.attn.c_attn.bias": "pytorch_model-00003-of-00003.bin", | |
| "h.4.attn.c_attn.weight": "pytorch_model-00003-of-00003.bin", | |
| "h.4.attn.c_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "h.4.attn.c_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "h.4.ln_1.bias": "pytorch_model-00003-of-00003.bin", | |
| "h.4.ln_1.weight": "pytorch_model-00003-of-00003.bin", | |
| "h.4.ln_2.bias": "pytorch_model-00003-of-00003.bin", | |
| "h.4.ln_2.weight": "pytorch_model-00003-of-00003.bin", | |
| "h.4.mlp.c_fc.bias": "pytorch_model-00003-of-00003.bin", | |
| "h.4.mlp.c_fc.weight": "pytorch_model-00003-of-00003.bin", | |
| "h.4.mlp.c_proj.bias": "pytorch_model-00003-of-00003.bin", | |
| "h.4.mlp.c_proj.weight": "pytorch_model-00003-of-00003.bin", | |
| "ln_f.bias": "pytorch_model-00003-of-00003.bin", | |
| "ln_f.weight": "pytorch_model-00003-of-00003.bin", | |
| "wpe.weight": "pytorch_model-00002-of-00003.bin", | |
| "wte.weight": "pytorch_model-00001-of-00003.bin" | |
| } | |
| } | |