| { | |
| "activation_function": "gelu", | |
| "architectures": [ | |
| "NanoGPTLMHeadModel" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "modeling_nanogpt.NanoGPTConfig", | |
| "AutoModelForCausalLM": "modeling_nanogpt.NanoGPTLMHeadModel" | |
| }, | |
| "attn_pdrop": 0.1, | |
| "bos_token_id": 50256, | |
| "embd_pdrop": 0.1, | |
| "eos_token_id": 50256, | |
| "initializer_range": 0.02, | |
| "layer_norm_epsilon": 1e-05, | |
| "model_type": "nanogpt", | |
| "n_embd": 384, | |
| "n_head": 8, | |
| "n_inner": 1536, | |
| "n_layer": 8, | |
| "n_positions": 512, | |
| "resid_pdrop": 0.1, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.51.3", | |
| "vocab_size": 50257 | |
| } | |