| { | |
| "architectures": [ | |
| "LilleForCausalLM" | |
| ], | |
| "block_size": 512, | |
| "dropout": 0.0, | |
| "layer_norm_eps": 1e-05, | |
| "model_type": "lille-130m", | |
| "n_embd": 640, | |
| "n_head": 10, | |
| "n_kv_heads": 2, | |
| "n_layer": 24, | |
| "rope_theta": 10000.0, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.53.3", | |
| "vocab_size": 32768 | |
| } | |