| { |
| "architectures": [ |
| "DCPythia" |
| ], |
| "auto_map": { |
| "AutoConfig": "configuration_dcpythia.DCPythiaConfig", |
| "AutoModelForCausalLM": "modeling_dcpythia.DCPythia" |
| }, |
| "block_size": 2048, |
| "bos_token_id": 0, |
| "dim": 4096, |
| "eos_token_id": 0, |
| "head_dim": 128, |
| "intermediate_size": 16384, |
| "is_training": false, |
| "model_type": "dcpythia", |
| "n_head": 32, |
| "n_layer": 32, |
| "n_local_heads": 32, |
| "norm_eps": 1e-05, |
| "q_chunk_size": 128, |
| "query_wise": false, |
| "rope_base": 10000, |
| "rotary_pct": 0.25, |
| "tie_word_embeddings": false, |
| "torch_dtype": "float16", |
| "transformers_version": "4.33.2", |
| "use_dcmha": true, |
| "use_gradient_checkpointing": false, |
| "use_linear_bias": true, |
| "use_parallel_residual": true, |
| "use_qk_norm": true, |
| "vocab_size": 50257, |
| "window_size": 256, |
| "window_type": null |
| } |
|
|
