| { |
| "activation_function": "gelu_new", |
| "architectures": [ |
| "GPTJForCausalLM" |
| ], |
| "attn_pdrop": 0.0, |
| "bos_token_id": 1, |
| "embd_pdrop": 0.0, |
| "eos_token_id": 50256, |
| "initializer_range": 0.02, |
| "layer_norm_epsilon": 1e-05, |
| "model_type": "gptj", |
| "n_embd": 4096, |
| "n_head": 16, |
| "n_inner": null, |
| "n_layer": 33, |
| "n_positions": 2048, |
| "resid_pdrop": 0.0, |
| "rotary_dim": 64, |
| "scale_attn_weights": true, |
| "tie_word_embeddings": false, |
| "tokenizer_class": "CodeGenTokenizer", |
| "torch_dtype": "float32", |
| "transformers_version": "4.25.1", |
| "use_cache": true, |
| "vocab_size": 50295 |
| } |
|
|