| { |
| "_name_or_path": "GerbilLab/Gerbil-D-6.7m", |
| "activation_function": "gelu_new", |
| "architectures": [ |
| "GPTJForCausalLM" |
| ], |
| "attn_pdrop": 0.0, |
| "bos_token_id": 50256, |
| "embd_pdrop": 0.0, |
| "eos_token_id": 50256, |
| "initializer_range": 0.02, |
| "layer_norm_epsilon": 1e-05, |
| "model_type": "gptj", |
| "n_embd": 64, |
| "n_head": 4, |
| "n_inner": null, |
| "n_layer": 4, |
| "n_positions": 2048, |
| "resid_pdrop": 0.0, |
| "rotary_dim": 16, |
| "tie_word_embeddings": false, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.29.0.dev0", |
| "use_cache": false, |
| "vocab_size": 50400 |
| } |
|
|