| { |
| "_name_or_path": "hugohrban/progen2-base", |
| "activation_function": "gelu_new", |
| "architectures": [ |
| "ProGenForCausalLM" |
| ], |
| "attn_pdrop": 0.0, |
| "auto_map": { |
| "AutoConfig": "configuration_progen.ProGenConfig", |
| "AutoModelForCausalLM": "modeling_progen.ProGenForCausalLM" |
| }, |
| "bos_token_id": 1, |
| "embd_pdrop": 0.0, |
| "embed_dim": 1536, |
| "eos_token_id": 2, |
| "gradient_checkpointing": false, |
| "initializer_range": 0.02, |
| "layer_norm_epsilon": 1e-05, |
| "model_type": "progen", |
| "n_head": 16, |
| "n_inner": null, |
| "n_layer": 27, |
| "n_positions": 2048, |
| "resid_pdrop": 0.0, |
| "rotary_dim": 48, |
| "scale_attn_weights": true, |
| "summary_activation": null, |
| "summary_first_dropout": 0.1, |
| "summary_proj_to_labels": true, |
| "summary_type": "cls_index", |
| "summary_use_proj": true, |
| "task_specific_params": { |
| "text-generation": { |
| "do_sample": true, |
| "max_length": 50, |
| "temperature": 1.0 |
| } |
| }, |
| "tokenizer_class": "GPT2Tokenizer", |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.40.0", |
| "use_cache": true, |
| "vocab_size": 32, |
| "vocab_size_emb": 32, |
| "vocab_size_lm_head": 32, |
| "model_file": "progen2_mlx.py", |
| "dtype": "bfloat16", |
| "pad_token_id": 0 |
| } |
|
|
