| { |
| "_name_or_path": "tiiuae/falcon-rw-1b", |
| "alibi": true, |
| "apply_residual_connection_post_layernorm": false, |
| "architectures": [ |
| "RWForCausalLM" |
| ], |
| "attention_dropout": 0.0, |
| "auto_map": { |
| "AutoConfig": "tiiuae/falcon-rw-1b--configuration_RW.RWConfig", |
| "AutoModelForCausalLM": "tiiuae/falcon-rw-1b--modelling_RW.RWForCausalLM" |
| }, |
| "bias": true, |
| "bos_token_id": 1, |
| "eos_token_id": 2, |
| "hidden_dropout": 0.0, |
| "hidden_size": 2048, |
| "initializer_range": 0.02, |
| "layer_norm_epsilon": 1e-05, |
| "model_type": "RefinedWebModel", |
| "multi_query": false, |
| "n_head": 32, |
| "n_layer": 24, |
| "parallel_attn": false, |
| "torch_dtype": "float32", |
| "transformers_version": "4.31.0.dev0", |
| "use_cache": true, |
| "vocab_size": 50304 |
| } |
|
|