| { |
| "architectures": [ |
| "MptForCausalLM" |
| ], |
| "attn_config": { |
| "attn_impl": "torch" |
| }, |
| "auto_map": { |
| "AutoConfig": "configuration_mpt.MPTConfig", |
| "AutoModelForCausalLM": "modeling_mpt.MPTForCausalLM" |
| }, |
| "d_model": 32, |
| "emb_pdrop": 0.0, |
| "embedding_fraction": 1.0, |
| "expansion_ratio": 4, |
| "init_device": "cpu", |
| "initializer_range": 0.02, |
| "layer_norm_epsilon": 1e-05, |
| "learned_pos_emb": true, |
| "logit_scale": null, |
| "max_seq_len": 2048, |
| "model_type": "mpt", |
| "n_heads": 4, |
| "n_layers": 5, |
| "no_bias": true, |
| "norm_type": "low_precision_layernorm", |
| "num_key_value_heads": 2, |
| "resid_pdrop": 0.0, |
| "torch_dtype": "float32", |
| "transformers_version": "4.32.0.dev0", |
| "use_cache": false, |
| "verbose": 0, |
| "vocab_size": 1024 |
| } |
|
|
