Download model_config.json from LSM571/LARA-Gen: direct link, hf CLI and curl.
- Browser
- Download file 1.51 kB
-
https://huggingface.co/LSM571/LARA-Gen/resolve/main/model_config.json
- Command line
-
hf download hf://LSM571/LARA-Gen/model_config.json
-
curl -L -o model_config.json https://huggingface.co/LSM571/LARA-Gen/resolve/main/model_config.json
1.51 kB
| { | |
| "transformer_lm": { | |
| "dim": 1536, | |
| "num_heads": 24, | |
| "num_layers": 48, | |
| "hidden_scale": 4, | |
| "n_q": 4, | |
| "card": 2048, | |
| "dropout": 0.0, | |
| "emb_lr": null, | |
| "activation": "gelu", | |
| "norm_first": true, | |
| "bias_ff": false, | |
| "bias_attn": false, | |
| "bias_proj": false, | |
| "past_context": null, | |
| "causal": true, | |
| "custom": false, | |
| "memory_efficient": true, | |
| "attention_as_float32": false, | |
| "layer_scale": null, | |
| "positional_embedding": "sin", | |
| "xpos": false, | |
| "checkpointing": "torch", | |
| "weight_init": "gaussian", | |
| "depthwise_init": "current", | |
| "zero_bias_init": true, | |
| "norm": "layer_norm", | |
| "cross_attention": false, | |
| "qk_layer_norm": false, | |
| "qk_layer_norm_cross": false, | |
| "attention_dropout": null, | |
| "kv_repeat": 1, | |
| "two_step_cfg": false | |
| }, | |
| "conditioners": { | |
| "description": { | |
| "model": "t5", | |
| "t5": { | |
| "name": "t5-base", | |
| "finetune": false, | |
| "word_dropout": 0.3, | |
| "normalize_text": false | |
| } | |
| } | |
| }, | |
| "fuser": { | |
| "cross_attention_pos_emb": false, | |
| "cross_attention_pos_emb_scale": 1, | |
| "sum": [], | |
| "prepend": [], | |
| "cross": [ | |
| "description" | |
| ], | |
| "input_interpolate": [] | |
| }, | |
| "codebooks_pattern": { | |
| "delay": { | |
| "delays": [ | |
| 0, | |
| 1, | |
| 2, | |
| 3 | |
| ], | |
| "flatten_first": 0, | |
| "empty_initial": 0 | |
| } | |
| }, | |
| "classifier_free_guidance": { | |
| "training_dropout": 0.3, | |
| "inference_coef": 3.0 | |
| } | |
| } | |