50 lines
1.1 KiB
JSON
50 lines
1.1 KiB
JSON
{
|
|
"architectures": [
|
|
"MptForCausalLM"
|
|
],
|
|
"attn_config": {
|
|
"alibi": true,
|
|
"alibi_bias_max": 8,
|
|
"attn_impl": "torch",
|
|
"attn_pdrop": 0,
|
|
"attn_type": "multihead_attention",
|
|
"attn_uses_sequence_id": false,
|
|
"clip_qkv": null,
|
|
"prefix_lm": false,
|
|
"qk_ln": false,
|
|
"softmax_scale": null
|
|
},
|
|
"d_model": 2048,
|
|
"emb_pdrop": 0,
|
|
"embedding_fraction": 1.0,
|
|
"expansion_ratio": 4,
|
|
"init_config": {
|
|
"emb_init_std": null,
|
|
"emb_init_uniform_lim": null,
|
|
"fan_mode": "fan_in",
|
|
"init_div_is_residual": true,
|
|
"init_gain": 0.0,
|
|
"init_nonlinearity": "relu",
|
|
"init_std": null,
|
|
"name": "kaiming_normal_",
|
|
"verbose": 0
|
|
},
|
|
"init_device": "cpu",
|
|
"initializer_range": 0.02,
|
|
"layer_norm_epsilon": 1e-05,
|
|
"learned_pos_emb": true,
|
|
"logit_scale": null,
|
|
"max_seq_len": 8192,
|
|
"model_type": "mpt",
|
|
"n_heads": 16,
|
|
"n_layers": 24,
|
|
"no_bias": true,
|
|
"norm_type": "low_precision_layernorm",
|
|
"resid_pdrop": 0,
|
|
"torch_dtype": "float32",
|
|
"transformers_version": "4.33.0.dev0",
|
|
"use_cache": false,
|
|
"verbose": 0,
|
|
"vocab_size": 50432
|
|
}
|