Text Generation
Transformers
Safetensors
Czech
mpt
custom_code
text-generation-inference
Inference Endpoints
csmpt7b / config.json
mfajcik's picture
code upload
27ccd05 verified
raw
history blame
1.68 kB
{
"architectures": [
"MPTForCausalLM"
],
"attn_config": {
"alibi": true,
"alibi_bias_max": 8,
"attn_impl": "flash",
"attn_pdrop": 0,
"attn_type": "multihead_attention",
"attn_uses_sequence_id": false,
"clip_qkv": null,
"prefix_lm": false,
"qk_gn": false,
"qk_ln": false,
"rope": false,
"rope_dail_config": {
"pos_idx_in_fp32": true,
"type": "original",
"xpos_scale_base": 512
},
"rope_hf_config": {
"factor": 1.0,
"type": "no_scaling"
},
"rope_impl": "dail",
"rope_theta": 10000,
"sliding_window_size": -1,
"softmax_scale": null
},
"auto_map": {
"AutoConfig": "configuration_mpt.MPTConfig",
"AutoModelForCausalLM": "modeling_mpt.MPTForCausalLM"
},
"d_model": 4096,
"emb_pdrop": 0,
"embedding_fraction": 1.0,
"eos_token_id": 64001,
"expansion_ratio": 4,
"fc_type": "torch",
"ffn_config": {
"fc_type": "torch",
"ffn_type": "mptmlp"
},
"init_config": {
"emb_init_std": null,
"emb_init_uniform_lim": null,
"fan_mode": "fan_in",
"init_div_is_residual": true,
"init_gain": 0,
"init_nonlinearity": "relu",
"init_std": 0.02,
"name": "kaiming_normal_",
"verbose": 0
},
"init_device": "cpu",
"learned_pos_emb": false,
"logit_scale": null,
"max_seq_len": 2048,
"model_type": "mpt",
"n_heads": 32,
"n_layers": 32,
"no_bias": true,
"norm_type": "low_precision_layernorm",
"resid_pdrop": 0,
"tokenizer_name": "EleutherAI/gpt-neox-20b",
"torch_dtype": "float32",
"transformers_version": "4.37.0.dev0",
"use_cache": false,
"use_pad_tok_in_ffn": true,
"vocab_size": 64002
}