ngme-babylm-100M-v2 / config.json
PatrickHaller's picture
Upload NGMEForCausalLM
e0609f8
raw
history blame
No virus
862 Bytes
{
"_name_or_path": "/glusterfs/dfs-gfs-dist/hallepat/ngme",
"architectures": [
"NGMEForCausalLM"
],
"auto_map": {
"AutoConfig": "configuration_ngme.NGMEConfig",
"AutoModelForCausalLM": "modeling_ngme.NGMEForCausalLM"
},
"bos_token_id": 1,
"eos_token_id": 0,
"hidden_act": "silu",
"hidden_size": 768,
"initializer_range": 0.02,
"intermediate_size": 3072,
"max_position_embeddings": 2048,
"model_type": "ngme",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"num_key_value_heads": 12,
"pad_token_id": 0,
"pretraining_tp": 1,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.26.1",
"unk_idx": 1,
"unk_token_id": 1,
"use_cache": true,
"use_flash_attn": false,
"use_small_embedding": false,
"vocab_size": 15237
}