Text Generation
Transformers
PyTorch
Safetensors
gpt2
conversational
text-generation-inference
Inference Endpoints
gpt-sw3-126m-instruct / config.json
Ekgren's picture
Update config.json
90a5293 verified
raw
history blame
983 Bytes
{
"_name_or_path": "/home/ariel/gpt_sw3/instruct_new/126m/hf/",
"activation_function": "gelu",
"apply_query_key_layer_scaling": true,
"architectures": [
"GPT2LMHeadModel"
],
"attn_pdrop": 0.1,
"bos_token_id": 2,
"embd_pdrop": 0.1,
"eos_token_id": 3,
"initializer_range": 0.023,
"layer_norm_epsilon": 1e-05,
"model_type": "gpt2",
"n_embd": 768,
"n_head": 12,
"n_inner": 3072,
"n_layer": 12,
"n_positions": 2048,
"normalize_attention_scores": true,
"pad_token_id": 0,
"reorder_and_upcast_attn": false,
"resid_pdrop": 0.1,
"scale_attn_by_inverse_layer_idx": false,
"scale_attn_weights": true,
"summary_activation": null,
"summary_first_dropout": 0.1,
"summary_proj_to_labels": true,
"summary_type": "cls_index",
"summary_use_proj": true,
"tokenizer_class": "GPTSw3Tokenizer",
"torch_dtype": "float32",
"transformers_version": "4.22.1",
"use_cache": true,
"vocab_size": 64000,
"max_length": 2048,
"n_ctx": 2048
}