File size: 1,949 Bytes
f664d12 18d22fd f664d12 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 |
{
"_name_or_path": "ayjays132/CustomGPT2Conversational",
"activation_function": "gelu_new",
"architectures": [
"GPT2LMHeadModel"
],
"attn_pdrop": 0.1,
"bos_token_id": 50256,
"config": {
"activation_function": "gelu_new",
"attn_pdrop": 0.1,
"embd_pdrop": 0.1,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"n_ctx": 2048,
"n_embd": 2048,
"n_head": 16,
"n_layer": 24,
"n_positions": 2048,
"n_special": 0,
"resid_pdrop": 0.1,
"summary_activation": null,
"summary_first_dropout": 0.1,
"summary_proj_to_labels": true,
"summary_type": "cls_index",
"summary_use_proj": true
},
"datasets": [
"vicgalle/alpaca-gpt4"
],
"embd_pdrop": 0.1,
"eos_token_id": 50256,
"initializer_range": 0.02,
"language": [
"en"
],
"layer_norm_epsilon": 1e-05,
"library_name": "transformers",
"license": "apache-2.0",
"metrics": [
"perplexity",
"accuracy"
],
"model_type": "gpt2",
"n_embd": 768,
"n_head": 12,
"n_inner": null,
"n_layer": 12,
"n_positions": 1024,
"pipeline_tag": "conversational",
"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,
"tags": [
"conversational"
],
"task_specific_params": {
"conversational": {
"early_stopping": true,
"length_penalty": 1.5,
"max_length": 1024,
"min_length": 20,
"no_repeat_ngram_size": 3,
"num_beams": 5,
"temperature": 0.7,
"top_k": 50,
"top_p": 0.9
}
},
"tokenizer_config": {
"bos_token_id": 50256,
"eos_token_id": 50256,
"n_positions": 2048
},
"torch_dtype": "float32",
"transformers_version": "4.37.2",
"use_cache": true,
"vocab_size": 50257
}
|