Delete SilkomePretrainedGPT
Browse files
SilkomePretrainedGPT/config.json
DELETED
|
@@ -1,29 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_name_or_path": "mjbuehler/GPTNeoLAMM_medium",
|
| 3 |
-
"architectures": [
|
| 4 |
-
"GPTNeoXForCausalLM"
|
| 5 |
-
],
|
| 6 |
-
"attention_dropout": 0.0,
|
| 7 |
-
"bos_token_id": 0,
|
| 8 |
-
"classifier_dropout": 0.1,
|
| 9 |
-
"eos_token_id": 2,
|
| 10 |
-
"hidden_act": "gelu",
|
| 11 |
-
"hidden_dropout": 0.0,
|
| 12 |
-
"hidden_size": 1024,
|
| 13 |
-
"initializer_range": 0.02,
|
| 14 |
-
"intermediate_size": 4096,
|
| 15 |
-
"layer_norm_eps": 1e-05,
|
| 16 |
-
"max_position_embeddings": 2048,
|
| 17 |
-
"model_type": "gpt_neox",
|
| 18 |
-
"num_attention_heads": 8,
|
| 19 |
-
"num_hidden_layers": 12,
|
| 20 |
-
"rope_scaling": null,
|
| 21 |
-
"rotary_emb_base": 10000,
|
| 22 |
-
"rotary_pct": 0.25,
|
| 23 |
-
"tie_word_embeddings": false,
|
| 24 |
-
"torch_dtype": "float32",
|
| 25 |
-
"transformers_version": "4.35.2",
|
| 26 |
-
"use_cache": false,
|
| 27 |
-
"use_parallel_residual": true,
|
| 28 |
-
"vocab_size": 50000
|
| 29 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
SilkomePretrainedGPT/generation_config.json
DELETED
|
@@ -1,6 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_from_model_config": true,
|
| 3 |
-
"bos_token_id": 0,
|
| 4 |
-
"eos_token_id": 2,
|
| 5 |
-
"transformers_version": "4.35.2"
|
| 6 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
SilkomePretrainedGPT/model.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:65c994b6adbf65f5219d453455afe638808d67b97b20b6ba0b46e47f8b332d06
|
| 3 |
-
size 1014244040
|
|
|
|
|
|
|
|
|
|
|
|
SilkomePretrainedGPT/special_tokens_map.json
DELETED
|
@@ -1,4 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"eos_token": "</s>",
|
| 3 |
-
"pad_token": "</s>"
|
| 4 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
SilkomePretrainedGPT/tokenizer.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
SilkomePretrainedGPT/tokenizer_config.json
DELETED
|
@@ -1,54 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"added_tokens_decoder": {
|
| 3 |
-
"0": {
|
| 4 |
-
"content": "<s>",
|
| 5 |
-
"lstrip": false,
|
| 6 |
-
"normalized": false,
|
| 7 |
-
"rstrip": false,
|
| 8 |
-
"single_word": false,
|
| 9 |
-
"special": true
|
| 10 |
-
},
|
| 11 |
-
"1": {
|
| 12 |
-
"content": "<pad>",
|
| 13 |
-
"lstrip": false,
|
| 14 |
-
"normalized": false,
|
| 15 |
-
"rstrip": false,
|
| 16 |
-
"single_word": false,
|
| 17 |
-
"special": true
|
| 18 |
-
},
|
| 19 |
-
"2": {
|
| 20 |
-
"content": "</s>",
|
| 21 |
-
"lstrip": false,
|
| 22 |
-
"normalized": false,
|
| 23 |
-
"rstrip": false,
|
| 24 |
-
"single_word": false,
|
| 25 |
-
"special": true
|
| 26 |
-
},
|
| 27 |
-
"3": {
|
| 28 |
-
"content": "<unk>",
|
| 29 |
-
"lstrip": false,
|
| 30 |
-
"normalized": false,
|
| 31 |
-
"rstrip": false,
|
| 32 |
-
"single_word": false,
|
| 33 |
-
"special": true
|
| 34 |
-
},
|
| 35 |
-
"4": {
|
| 36 |
-
"content": "<mask>",
|
| 37 |
-
"lstrip": false,
|
| 38 |
-
"normalized": false,
|
| 39 |
-
"rstrip": false,
|
| 40 |
-
"single_word": false,
|
| 41 |
-
"special": true
|
| 42 |
-
}
|
| 43 |
-
},
|
| 44 |
-
"clean_up_tokenization_spaces": true,
|
| 45 |
-
"eos_token": "</s>",
|
| 46 |
-
"max_length": null,
|
| 47 |
-
"model_max_length": 1000000000000000019884624838656,
|
| 48 |
-
"pad_to_multiple_of": null,
|
| 49 |
-
"pad_token": "</s>",
|
| 50 |
-
"pad_token_type_id": 0,
|
| 51 |
-
"padding": "max_length",
|
| 52 |
-
"padding_side": "right",
|
| 53 |
-
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 54 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|