Jiayi-Pan commited on
Commit
0bcd0fd
·
verified ·
1 Parent(s): e0d0d21

Upload folder using huggingface_hub

Browse files
Files changed (2) hide show
  1. config.json +1 -37
  2. params.msgpack +1 -1
config.json CHANGED
@@ -1,37 +1 @@
1
- {
2
- "_name_or_path": "./model",
3
- "activation_function": "gelu_new",
4
- "architectures": [
5
- "GPT2LMHeadModel"
6
- ],
7
- "attn_pdrop": 0.0,
8
- "bos_token_id": 50256,
9
- "embd_pdrop": 0.0,
10
- "eos_token_id": 50256,
11
- "initializer_range": 0.02,
12
- "layer_norm_epsilon": 1e-05,
13
- "model_type": "gpt2",
14
- "n_ctx": 4096,
15
- "n_embd": 1024,
16
- "n_head": 16,
17
- "n_inner": 4096,
18
- "n_layer": 16,
19
- "n_positions": 4096,
20
- "pad_token_id": 50255,
21
- "remat_attention": "",
22
- "remat_block": "nothing_saveable",
23
- "remat_mlp": "",
24
- "reorder_and_upcast_attn": false,
25
- "resid_pdrop": 0.0,
26
- "scale_attn_by_inverse_layer_idx": false,
27
- "scale_attn_weights": true,
28
- "summary_activation": null,
29
- "summary_first_dropout": 0.1,
30
- "summary_proj_to_labels": true,
31
- "summary_type": "cls_index",
32
- "summary_use_proj": true,
33
- "torch_dtype": "float32",
34
- "transformers_version": "4.47.1",
35
- "use_cache": true,
36
- "vocab_size": 50258
37
- }
 
1
+ {"vocab_size": 50258, "n_positions": 4096, "n_embd": 1024, "n_layer": 16, "n_head": 16, "n_inner": 4096, "activation_function": "gelu_new", "resid_pdrop": 0.0, "embd_pdrop": 0.0, "attn_pdrop": 0.0, "layer_norm_epsilon": 1e-05, "initializer_range": 0.02, "summary_type": "cls_index", "summary_use_proj": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "scale_attn_weights": true, "use_cache": true, "scale_attn_by_inverse_layer_idx": false, "reorder_and_upcast_attn": false, "remat_block": "nothing_saveable", "remat_attention": "", "remat_mlp": "", "bos_token_id": 50256, "eos_token_id": 50256, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": "bfloat16", "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": true, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": null, "architectures": ["GPT2LMHeadModel"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "pad_token_id": 50255, "sep_token_id": null, "decoder_start_token_id": null, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.47.1", "model_type": "gpt2", "n_ctx": 4096}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
params.msgpack CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:57f48d7a46cb8371bcfc16c900bb3468d52b280fcdaf58c8d7af94fb68ee20c5
3
  size 514412035
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ab94ac074e513c9e485b9129511a28921ccc46fa688da887b83813d8d96c435
3
  size 514412035