MikeMpapa commited on
Commit
a2e2197
1 Parent(s): 13013a6

Upload folder using huggingface_hub

Browse files
config.json CHANGED
@@ -1,36 +1 @@
1
- {
2
- "_name_or_path": "/home/ec2-user/SageMaker/levanter/checkpoints/hf_202407_midi_test_files",
3
- "activation_function": "gelu_new",
4
- "architectures": [
5
- "GPT2Model"
6
- ],
7
- "attn_pdrop": 0.0,
8
- "begin_suppress_tokens": [
9
- 50256
10
- ],
11
- "bos_token_id": 50256,
12
- "decoder_start_token_id": 50256,
13
- "embd_pdrop": 0.0,
14
- "eos_token_id": 50256,
15
- "initializer_range": 0.02,
16
- "layer_norm_epsilon": 1e-05,
17
- "model_type": "gpt2",
18
- "n_embd": 1024,
19
- "n_head": 16,
20
- "n_inner": null,
21
- "n_layer": 24,
22
- "n_positions": 1024,
23
- "reorder_and_upcast_attn": false,
24
- "resid_pdrop": 0.1,
25
- "scale_attn_by_inverse_layer_idx": true,
26
- "scale_attn_weights": true,
27
- "summary_activation": null,
28
- "summary_first_dropout": 0.1,
29
- "summary_proj_to_labels": true,
30
- "summary_type": "cls_index",
31
- "summary_use_proj": true,
32
- "torch_dtype": "float32",
33
- "transformers_version": "4.42.4",
34
- "use_cache": true,
35
- "vocab_size": 55028
36
- }
 
1
+ {"vocab_size": 55028, "n_positions": 1024, "n_embd": 1024, "n_layer": 24, "n_head": 16, "n_inner": null, "activation_function": "gelu_new", "resid_pdrop": 0.1, "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": true, "reorder_and_upcast_attn": false, "bos_token_id": 50256, "eos_token_id": 50256, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "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": [50256], "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": null, "sep_token_id": null, "decoder_start_token_id": 50256, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "transformers_version": "4.43.1", "model_type": "gpt2"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ffff8e0380ff50d9f293b75704d54ed525e3e84e06c03e8e1b2fa6dfe070465
3
  size 1438861392
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:233c7d37436ffe8210e8a173a54415fac806f653580ac99daaae7883e55b3b17
3
  size 1438861392
special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "unk_token": "<|endoftext|>"
5
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ }
12
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": true,
15
+ "eos_token": "<|endoftext|>",
16
+ "model_max_length": 1024,
17
+ "tokenizer_class": "GPT2Tokenizer",
18
+ "unk_token": "<|endoftext|>"
19
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff