Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- resemble_to_drop_frequency_3591/checkpoint-40000/config.json +31 -0
- resemble_to_drop_frequency_3591/checkpoint-40000/generation_config.json +6 -0
- resemble_to_drop_frequency_3591/checkpoint-40000/merges.txt +0 -0
- resemble_to_drop_frequency_3591/checkpoint-40000/model.safetensors +3 -0
- resemble_to_drop_frequency_3591/checkpoint-40000/optimizer.pt +3 -0
- resemble_to_drop_frequency_3591/checkpoint-40000/rng_state.pth +3 -0
- resemble_to_drop_frequency_3591/checkpoint-40000/scaler.pt +3 -0
- resemble_to_drop_frequency_3591/checkpoint-40000/scheduler.pt +3 -0
- resemble_to_drop_frequency_3591/checkpoint-40000/special_tokens_map.json +5 -0
- resemble_to_drop_frequency_3591/checkpoint-40000/tokenizer.json +0 -0
- resemble_to_drop_frequency_3591/checkpoint-40000/tokenizer_config.json +20 -0
- resemble_to_drop_frequency_3591/checkpoint-40000/trainer_state.json +0 -0
- resemble_to_drop_frequency_3591/checkpoint-40000/training_args.bin +3 -0
- resemble_to_drop_frequency_3591/checkpoint-40000/vocab.json +0 -0
- resemble_to_drop_frequency_3591/checkpoint-50000/config.json +31 -0
- resemble_to_drop_frequency_3591/checkpoint-50000/generation_config.json +6 -0
- resemble_to_drop_frequency_3591/checkpoint-50000/merges.txt +0 -0
- resemble_to_drop_frequency_3591/checkpoint-50000/model.safetensors +3 -0
- resemble_to_drop_frequency_3591/checkpoint-50000/optimizer.pt +3 -0
- resemble_to_drop_frequency_3591/checkpoint-50000/rng_state.pth +3 -0
- resemble_to_drop_frequency_3591/checkpoint-50000/scaler.pt +3 -0
- resemble_to_drop_frequency_3591/checkpoint-50000/scheduler.pt +3 -0
- resemble_to_drop_frequency_3591/checkpoint-50000/special_tokens_map.json +5 -0
- resemble_to_drop_frequency_3591/checkpoint-50000/tokenizer.json +0 -0
- resemble_to_drop_frequency_3591/checkpoint-50000/tokenizer_config.json +20 -0
- resemble_to_drop_frequency_3591/checkpoint-50000/trainer_state.json +0 -0
- resemble_to_drop_frequency_3591/checkpoint-50000/training_args.bin +3 -0
- resemble_to_drop_frequency_3591/checkpoint-50000/vocab.json +0 -0
- resemble_to_drop_frequency_3591/checkpoint-60000/config.json +31 -0
- resemble_to_drop_frequency_3591/checkpoint-60000/generation_config.json +6 -0
- resemble_to_drop_frequency_3591/checkpoint-60000/merges.txt +0 -0
- resemble_to_drop_frequency_3591/checkpoint-60000/model.safetensors +3 -0
- resemble_to_drop_frequency_3591/checkpoint-60000/optimizer.pt +3 -0
- resemble_to_drop_frequency_3591/checkpoint-60000/rng_state.pth +3 -0
- resemble_to_drop_frequency_3591/checkpoint-60000/scaler.pt +3 -0
- resemble_to_drop_frequency_3591/checkpoint-60000/scheduler.pt +3 -0
- resemble_to_drop_frequency_3591/checkpoint-60000/special_tokens_map.json +5 -0
- resemble_to_drop_frequency_3591/checkpoint-60000/tokenizer.json +0 -0
- resemble_to_drop_frequency_3591/checkpoint-60000/tokenizer_config.json +20 -0
- resemble_to_drop_frequency_3591/checkpoint-60000/trainer_state.json +0 -0
- resemble_to_drop_frequency_3591/checkpoint-60000/training_args.bin +3 -0
- resemble_to_drop_frequency_3591/checkpoint-60000/vocab.json +0 -0
- resemble_to_drop_frequency_3591/checkpoint-70000/config.json +31 -0
- resemble_to_drop_frequency_3591/checkpoint-70000/generation_config.json +6 -0
- resemble_to_drop_frequency_3591/checkpoint-70000/merges.txt +0 -0
- resemble_to_drop_frequency_3591/checkpoint-70000/model.safetensors +3 -0
- resemble_to_drop_frequency_3591/checkpoint-70000/optimizer.pt +3 -0
- resemble_to_drop_frequency_3591/checkpoint-70000/rng_state.pth +3 -0
- resemble_to_drop_frequency_3591/checkpoint-70000/scaler.pt +3 -0
- resemble_to_drop_frequency_3591/checkpoint-70000/scheduler.pt +3 -0
resemble_to_drop_frequency_3591/checkpoint-40000/config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GPT2LMHeadModel"
|
| 5 |
+
],
|
| 6 |
+
"attn_pdrop": 0.1,
|
| 7 |
+
"bos_token_id": 50256,
|
| 8 |
+
"embd_pdrop": 0.1,
|
| 9 |
+
"eos_token_id": 50256,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"layer_norm_epsilon": 1e-05,
|
| 12 |
+
"model_type": "gpt2",
|
| 13 |
+
"n_embd": 768,
|
| 14 |
+
"n_head": 12,
|
| 15 |
+
"n_inner": null,
|
| 16 |
+
"n_layer": 12,
|
| 17 |
+
"n_positions": 1024,
|
| 18 |
+
"reorder_and_upcast_attn": false,
|
| 19 |
+
"resid_pdrop": 0.1,
|
| 20 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 21 |
+
"scale_attn_weights": true,
|
| 22 |
+
"summary_activation": null,
|
| 23 |
+
"summary_first_dropout": 0.1,
|
| 24 |
+
"summary_proj_to_labels": true,
|
| 25 |
+
"summary_type": "cls_index",
|
| 26 |
+
"summary_use_proj": true,
|
| 27 |
+
"torch_dtype": "float32",
|
| 28 |
+
"transformers_version": "4.55.2",
|
| 29 |
+
"use_cache": true,
|
| 30 |
+
"vocab_size": 50257
|
| 31 |
+
}
|
resemble_to_drop_frequency_3591/checkpoint-40000/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "4.55.2"
|
| 6 |
+
}
|
resemble_to_drop_frequency_3591/checkpoint-40000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
resemble_to_drop_frequency_3591/checkpoint-40000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7d77fffe19c0ac6915706b2c6df80af612b079a72057e5fea40cc622450665ad
|
| 3 |
+
size 497774208
|
resemble_to_drop_frequency_3591/checkpoint-40000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:643583a5a7c070d199d7a8e29d5b7370e38ccc556b4157ed216d7696654efc4d
|
| 3 |
+
size 995644811
|
resemble_to_drop_frequency_3591/checkpoint-40000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ae39a9c54fe946639529d1ec86e921d976be8714da9f1762f8be2f57aa5e3ece
|
| 3 |
+
size 14645
|
resemble_to_drop_frequency_3591/checkpoint-40000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:728e44349b28ca534e2b04df0e5dc3845fb30a911dc7d7a13ef962caa844372e
|
| 3 |
+
size 1383
|
resemble_to_drop_frequency_3591/checkpoint-40000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f2358aa5657b1e21f344557abc28c2385065d2ed2f82389cf3ff94ad7b8bd44f
|
| 3 |
+
size 1465
|
resemble_to_drop_frequency_3591/checkpoint-40000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<|endoftext|>",
|
| 3 |
+
"eos_token": "<|endoftext|>",
|
| 4 |
+
"unk_token": "<|endoftext|>"
|
| 5 |
+
}
|
resemble_to_drop_frequency_3591/checkpoint-40000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
resemble_to_drop_frequency_3591/checkpoint-40000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": false,
|
| 15 |
+
"eos_token": "<|endoftext|>",
|
| 16 |
+
"extra_special_tokens": {},
|
| 17 |
+
"model_max_length": 1024,
|
| 18 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 19 |
+
"unk_token": "<|endoftext|>"
|
| 20 |
+
}
|
resemble_to_drop_frequency_3591/checkpoint-40000/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
resemble_to_drop_frequency_3591/checkpoint-40000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bec96c10e17a6d709f2402982e5e9fcc043d9077a59703780c138d2104dbd481
|
| 3 |
+
size 5969
|
resemble_to_drop_frequency_3591/checkpoint-40000/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
resemble_to_drop_frequency_3591/checkpoint-50000/config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GPT2LMHeadModel"
|
| 5 |
+
],
|
| 6 |
+
"attn_pdrop": 0.1,
|
| 7 |
+
"bos_token_id": 50256,
|
| 8 |
+
"embd_pdrop": 0.1,
|
| 9 |
+
"eos_token_id": 50256,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"layer_norm_epsilon": 1e-05,
|
| 12 |
+
"model_type": "gpt2",
|
| 13 |
+
"n_embd": 768,
|
| 14 |
+
"n_head": 12,
|
| 15 |
+
"n_inner": null,
|
| 16 |
+
"n_layer": 12,
|
| 17 |
+
"n_positions": 1024,
|
| 18 |
+
"reorder_and_upcast_attn": false,
|
| 19 |
+
"resid_pdrop": 0.1,
|
| 20 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 21 |
+
"scale_attn_weights": true,
|
| 22 |
+
"summary_activation": null,
|
| 23 |
+
"summary_first_dropout": 0.1,
|
| 24 |
+
"summary_proj_to_labels": true,
|
| 25 |
+
"summary_type": "cls_index",
|
| 26 |
+
"summary_use_proj": true,
|
| 27 |
+
"torch_dtype": "float32",
|
| 28 |
+
"transformers_version": "4.55.2",
|
| 29 |
+
"use_cache": true,
|
| 30 |
+
"vocab_size": 50257
|
| 31 |
+
}
|
resemble_to_drop_frequency_3591/checkpoint-50000/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "4.55.2"
|
| 6 |
+
}
|
resemble_to_drop_frequency_3591/checkpoint-50000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
resemble_to_drop_frequency_3591/checkpoint-50000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f6e7b4791865d3360541eab474f20fb67c793814c87fb433d077b938d24c1bd0
|
| 3 |
+
size 497774208
|
resemble_to_drop_frequency_3591/checkpoint-50000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b2061d5f87abaedc9462a4bd4c6cc81c627d08979a1996baf8f7f803220d1da8
|
| 3 |
+
size 995644811
|
resemble_to_drop_frequency_3591/checkpoint-50000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:12f39e2465dbc023814fa665f7a732d148eb0e4b1ae7a6db53ef88a35421f165
|
| 3 |
+
size 14645
|
resemble_to_drop_frequency_3591/checkpoint-50000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ab6f83cb1957ae158df43ef61dafe2cadd5b16c24e6f0928531ae5d811029227
|
| 3 |
+
size 1383
|
resemble_to_drop_frequency_3591/checkpoint-50000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:377c4525c7c71feb1a629cb8c76d31b37815acb15a41dfc2e1832b672584f32f
|
| 3 |
+
size 1465
|
resemble_to_drop_frequency_3591/checkpoint-50000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<|endoftext|>",
|
| 3 |
+
"eos_token": "<|endoftext|>",
|
| 4 |
+
"unk_token": "<|endoftext|>"
|
| 5 |
+
}
|
resemble_to_drop_frequency_3591/checkpoint-50000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
resemble_to_drop_frequency_3591/checkpoint-50000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": false,
|
| 15 |
+
"eos_token": "<|endoftext|>",
|
| 16 |
+
"extra_special_tokens": {},
|
| 17 |
+
"model_max_length": 1024,
|
| 18 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 19 |
+
"unk_token": "<|endoftext|>"
|
| 20 |
+
}
|
resemble_to_drop_frequency_3591/checkpoint-50000/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
resemble_to_drop_frequency_3591/checkpoint-50000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bec96c10e17a6d709f2402982e5e9fcc043d9077a59703780c138d2104dbd481
|
| 3 |
+
size 5969
|
resemble_to_drop_frequency_3591/checkpoint-50000/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
resemble_to_drop_frequency_3591/checkpoint-60000/config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GPT2LMHeadModel"
|
| 5 |
+
],
|
| 6 |
+
"attn_pdrop": 0.1,
|
| 7 |
+
"bos_token_id": 50256,
|
| 8 |
+
"embd_pdrop": 0.1,
|
| 9 |
+
"eos_token_id": 50256,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"layer_norm_epsilon": 1e-05,
|
| 12 |
+
"model_type": "gpt2",
|
| 13 |
+
"n_embd": 768,
|
| 14 |
+
"n_head": 12,
|
| 15 |
+
"n_inner": null,
|
| 16 |
+
"n_layer": 12,
|
| 17 |
+
"n_positions": 1024,
|
| 18 |
+
"reorder_and_upcast_attn": false,
|
| 19 |
+
"resid_pdrop": 0.1,
|
| 20 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 21 |
+
"scale_attn_weights": true,
|
| 22 |
+
"summary_activation": null,
|
| 23 |
+
"summary_first_dropout": 0.1,
|
| 24 |
+
"summary_proj_to_labels": true,
|
| 25 |
+
"summary_type": "cls_index",
|
| 26 |
+
"summary_use_proj": true,
|
| 27 |
+
"torch_dtype": "float32",
|
| 28 |
+
"transformers_version": "4.55.2",
|
| 29 |
+
"use_cache": true,
|
| 30 |
+
"vocab_size": 50257
|
| 31 |
+
}
|
resemble_to_drop_frequency_3591/checkpoint-60000/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "4.55.2"
|
| 6 |
+
}
|
resemble_to_drop_frequency_3591/checkpoint-60000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
resemble_to_drop_frequency_3591/checkpoint-60000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:33df32af352d40440772eede67abafc28a402a1148ef8978eca82ac546494caa
|
| 3 |
+
size 497774208
|
resemble_to_drop_frequency_3591/checkpoint-60000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b63779ca404c21bf487ebef04690d3f9052a79ff07d3f658e31f7fe9cecd526
|
| 3 |
+
size 995644811
|
resemble_to_drop_frequency_3591/checkpoint-60000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e37a80bb23d827365ee82911accebb2560873d4d6ee73dd7508bbda3a4150e79
|
| 3 |
+
size 14645
|
resemble_to_drop_frequency_3591/checkpoint-60000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:65ac0498f9b9a1cbc22618943d83c80c9a7141feb98a468c9a8ec940b55b0710
|
| 3 |
+
size 1383
|
resemble_to_drop_frequency_3591/checkpoint-60000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c3c70200a195f5b6062f0194e47843ceb01c33595efcd51f2af84bf2de1f1765
|
| 3 |
+
size 1465
|
resemble_to_drop_frequency_3591/checkpoint-60000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<|endoftext|>",
|
| 3 |
+
"eos_token": "<|endoftext|>",
|
| 4 |
+
"unk_token": "<|endoftext|>"
|
| 5 |
+
}
|
resemble_to_drop_frequency_3591/checkpoint-60000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
resemble_to_drop_frequency_3591/checkpoint-60000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": false,
|
| 15 |
+
"eos_token": "<|endoftext|>",
|
| 16 |
+
"extra_special_tokens": {},
|
| 17 |
+
"model_max_length": 1024,
|
| 18 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 19 |
+
"unk_token": "<|endoftext|>"
|
| 20 |
+
}
|
resemble_to_drop_frequency_3591/checkpoint-60000/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
resemble_to_drop_frequency_3591/checkpoint-60000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bec96c10e17a6d709f2402982e5e9fcc043d9077a59703780c138d2104dbd481
|
| 3 |
+
size 5969
|
resemble_to_drop_frequency_3591/checkpoint-60000/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
resemble_to_drop_frequency_3591/checkpoint-70000/config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GPT2LMHeadModel"
|
| 5 |
+
],
|
| 6 |
+
"attn_pdrop": 0.1,
|
| 7 |
+
"bos_token_id": 50256,
|
| 8 |
+
"embd_pdrop": 0.1,
|
| 9 |
+
"eos_token_id": 50256,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"layer_norm_epsilon": 1e-05,
|
| 12 |
+
"model_type": "gpt2",
|
| 13 |
+
"n_embd": 768,
|
| 14 |
+
"n_head": 12,
|
| 15 |
+
"n_inner": null,
|
| 16 |
+
"n_layer": 12,
|
| 17 |
+
"n_positions": 1024,
|
| 18 |
+
"reorder_and_upcast_attn": false,
|
| 19 |
+
"resid_pdrop": 0.1,
|
| 20 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 21 |
+
"scale_attn_weights": true,
|
| 22 |
+
"summary_activation": null,
|
| 23 |
+
"summary_first_dropout": 0.1,
|
| 24 |
+
"summary_proj_to_labels": true,
|
| 25 |
+
"summary_type": "cls_index",
|
| 26 |
+
"summary_use_proj": true,
|
| 27 |
+
"torch_dtype": "float32",
|
| 28 |
+
"transformers_version": "4.55.2",
|
| 29 |
+
"use_cache": true,
|
| 30 |
+
"vocab_size": 50257
|
| 31 |
+
}
|
resemble_to_drop_frequency_3591/checkpoint-70000/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "4.55.2"
|
| 6 |
+
}
|
resemble_to_drop_frequency_3591/checkpoint-70000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
resemble_to_drop_frequency_3591/checkpoint-70000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5e1544a9e1a3a80a2f64d3a36cf47802ac2b842a83e44af81a500178c2f97422
|
| 3 |
+
size 497774208
|
resemble_to_drop_frequency_3591/checkpoint-70000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:55203275b0ff0ef0f8e021771f3ef94d8200c2b60e9e260d966706fb3acbc4a0
|
| 3 |
+
size 995644811
|
resemble_to_drop_frequency_3591/checkpoint-70000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac247caa082213ce75fa070a37e9d4196639932aac7ebadd8312cda9d99502ee
|
| 3 |
+
size 14645
|
resemble_to_drop_frequency_3591/checkpoint-70000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a8ded865ec6ac91caef657c3b3ed159cd2fbf7ce24e435ad72251afa3b3a2ecc
|
| 3 |
+
size 1383
|
resemble_to_drop_frequency_3591/checkpoint-70000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b5d9147f6c552b97d557708553469c436b903ee5755fef452f0f9cdd97c2e62e
|
| 3 |
+
size 1465
|