初始化项目,由ModelHub XC社区提供模型
Model: fpadovani/tur-latn-100mb-100mb_seed3407 Source: Original Platform
This commit is contained in:
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
58
README.md
Normal file
58
README.md
Normal file
@@ -0,0 +1,58 @@
|
||||
---
|
||||
base_model: goldfish-models/tur_latn_100mb
|
||||
library_name: transformers
|
||||
model_name: tur-latn-100mb-100mb_seed3407
|
||||
tags:
|
||||
- generated_from_trainer
|
||||
- trl
|
||||
- sft
|
||||
licence: license
|
||||
---
|
||||
|
||||
# Model Card for tur-latn-100mb-100mb_seed3407
|
||||
|
||||
This model is a fine-tuned version of [goldfish-models/tur_latn_100mb](https://huggingface.co/goldfish-models/tur_latn_100mb).
|
||||
It has been trained using [TRL](https://github.com/huggingface/trl).
|
||||
|
||||
## Quick start
|
||||
|
||||
```python
|
||||
from transformers import pipeline
|
||||
|
||||
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
|
||||
generator = pipeline("text-generation", model="fpadovani/tur-latn-100mb-100mb_seed3407", device="cuda")
|
||||
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
|
||||
print(output["generated_text"])
|
||||
```
|
||||
|
||||
## Training procedure
|
||||
|
||||
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/f-padovani-university-of-groningen/new_tokenizers/runs/yvenaede)
|
||||
|
||||
|
||||
This model was trained with SFT.
|
||||
|
||||
### Framework versions
|
||||
|
||||
- TRL: 0.23.0
|
||||
- Transformers: 4.56.2
|
||||
- Pytorch: 2.11.0
|
||||
- Datasets: 4.8.4
|
||||
- Tokenizers: 0.22.1
|
||||
|
||||
## Citations
|
||||
|
||||
|
||||
|
||||
Cite TRL as:
|
||||
|
||||
```bibtex
|
||||
@misc{vonwerra2022trl,
|
||||
title = {{TRL: Transformer Reinforcement Learning}},
|
||||
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
|
||||
year = 2020,
|
||||
journal = {GitHub repository},
|
||||
publisher = {GitHub},
|
||||
howpublished = {\url{https://github.com/huggingface/trl}}
|
||||
}
|
||||
```
|
||||
1202
added_tokens.json
Normal file
1202
added_tokens.json
Normal file
File diff suppressed because it is too large
Load Diff
1202
checkpoint-100030/added_tokens.json
Normal file
1202
checkpoint-100030/added_tokens.json
Normal file
File diff suppressed because it is too large
Load Diff
34
checkpoint-100030/config.json
Normal file
34
checkpoint-100030/config.json
Normal file
@@ -0,0 +1,34 @@
|
||||
{
|
||||
"activation_function": "gelu",
|
||||
"architectures": [
|
||||
"GPT2LMHeadModel"
|
||||
],
|
||||
"attn_pdrop": 0.1,
|
||||
"bos_token_id": 50000,
|
||||
"dtype": "bfloat16",
|
||||
"embd_pdrop": 0.1,
|
||||
"eos_token_id": 50001,
|
||||
"initializer_range": 0.02,
|
||||
"layer_norm_epsilon": 1e-05,
|
||||
"model_type": "gpt2",
|
||||
"n_ctx": 512,
|
||||
"n_embd": 768,
|
||||
"n_head": 12,
|
||||
"n_inner": 3072,
|
||||
"n_layer": 12,
|
||||
"n_positions": 512,
|
||||
"pad_token_id": 50002,
|
||||
"prefix": "[CLS]",
|
||||
"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,
|
||||
"transformers_version": "4.56.2",
|
||||
"use_cache": true,
|
||||
"vocab_size": 51200
|
||||
}
|
||||
9
checkpoint-100030/generation_config.json
Normal file
9
checkpoint-100030/generation_config.json
Normal file
@@ -0,0 +1,9 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 50000,
|
||||
"eos_token_id": [
|
||||
50001
|
||||
],
|
||||
"pad_token_id": 50002,
|
||||
"transformers_version": "4.56.2"
|
||||
}
|
||||
3
checkpoint-100030/model.safetensors
Normal file
3
checkpoint-100030/model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8d313856b32ac4cfe674e3607edab85bb139a93abf74b8236843ac9f9819bc44
|
||||
size 249556672
|
||||
3
checkpoint-100030/optimizer.pt
Normal file
3
checkpoint-100030/optimizer.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d389957de48619c5547b91a73e55f04cf3e59ebd06fa6e9dcf5a8f4a476169c4
|
||||
size 499209675
|
||||
3
checkpoint-100030/rng_state.pth
Normal file
3
checkpoint-100030/rng_state.pth
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:de7b13901c264bfbd338a4e975bdbba44a3d64505f729d92401deb86f2ad302d
|
||||
size 14645
|
||||
3
checkpoint-100030/scheduler.pt
Normal file
3
checkpoint-100030/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:41cb7abc62ae585bbd3665cb8266887e92998981e1daf90c575b040764a55217
|
||||
size 1465
|
||||
1249
checkpoint-100030/special_tokens_map.json
Normal file
1249
checkpoint-100030/special_tokens_map.json
Normal file
File diff suppressed because it is too large
Load Diff
3
checkpoint-100030/spiece.model
Normal file
3
checkpoint-100030/spiece.model
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d95f71157f3785af106d43210eaf3449759831f798d5580ffb139c8e488dabc0
|
||||
size 1200440
|
||||
10825
checkpoint-100030/tokenizer_config.json
Normal file
10825
checkpoint-100030/tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
200457
checkpoint-100030/trainer_state.json
Normal file
200457
checkpoint-100030/trainer_state.json
Normal file
File diff suppressed because it is too large
Load Diff
3
checkpoint-100030/training_args.bin
Normal file
3
checkpoint-100030/training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:92508653758cccb3d31b92812aeff44e9d57eb8948d1266513b8562520bfbbb0
|
||||
size 6289
|
||||
1202
checkpoint-12000/added_tokens.json
Normal file
1202
checkpoint-12000/added_tokens.json
Normal file
File diff suppressed because it is too large
Load Diff
34
checkpoint-12000/config.json
Normal file
34
checkpoint-12000/config.json
Normal file
@@ -0,0 +1,34 @@
|
||||
{
|
||||
"activation_function": "gelu",
|
||||
"architectures": [
|
||||
"GPT2LMHeadModel"
|
||||
],
|
||||
"attn_pdrop": 0.1,
|
||||
"bos_token_id": 50000,
|
||||
"dtype": "bfloat16",
|
||||
"embd_pdrop": 0.1,
|
||||
"eos_token_id": 50001,
|
||||
"initializer_range": 0.02,
|
||||
"layer_norm_epsilon": 1e-05,
|
||||
"model_type": "gpt2",
|
||||
"n_ctx": 512,
|
||||
"n_embd": 768,
|
||||
"n_head": 12,
|
||||
"n_inner": 3072,
|
||||
"n_layer": 12,
|
||||
"n_positions": 512,
|
||||
"pad_token_id": 50002,
|
||||
"prefix": "[CLS]",
|
||||
"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,
|
||||
"transformers_version": "4.56.2",
|
||||
"use_cache": true,
|
||||
"vocab_size": 51200
|
||||
}
|
||||
9
checkpoint-12000/generation_config.json
Normal file
9
checkpoint-12000/generation_config.json
Normal file
@@ -0,0 +1,9 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 50000,
|
||||
"eos_token_id": [
|
||||
50001
|
||||
],
|
||||
"pad_token_id": 50002,
|
||||
"transformers_version": "4.56.2"
|
||||
}
|
||||
3
checkpoint-12000/model.safetensors
Normal file
3
checkpoint-12000/model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3c353ed19283b0ccd35d1d2fb5f2b326d60320b9d663a1b3b4d195b4f3758e47
|
||||
size 249556672
|
||||
3
checkpoint-12000/rng_state.pth
Normal file
3
checkpoint-12000/rng_state.pth
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:31d02878b18f09768d2773571fd733cbfc57d5678828d933a9c3e3d0cb742631
|
||||
size 14645
|
||||
3
checkpoint-12000/scheduler.pt
Normal file
3
checkpoint-12000/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:31a2e0332feac9cab0ed296d951fcac98af526dc15002b1c701715dae987184a
|
||||
size 1465
|
||||
1249
checkpoint-12000/special_tokens_map.json
Normal file
1249
checkpoint-12000/special_tokens_map.json
Normal file
File diff suppressed because it is too large
Load Diff
3
checkpoint-12000/spiece.model
Normal file
3
checkpoint-12000/spiece.model
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d95f71157f3785af106d43210eaf3449759831f798d5580ffb139c8e488dabc0
|
||||
size 1200440
|
||||
10825
checkpoint-12000/tokenizer_config.json
Normal file
10825
checkpoint-12000/tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
24078
checkpoint-12000/trainer_state.json
Normal file
24078
checkpoint-12000/trainer_state.json
Normal file
File diff suppressed because it is too large
Load Diff
3
checkpoint-12000/training_args.bin
Normal file
3
checkpoint-12000/training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:92508653758cccb3d31b92812aeff44e9d57eb8948d1266513b8562520bfbbb0
|
||||
size 6289
|
||||
1202
checkpoint-15000/added_tokens.json
Normal file
1202
checkpoint-15000/added_tokens.json
Normal file
File diff suppressed because it is too large
Load Diff
34
checkpoint-15000/config.json
Normal file
34
checkpoint-15000/config.json
Normal file
@@ -0,0 +1,34 @@
|
||||
{
|
||||
"activation_function": "gelu",
|
||||
"architectures": [
|
||||
"GPT2LMHeadModel"
|
||||
],
|
||||
"attn_pdrop": 0.1,
|
||||
"bos_token_id": 50000,
|
||||
"dtype": "bfloat16",
|
||||
"embd_pdrop": 0.1,
|
||||
"eos_token_id": 50001,
|
||||
"initializer_range": 0.02,
|
||||
"layer_norm_epsilon": 1e-05,
|
||||
"model_type": "gpt2",
|
||||
"n_ctx": 512,
|
||||
"n_embd": 768,
|
||||
"n_head": 12,
|
||||
"n_inner": 3072,
|
||||
"n_layer": 12,
|
||||
"n_positions": 512,
|
||||
"pad_token_id": 50002,
|
||||
"prefix": "[CLS]",
|
||||
"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,
|
||||
"transformers_version": "4.56.2",
|
||||
"use_cache": true,
|
||||
"vocab_size": 51200
|
||||
}
|
||||
9
checkpoint-15000/generation_config.json
Normal file
9
checkpoint-15000/generation_config.json
Normal file
@@ -0,0 +1,9 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 50000,
|
||||
"eos_token_id": [
|
||||
50001
|
||||
],
|
||||
"pad_token_id": 50002,
|
||||
"transformers_version": "4.56.2"
|
||||
}
|
||||
3
checkpoint-15000/model.safetensors
Normal file
3
checkpoint-15000/model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ab4ee2658735374f610984cc4b3bb2d408bbd40d7c46b6b412ac4b408a22cdf8
|
||||
size 249556672
|
||||
3
checkpoint-15000/rng_state.pth
Normal file
3
checkpoint-15000/rng_state.pth
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8ff859c142a62ef108eb0460c36672de84e2777faa8ac205b84854698132ca46
|
||||
size 14645
|
||||
3
checkpoint-15000/scheduler.pt
Normal file
3
checkpoint-15000/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c0f8521dea9d976a4565dab0e9ad11aff277d1f4988157f533e638cc8585d882
|
||||
size 1465
|
||||
1249
checkpoint-15000/special_tokens_map.json
Normal file
1249
checkpoint-15000/special_tokens_map.json
Normal file
File diff suppressed because it is too large
Load Diff
3
checkpoint-15000/spiece.model
Normal file
3
checkpoint-15000/spiece.model
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d95f71157f3785af106d43210eaf3449759831f798d5580ffb139c8e488dabc0
|
||||
size 1200440
|
||||
10825
checkpoint-15000/tokenizer_config.json
Normal file
10825
checkpoint-15000/tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
30089
checkpoint-15000/trainer_state.json
Normal file
30089
checkpoint-15000/trainer_state.json
Normal file
File diff suppressed because it is too large
Load Diff
3
checkpoint-15000/training_args.bin
Normal file
3
checkpoint-15000/training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:92508653758cccb3d31b92812aeff44e9d57eb8948d1266513b8562520bfbbb0
|
||||
size 6289
|
||||
1202
checkpoint-18000/added_tokens.json
Normal file
1202
checkpoint-18000/added_tokens.json
Normal file
File diff suppressed because it is too large
Load Diff
34
checkpoint-18000/config.json
Normal file
34
checkpoint-18000/config.json
Normal file
@@ -0,0 +1,34 @@
|
||||
{
|
||||
"activation_function": "gelu",
|
||||
"architectures": [
|
||||
"GPT2LMHeadModel"
|
||||
],
|
||||
"attn_pdrop": 0.1,
|
||||
"bos_token_id": 50000,
|
||||
"dtype": "bfloat16",
|
||||
"embd_pdrop": 0.1,
|
||||
"eos_token_id": 50001,
|
||||
"initializer_range": 0.02,
|
||||
"layer_norm_epsilon": 1e-05,
|
||||
"model_type": "gpt2",
|
||||
"n_ctx": 512,
|
||||
"n_embd": 768,
|
||||
"n_head": 12,
|
||||
"n_inner": 3072,
|
||||
"n_layer": 12,
|
||||
"n_positions": 512,
|
||||
"pad_token_id": 50002,
|
||||
"prefix": "[CLS]",
|
||||
"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,
|
||||
"transformers_version": "4.56.2",
|
||||
"use_cache": true,
|
||||
"vocab_size": 51200
|
||||
}
|
||||
9
checkpoint-18000/generation_config.json
Normal file
9
checkpoint-18000/generation_config.json
Normal file
@@ -0,0 +1,9 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 50000,
|
||||
"eos_token_id": [
|
||||
50001
|
||||
],
|
||||
"pad_token_id": 50002,
|
||||
"transformers_version": "4.56.2"
|
||||
}
|
||||
3
checkpoint-18000/model.safetensors
Normal file
3
checkpoint-18000/model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:36477014304dfe0c871c58c9d264f31dde2205aa6a274641159ab393c5966471
|
||||
size 249556672
|
||||
3
checkpoint-18000/rng_state.pth
Normal file
3
checkpoint-18000/rng_state.pth
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:235a5a0dceb259689d9934e85f44152154935ee37b267b2803bf63423c9f5e50
|
||||
size 14645
|
||||
3
checkpoint-18000/scheduler.pt
Normal file
3
checkpoint-18000/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e2aa1a723a7696e60c5c7842ecd8ff735c1eeb6c140707726577ebc4bd0de311
|
||||
size 1465
|
||||
1249
checkpoint-18000/special_tokens_map.json
Normal file
1249
checkpoint-18000/special_tokens_map.json
Normal file
File diff suppressed because it is too large
Load Diff
3
checkpoint-18000/spiece.model
Normal file
3
checkpoint-18000/spiece.model
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d95f71157f3785af106d43210eaf3449759831f798d5580ffb139c8e488dabc0
|
||||
size 1200440
|
||||
10825
checkpoint-18000/tokenizer_config.json
Normal file
10825
checkpoint-18000/tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
36100
checkpoint-18000/trainer_state.json
Normal file
36100
checkpoint-18000/trainer_state.json
Normal file
File diff suppressed because it is too large
Load Diff
3
checkpoint-18000/training_args.bin
Normal file
3
checkpoint-18000/training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:92508653758cccb3d31b92812aeff44e9d57eb8948d1266513b8562520bfbbb0
|
||||
size 6289
|
||||
1202
checkpoint-21000/added_tokens.json
Normal file
1202
checkpoint-21000/added_tokens.json
Normal file
File diff suppressed because it is too large
Load Diff
34
checkpoint-21000/config.json
Normal file
34
checkpoint-21000/config.json
Normal file
@@ -0,0 +1,34 @@
|
||||
{
|
||||
"activation_function": "gelu",
|
||||
"architectures": [
|
||||
"GPT2LMHeadModel"
|
||||
],
|
||||
"attn_pdrop": 0.1,
|
||||
"bos_token_id": 50000,
|
||||
"dtype": "bfloat16",
|
||||
"embd_pdrop": 0.1,
|
||||
"eos_token_id": 50001,
|
||||
"initializer_range": 0.02,
|
||||
"layer_norm_epsilon": 1e-05,
|
||||
"model_type": "gpt2",
|
||||
"n_ctx": 512,
|
||||
"n_embd": 768,
|
||||
"n_head": 12,
|
||||
"n_inner": 3072,
|
||||
"n_layer": 12,
|
||||
"n_positions": 512,
|
||||
"pad_token_id": 50002,
|
||||
"prefix": "[CLS]",
|
||||
"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,
|
||||
"transformers_version": "4.56.2",
|
||||
"use_cache": true,
|
||||
"vocab_size": 51200
|
||||
}
|
||||
9
checkpoint-21000/generation_config.json
Normal file
9
checkpoint-21000/generation_config.json
Normal file
@@ -0,0 +1,9 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 50000,
|
||||
"eos_token_id": [
|
||||
50001
|
||||
],
|
||||
"pad_token_id": 50002,
|
||||
"transformers_version": "4.56.2"
|
||||
}
|
||||
3
checkpoint-21000/model.safetensors
Normal file
3
checkpoint-21000/model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4e5838cb4b7133e9c4c1f481ed90c061a659253b6784243155626c5aba9a70ad
|
||||
size 249556672
|
||||
3
checkpoint-21000/rng_state.pth
Normal file
3
checkpoint-21000/rng_state.pth
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:863472a45b003dc0a0f1d5e131dac6a9c24fbf0ad6fc0fec18b791d755af9288
|
||||
size 14645
|
||||
3
checkpoint-21000/scheduler.pt
Normal file
3
checkpoint-21000/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c85dd6a5f2a15d9424a3c3794a31f69333c1951abb92d7f07d62623c04757a79
|
||||
size 1465
|
||||
1249
checkpoint-21000/special_tokens_map.json
Normal file
1249
checkpoint-21000/special_tokens_map.json
Normal file
File diff suppressed because it is too large
Load Diff
3
checkpoint-21000/spiece.model
Normal file
3
checkpoint-21000/spiece.model
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d95f71157f3785af106d43210eaf3449759831f798d5580ffb139c8e488dabc0
|
||||
size 1200440
|
||||
10825
checkpoint-21000/tokenizer_config.json
Normal file
10825
checkpoint-21000/tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
42111
checkpoint-21000/trainer_state.json
Normal file
42111
checkpoint-21000/trainer_state.json
Normal file
File diff suppressed because it is too large
Load Diff
3
checkpoint-21000/training_args.bin
Normal file
3
checkpoint-21000/training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:92508653758cccb3d31b92812aeff44e9d57eb8948d1266513b8562520bfbbb0
|
||||
size 6289
|
||||
1202
checkpoint-24000/added_tokens.json
Normal file
1202
checkpoint-24000/added_tokens.json
Normal file
File diff suppressed because it is too large
Load Diff
34
checkpoint-24000/config.json
Normal file
34
checkpoint-24000/config.json
Normal file
@@ -0,0 +1,34 @@
|
||||
{
|
||||
"activation_function": "gelu",
|
||||
"architectures": [
|
||||
"GPT2LMHeadModel"
|
||||
],
|
||||
"attn_pdrop": 0.1,
|
||||
"bos_token_id": 50000,
|
||||
"dtype": "bfloat16",
|
||||
"embd_pdrop": 0.1,
|
||||
"eos_token_id": 50001,
|
||||
"initializer_range": 0.02,
|
||||
"layer_norm_epsilon": 1e-05,
|
||||
"model_type": "gpt2",
|
||||
"n_ctx": 512,
|
||||
"n_embd": 768,
|
||||
"n_head": 12,
|
||||
"n_inner": 3072,
|
||||
"n_layer": 12,
|
||||
"n_positions": 512,
|
||||
"pad_token_id": 50002,
|
||||
"prefix": "[CLS]",
|
||||
"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,
|
||||
"transformers_version": "4.56.2",
|
||||
"use_cache": true,
|
||||
"vocab_size": 51200
|
||||
}
|
||||
9
checkpoint-24000/generation_config.json
Normal file
9
checkpoint-24000/generation_config.json
Normal file
@@ -0,0 +1,9 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 50000,
|
||||
"eos_token_id": [
|
||||
50001
|
||||
],
|
||||
"pad_token_id": 50002,
|
||||
"transformers_version": "4.56.2"
|
||||
}
|
||||
3
checkpoint-24000/model.safetensors
Normal file
3
checkpoint-24000/model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7edf80a3b19d0d05a198bfa81b0cacaba2d9c80ad58cf7832040b066a5d3a8e3
|
||||
size 249556672
|
||||
3
checkpoint-24000/rng_state.pth
Normal file
3
checkpoint-24000/rng_state.pth
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:bd3ae12a03030f6aae86746e9c7bab91edd7604771c7a8406a8dfb901f58c076
|
||||
size 14645
|
||||
3
checkpoint-24000/scheduler.pt
Normal file
3
checkpoint-24000/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b4c4dae532fefe15cb817f03f77c8a74c9d4ba790af55328970eff586651d92c
|
||||
size 1465
|
||||
1249
checkpoint-24000/special_tokens_map.json
Normal file
1249
checkpoint-24000/special_tokens_map.json
Normal file
File diff suppressed because it is too large
Load Diff
3
checkpoint-24000/spiece.model
Normal file
3
checkpoint-24000/spiece.model
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d95f71157f3785af106d43210eaf3449759831f798d5580ffb139c8e488dabc0
|
||||
size 1200440
|
||||
10825
checkpoint-24000/tokenizer_config.json
Normal file
10825
checkpoint-24000/tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
48122
checkpoint-24000/trainer_state.json
Normal file
48122
checkpoint-24000/trainer_state.json
Normal file
File diff suppressed because it is too large
Load Diff
3
checkpoint-24000/training_args.bin
Normal file
3
checkpoint-24000/training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:92508653758cccb3d31b92812aeff44e9d57eb8948d1266513b8562520bfbbb0
|
||||
size 6289
|
||||
1202
checkpoint-27000/added_tokens.json
Normal file
1202
checkpoint-27000/added_tokens.json
Normal file
File diff suppressed because it is too large
Load Diff
34
checkpoint-27000/config.json
Normal file
34
checkpoint-27000/config.json
Normal file
@@ -0,0 +1,34 @@
|
||||
{
|
||||
"activation_function": "gelu",
|
||||
"architectures": [
|
||||
"GPT2LMHeadModel"
|
||||
],
|
||||
"attn_pdrop": 0.1,
|
||||
"bos_token_id": 50000,
|
||||
"dtype": "bfloat16",
|
||||
"embd_pdrop": 0.1,
|
||||
"eos_token_id": 50001,
|
||||
"initializer_range": 0.02,
|
||||
"layer_norm_epsilon": 1e-05,
|
||||
"model_type": "gpt2",
|
||||
"n_ctx": 512,
|
||||
"n_embd": 768,
|
||||
"n_head": 12,
|
||||
"n_inner": 3072,
|
||||
"n_layer": 12,
|
||||
"n_positions": 512,
|
||||
"pad_token_id": 50002,
|
||||
"prefix": "[CLS]",
|
||||
"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,
|
||||
"transformers_version": "4.56.2",
|
||||
"use_cache": true,
|
||||
"vocab_size": 51200
|
||||
}
|
||||
9
checkpoint-27000/generation_config.json
Normal file
9
checkpoint-27000/generation_config.json
Normal file
@@ -0,0 +1,9 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 50000,
|
||||
"eos_token_id": [
|
||||
50001
|
||||
],
|
||||
"pad_token_id": 50002,
|
||||
"transformers_version": "4.56.2"
|
||||
}
|
||||
3
checkpoint-27000/model.safetensors
Normal file
3
checkpoint-27000/model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7094bafaf722f1ddd55b4e384a56613b05b473b44744a5890963a5b1956e61fa
|
||||
size 249556672
|
||||
3
checkpoint-27000/rng_state.pth
Normal file
3
checkpoint-27000/rng_state.pth
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:129c8969d01ccfc82b347a64230a963d6d10f7cde0977577d91daa7cfd29f122
|
||||
size 14645
|
||||
3
checkpoint-27000/scheduler.pt
Normal file
3
checkpoint-27000/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a81f49e99758fbf1abf52b54ef37aa17284105b1fec41821a3dfdb1d1a6c9600
|
||||
size 1465
|
||||
1249
checkpoint-27000/special_tokens_map.json
Normal file
1249
checkpoint-27000/special_tokens_map.json
Normal file
File diff suppressed because it is too large
Load Diff
3
checkpoint-27000/spiece.model
Normal file
3
checkpoint-27000/spiece.model
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d95f71157f3785af106d43210eaf3449759831f798d5580ffb139c8e488dabc0
|
||||
size 1200440
|
||||
10825
checkpoint-27000/tokenizer_config.json
Normal file
10825
checkpoint-27000/tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
54133
checkpoint-27000/trainer_state.json
Normal file
54133
checkpoint-27000/trainer_state.json
Normal file
File diff suppressed because it is too large
Load Diff
3
checkpoint-27000/training_args.bin
Normal file
3
checkpoint-27000/training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:92508653758cccb3d31b92812aeff44e9d57eb8948d1266513b8562520bfbbb0
|
||||
size 6289
|
||||
1202
checkpoint-3000/added_tokens.json
Normal file
1202
checkpoint-3000/added_tokens.json
Normal file
File diff suppressed because it is too large
Load Diff
34
checkpoint-3000/config.json
Normal file
34
checkpoint-3000/config.json
Normal file
@@ -0,0 +1,34 @@
|
||||
{
|
||||
"activation_function": "gelu",
|
||||
"architectures": [
|
||||
"GPT2LMHeadModel"
|
||||
],
|
||||
"attn_pdrop": 0.1,
|
||||
"bos_token_id": 50000,
|
||||
"dtype": "bfloat16",
|
||||
"embd_pdrop": 0.1,
|
||||
"eos_token_id": 50001,
|
||||
"initializer_range": 0.02,
|
||||
"layer_norm_epsilon": 1e-05,
|
||||
"model_type": "gpt2",
|
||||
"n_ctx": 512,
|
||||
"n_embd": 768,
|
||||
"n_head": 12,
|
||||
"n_inner": 3072,
|
||||
"n_layer": 12,
|
||||
"n_positions": 512,
|
||||
"pad_token_id": 50002,
|
||||
"prefix": "[CLS]",
|
||||
"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,
|
||||
"transformers_version": "4.56.2",
|
||||
"use_cache": true,
|
||||
"vocab_size": 51200
|
||||
}
|
||||
9
checkpoint-3000/generation_config.json
Normal file
9
checkpoint-3000/generation_config.json
Normal file
@@ -0,0 +1,9 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 50000,
|
||||
"eos_token_id": [
|
||||
50001
|
||||
],
|
||||
"pad_token_id": 50002,
|
||||
"transformers_version": "4.56.2"
|
||||
}
|
||||
3
checkpoint-3000/model.safetensors
Normal file
3
checkpoint-3000/model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:af0c58f5b40ef51c60ceb63b13cfc3eb61979daff788624c3a945759804ef1ee
|
||||
size 249556672
|
||||
3
checkpoint-3000/rng_state.pth
Normal file
3
checkpoint-3000/rng_state.pth
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:dde6d5e912883ba6a24e8b6b6255542757fd80e29401f7a19a08641885d19e33
|
||||
size 14645
|
||||
3
checkpoint-3000/scheduler.pt
Normal file
3
checkpoint-3000/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:711276912c78bc25a0a602c3637a2516a8907ce81ed72002bb1d4b7794c9fb93
|
||||
size 1465
|
||||
1249
checkpoint-3000/special_tokens_map.json
Normal file
1249
checkpoint-3000/special_tokens_map.json
Normal file
File diff suppressed because it is too large
Load Diff
3
checkpoint-3000/spiece.model
Normal file
3
checkpoint-3000/spiece.model
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d95f71157f3785af106d43210eaf3449759831f798d5580ffb139c8e488dabc0
|
||||
size 1200440
|
||||
10825
checkpoint-3000/tokenizer_config.json
Normal file
10825
checkpoint-3000/tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
6045
checkpoint-3000/trainer_state.json
Normal file
6045
checkpoint-3000/trainer_state.json
Normal file
File diff suppressed because it is too large
Load Diff
3
checkpoint-3000/training_args.bin
Normal file
3
checkpoint-3000/training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:92508653758cccb3d31b92812aeff44e9d57eb8948d1266513b8562520bfbbb0
|
||||
size 6289
|
||||
1202
checkpoint-30000/added_tokens.json
Normal file
1202
checkpoint-30000/added_tokens.json
Normal file
File diff suppressed because it is too large
Load Diff
34
checkpoint-30000/config.json
Normal file
34
checkpoint-30000/config.json
Normal file
@@ -0,0 +1,34 @@
|
||||
{
|
||||
"activation_function": "gelu",
|
||||
"architectures": [
|
||||
"GPT2LMHeadModel"
|
||||
],
|
||||
"attn_pdrop": 0.1,
|
||||
"bos_token_id": 50000,
|
||||
"dtype": "bfloat16",
|
||||
"embd_pdrop": 0.1,
|
||||
"eos_token_id": 50001,
|
||||
"initializer_range": 0.02,
|
||||
"layer_norm_epsilon": 1e-05,
|
||||
"model_type": "gpt2",
|
||||
"n_ctx": 512,
|
||||
"n_embd": 768,
|
||||
"n_head": 12,
|
||||
"n_inner": 3072,
|
||||
"n_layer": 12,
|
||||
"n_positions": 512,
|
||||
"pad_token_id": 50002,
|
||||
"prefix": "[CLS]",
|
||||
"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,
|
||||
"transformers_version": "4.56.2",
|
||||
"use_cache": true,
|
||||
"vocab_size": 51200
|
||||
}
|
||||
9
checkpoint-30000/generation_config.json
Normal file
9
checkpoint-30000/generation_config.json
Normal file
@@ -0,0 +1,9 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 50000,
|
||||
"eos_token_id": [
|
||||
50001
|
||||
],
|
||||
"pad_token_id": 50002,
|
||||
"transformers_version": "4.56.2"
|
||||
}
|
||||
3
checkpoint-30000/model.safetensors
Normal file
3
checkpoint-30000/model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0e3d8c8a751e76f94660844d7fe6ccde87120864f9e35ff9cfd753d247490b8a
|
||||
size 249556672
|
||||
3
checkpoint-30000/rng_state.pth
Normal file
3
checkpoint-30000/rng_state.pth
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0c1b26099c33dfefa7dd91483773f2019575d9b1d1d380b5f215285db9bff24b
|
||||
size 14645
|
||||
3
checkpoint-30000/scheduler.pt
Normal file
3
checkpoint-30000/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a70b932f45c1e400eda963e62b9c6546b2e783bc86e2cd28000768b92e27e68f
|
||||
size 1465
|
||||
1249
checkpoint-30000/special_tokens_map.json
Normal file
1249
checkpoint-30000/special_tokens_map.json
Normal file
File diff suppressed because it is too large
Load Diff
3
checkpoint-30000/spiece.model
Normal file
3
checkpoint-30000/spiece.model
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d95f71157f3785af106d43210eaf3449759831f798d5580ffb139c8e488dabc0
|
||||
size 1200440
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user