初始化项目,由ModelHub XC社区提供模型
Model: fpadovani/tur-latn-100mb-after-ppt-Dp-100mb-ckpt500_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: fpadovani/tur-latn-100mb-ppt-Dp-100mb_seed3407
|
||||
library_name: transformers
|
||||
model_name: tur-latn-100mb-after-ppt-Dp-100mb-ckpt500_seed3407
|
||||
tags:
|
||||
- generated_from_trainer
|
||||
- trl
|
||||
- sft
|
||||
licence: license
|
||||
---
|
||||
|
||||
# Model Card for tur-latn-100mb-after-ppt-Dp-100mb-ckpt500_seed3407
|
||||
|
||||
This model is a fine-tuned version of [fpadovani/tur-latn-100mb-ppt-Dp-100mb_seed3407](https://huggingface.co/fpadovani/tur-latn-100mb-ppt-Dp-100mb_seed3407).
|
||||
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-after-ppt-Dp-100mb-ckpt500_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/atbgw5nc)
|
||||
|
||||
|
||||
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 sha256:80066de69ad8e1d43fd3534dc639927627623dd27d1bb4418bfae59b770f3499
|
||||
size 249556672
|
||||
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 sha256:7ddb8dfa77c62105a7cb8a108aad8fcbb13a3daa886aa7f6b3fafa67e8723095
|
||||
size 6353
|
||||
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 sha256:6a7dc8c20e1f348b25983bea3b5940a8bcc0a8f86bc34f7320e0ecb933ee6104
|
||||
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 sha256:7ddb8dfa77c62105a7cb8a108aad8fcbb13a3daa886aa7f6b3fafa67e8723095
|
||||
size 6353
|
||||
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:d4192a22339939fbf7263e61a0b3fee468aab9fb4a509b33acff7e9b4b001cdf
|
||||
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 sha256:7ddb8dfa77c62105a7cb8a108aad8fcbb13a3daa886aa7f6b3fafa67e8723095
|
||||
size 6353
|
||||
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 sha256:96f99a0351420d1d96a9b35fab41847165ee64ec12894d8489dd83340327083c
|
||||
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 sha256:7ddb8dfa77c62105a7cb8a108aad8fcbb13a3daa886aa7f6b3fafa67e8723095
|
||||
size 6353
|
||||
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 sha256:37a76b3290bb917a5d3df03eeca26dc8ee9ad23c6a96c5a564d781497a4d141b
|
||||
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 sha256:7ddb8dfa77c62105a7cb8a108aad8fcbb13a3daa886aa7f6b3fafa67e8723095
|
||||
size 6353
|
||||
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 sha256:2a5407518975dc334ae66c6e1441c1058664eaca2e7a4ec4fc6177c4f9e10b9b
|
||||
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 sha256:7ddb8dfa77c62105a7cb8a108aad8fcbb13a3daa886aa7f6b3fafa67e8723095
|
||||
size 6353
|
||||
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:d3d19e543cf3f242d81733260d59b80565840519d6fcde670652be9af1409b0c
|
||||
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 sha256:7ddb8dfa77c62105a7cb8a108aad8fcbb13a3daa886aa7f6b3fafa67e8723095
|
||||
size 6353
|
||||
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 sha256:583ac3560ea21ad6e939a8cfaace650dfe86eca56eb3e4f8f3786391e7e0485c
|
||||
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 sha256:7ddb8dfa77c62105a7cb8a108aad8fcbb13a3daa886aa7f6b3fafa67e8723095
|
||||
size 6353
|
||||
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 sha256:286f81f875b2ec72eb4cc22148c60be7cde4afdb99e8592cf357095df82c7a9b
|
||||
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
|
||||
10825
checkpoint-30000/tokenizer_config.json
Normal file
10825
checkpoint-30000/tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user