初始化项目，由ModelHub XC社区提供模型

Model: fpadovani/zho-hans-10mb-10mb_seed3407
Source: Original Platform

.gitattributes

@@ -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

README.md

@@ -0,0 +1,58 @@
+---
+base_model: goldfish-models/zho_hans_10mb
+library_name: transformers
+model_name: zho-hans-10mb-10mb_seed3407
+tags:
+- generated_from_trainer
+- sft
+- trl
+licence: license
+---
+
+# Model Card for zho-hans-10mb-10mb_seed3407
+
+This model is a fine-tuned version of [goldfish-models/zho_hans_10mb](https://huggingface.co/goldfish-models/zho_hans_10mb).
+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/zho-hans-10mb-10mb_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/xrj1expt) 
+
+
+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}}
+}
+```

checkpoint-1000/config.json

@@ -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": 512,
+  "n_head": 8,
+  "n_inner": 2048,
+  "n_layer": 4,
+  "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
+}

checkpoint-1000/generation_config.json

@@ -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"
+}

checkpoint-1000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c621c24ae19f274d0b3f0e2f36f2a0caf5980616a27c7cf68b42ee6b6a41d5a5
+size 78179408

checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e83fdc20cfc8791ec8c94bbb0140f434f66630c873d663b0638c0e8047454797
+size 14645

checkpoint-1000/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f98674a11db150158650e69331dc6119088d8e5c44310c21577f8d5c67b6447b
+size 1132145

checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c4d0f460dd7bcc268550166e55936247829f8590599ad8b4bec79d16812ea0d
+size 6289

checkpoint-1500/config.json

@@ -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": 512,
+  "n_head": 8,
+  "n_inner": 2048,
+  "n_layer": 4,
+  "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
+}

checkpoint-1500/generation_config.json

@@ -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"
+}

checkpoint-1500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31974251f7162abf98a714471e29cfe139a960e9c831e0e1639331a76b060aa3
+size 78179408

checkpoint-1500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:108daf965509ba532a94be08aed23e05e8b49e33ddaf1219095489cb26e40f7c
+size 14645

checkpoint-1500/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f98674a11db150158650e69331dc6119088d8e5c44310c21577f8d5c67b6447b
+size 1132145

checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c4d0f460dd7bcc268550166e55936247829f8590599ad8b4bec79d16812ea0d
+size 6289

checkpoint-2000/config.json

@@ -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": 512,
+  "n_head": 8,
+  "n_inner": 2048,
+  "n_layer": 4,
+  "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
+}

checkpoint-2000/generation_config.json

@@ -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"
+}

checkpoint-2000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c4b4fab90f46d7cc1033b132a8ee3e515f6d4a8fbd13c9f57e1998fecf66c6e
+size 78179408

checkpoint-2000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:563606b54b616d70be117b265b6cd4f6c13feccb17c09f0653b58be28a166ef7
+size 14645

checkpoint-2000/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f98674a11db150158650e69331dc6119088d8e5c44310c21577f8d5c67b6447b
+size 1132145

checkpoint-2000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c4d0f460dd7bcc268550166e55936247829f8590599ad8b4bec79d16812ea0d
+size 6289

checkpoint-2500/config.json

@@ -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": 512,
+  "n_head": 8,
+  "n_inner": 2048,
+  "n_layer": 4,
+  "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
+}

checkpoint-2500/generation_config.json

@@ -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"
+}

checkpoint-2500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b26d672cb53ad1c1eb7e23d454a08dbc45a3043cb065b9400885fe955ff1c325
+size 78179408

checkpoint-2500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0f61d4a5f76c434f1864fe51325b5d94956c72c5df249969c40c96945b13112
+size 14645

checkpoint-2500/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f98674a11db150158650e69331dc6119088d8e5c44310c21577f8d5c67b6447b
+size 1132145

checkpoint-2500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c4d0f460dd7bcc268550166e55936247829f8590599ad8b4bec79d16812ea0d
+size 6289

checkpoint-3000/config.json

@@ -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": 512,
+  "n_head": 8,
+  "n_inner": 2048,
+  "n_layer": 4,
+  "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
+}

checkpoint-3000/generation_config.json

@@ -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"
+}

checkpoint-3000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a2e9f7b9b8cbc4c2e4f769c390914a1ce8435497dc13f35def4dee442c8cecb
+size 78179408

checkpoint-3000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38618f19e5175e4237b25142569e9ee2f9dec62fb09e5c70627bac2bcdb73ae4
+size 14645

checkpoint-3000/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f98674a11db150158650e69331dc6119088d8e5c44310c21577f8d5c67b6447b
+size 1132145

checkpoint-3000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c4d0f460dd7bcc268550166e55936247829f8590599ad8b4bec79d16812ea0d
+size 6289

checkpoint-3500/config.json

@@ -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": 512,
+  "n_head": 8,
+  "n_inner": 2048,
+  "n_layer": 4,
+  "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
+}

checkpoint-3500/generation_config.json

@@ -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"
+}

checkpoint-3500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c23a78f33b304f0c193d0b702e43b24021bf26bf739566282cecfab34e13517
+size 78179408

checkpoint-3500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7288894dba5a7910e08b8bed4d4dbac943ae59ed85d244fa2195f2de0398c5bf
+size 14645

checkpoint-3500/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f98674a11db150158650e69331dc6119088d8e5c44310c21577f8d5c67b6447b
+size 1132145

checkpoint-3500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c4d0f460dd7bcc268550166e55936247829f8590599ad8b4bec79d16812ea0d
+size 6289

checkpoint-4000/config.json

@@ -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": 512,
+  "n_head": 8,
+  "n_inner": 2048,
+  "n_layer": 4,
+  "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
+}

checkpoint-4000/generation_config.json

@@ -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"
+}

checkpoint-4000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc21f2f8b323c8cb0ee8334a056e3818e31c185c4fb44ab3b42ab963a11036ae
+size 78179408

checkpoint-4000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4140060b3ccf0816dc8b2b4e150e5fca53ba36153c8bdb58b7efbd48accee3b7
+size 14645

checkpoint-4000/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f98674a11db150158650e69331dc6119088d8e5c44310c21577f8d5c67b6447b
+size 1132145

checkpoint-4000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c4d0f460dd7bcc268550166e55936247829f8590599ad8b4bec79d16812ea0d
+size 6289

checkpoint-4500/config.json

@@ -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": 512,
+  "n_head": 8,
+  "n_inner": 2048,
+  "n_layer": 4,
+  "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
+}

checkpoint-4500/generation_config.json

@@ -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"
+}

checkpoint-4500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad68d08b9b6adf3b0d4a6fdfa865f1c3b14979d5ef184f986c1527fb780acb5b
+size 78179408

checkpoint-4500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3a0eeab53229a6df834e1ff3d8b4cd41dff8400b4313d8268b984d86cc727a7
+size 14645

checkpoint-4500/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f98674a11db150158650e69331dc6119088d8e5c44310c21577f8d5c67b6447b
+size 1132145

checkpoint-4500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c4d0f460dd7bcc268550166e55936247829f8590599ad8b4bec79d16812ea0d
+size 6289

checkpoint-500/config.json

@@ -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": 512,
+  "n_head": 8,
+  "n_inner": 2048,
+  "n_layer": 4,
+  "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
+}

checkpoint-500/generation_config.json

@@ -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"
+}

checkpoint-500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1c6b112f7f02137299b86baefc32defae0fd73ce1c9985ccc236c97d914d5bd
+size 78179408

checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9eb80c89a85a9e6fad9f643cfce25889b75ffd41016a5da509fd7a66ba91fd5
+size 14645

checkpoint-500/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f98674a11db150158650e69331dc6119088d8e5c44310c21577f8d5c67b6447b
+size 1132145

checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c4d0f460dd7bcc268550166e55936247829f8590599ad8b4bec79d16812ea0d
+size 6289

checkpoint-5000/config.json

@@ -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": 512,
+  "n_head": 8,
+  "n_inner": 2048,
+  "n_layer": 4,
+  "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
+}

checkpoint-5000/generation_config.json

@@ -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"
+}

checkpoint-5000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af7ac42177dd70e858d49aba1ff2e51740b14c35671bc94a41bdb4b531c58051
+size 78179408

checkpoint-5000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe78c843e9ad6e6db22dec3375d196d4da0a4a84199784704a0713753f30b526
+size 14645

checkpoint-5000/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f98674a11db150158650e69331dc6119088d8e5c44310c21577f8d5c67b6447b
+size 1132145