Kenobiwan/DialoGPT-small-AizakkuBot2
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: Kenobiwan/DialoGPT-small-AizakkuBot2
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-15 11:17:18 +08:00
commit b93cf45a1e
45 changed files with 601712 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
.gitattributes vendored Normal file
View 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

6
README.md Normal file
View File

@@ -0,0 +1,6 @@
---
tags:
- conversational
---
# Aizakku DiabloGPT Model

38
checkpoint-10500/config.json Normal file
View File

@@ -0,0 +1,38 @@
{
"_name_or_path": "microsoft/DialoGPT-small",
"activation_function": "gelu_new",
"architectures": [
"GPT2LMHeadModel"
],
"attn_pdrop": 0.1,
"bos_token_id": 50256,
"embd_pdrop": 0.1,
"eos_token_id": 50256,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "gpt2",
"n_ctx": 1024,
"n_embd": 768,
"n_head": 12,
"n_inner": null,
"n_layer": 12,
"n_positions": 1024,
"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,
"task_specific_params": {
"conversational": {
"max_length": 1000
}
},
"torch_dtype": "float32",
"transformers_version": "4.31.0",
"use_cache": true,
"vocab_size": 50257
}

6
checkpoint-10500/generation_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"_from_model_config": true,
"bos_token_id": 50256,
"eos_token_id": 50256,
"transformers_version": "4.31.0"
}

50001
checkpoint-10500/merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

3
checkpoint-10500/optimizer.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:367931ff0fd649c653dacfb6a7b2b08c365f72e29d3d82849b712f6f5690bc3b
size 995605189

3
checkpoint-10500/pytorch_model.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2cf481a3b4dcd6f34e9b8f306b9ee92b5bd8afc8898154a10675f2a7baccd085
size 497807197

3
checkpoint-10500/scheduler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:087c62534a327b65bed06794d8475b45608494c632ab58c33d019bedca18e037
size 627

23
checkpoint-10500/special_tokens_map.json Normal file
View File

@@ -0,0 +1,23 @@
{
"bos_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

100305
checkpoint-10500/tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

33
checkpoint-10500/tokenizer_config.json Normal file
View File

@@ -0,0 +1,33 @@
{
"add_bos_token": false,
"add_prefix_space": false,
"bos_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"clean_up_tokenization_spaces": true,
"eos_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"errors": "replace",
"model_max_length": 1024,
"pad_token": null,
"tokenizer_class": "GPT2Tokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

3
checkpoint-10500/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:468adcdb877ff6dc51b3bc405956aa0bec2c208955d786fcce57466c18c7be9a
size 1339

1
checkpoint-10500/vocab.json Normal file
View File

File diff suppressed because one or more lines are too long

38
checkpoint-3500/config.json Normal file
View File

@@ -0,0 +1,38 @@
{
"_name_or_path": "microsoft/DialoGPT-small",
"activation_function": "gelu_new",
"architectures": [
"GPT2LMHeadModel"
],
"attn_pdrop": 0.1,
"bos_token_id": 50256,
"embd_pdrop": 0.1,
"eos_token_id": 50256,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "gpt2",
"n_ctx": 1024,
"n_embd": 768,
"n_head": 12,
"n_inner": null,
"n_layer": 12,
"n_positions": 1024,
"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,
"task_specific_params": {
"conversational": {
"max_length": 1000
}
},
"torch_dtype": "float32",
"transformers_version": "4.31.0",
"use_cache": true,
"vocab_size": 50257
}

6
checkpoint-3500/generation_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"_from_model_config": true,
"bos_token_id": 50256,
"eos_token_id": 50256,
"transformers_version": "4.31.0"
}

50001
checkpoint-3500/merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

3
checkpoint-3500/optimizer.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:71cb04147bdea5db30c34c997ee2f659c201a92231e003203c8bee4bd87e478c
size 995605189

3
checkpoint-3500/pytorch_model.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1b29954de578d3e0b233fae4d87df181b630a0ae2882cc77a2987e624cf38f41
size 497807197

3
checkpoint-3500/scheduler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9988d5ee0944e210d32341f54ec4a6fe888bd1f3fae291841e4d9915ba3b6b01
size 627

23
checkpoint-3500/special_tokens_map.json Normal file
View File

@@ -0,0 +1,23 @@
{
"bos_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

100305
checkpoint-3500/tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

33
checkpoint-3500/tokenizer_config.json Normal file
View File

@@ -0,0 +1,33 @@
{
"add_bos_token": false,
"add_prefix_space": false,
"bos_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"clean_up_tokenization_spaces": true,
"eos_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"errors": "replace",
"model_max_length": 1024,
"pad_token": null,
"tokenizer_class": "GPT2Tokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

3
checkpoint-3500/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:468adcdb877ff6dc51b3bc405956aa0bec2c208955d786fcce57466c18c7be9a
size 1339

1
checkpoint-3500/vocab.json Normal file
View File

File diff suppressed because one or more lines are too long

38
checkpoint-7000/config.json Normal file
View File

@@ -0,0 +1,38 @@
{
"_name_or_path": "microsoft/DialoGPT-small",
"activation_function": "gelu_new",
"architectures": [
"GPT2LMHeadModel"
],
"attn_pdrop": 0.1,
"bos_token_id": 50256,
"embd_pdrop": 0.1,
"eos_token_id": 50256,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "gpt2",
"n_ctx": 1024,
"n_embd": 768,
"n_head": 12,
"n_inner": null,
"n_layer": 12,
"n_positions": 1024,
"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,
"task_specific_params": {
"conversational": {
"max_length": 1000
}
},
"torch_dtype": "float32",
"transformers_version": "4.31.0",
"use_cache": true,
"vocab_size": 50257
}

6
checkpoint-7000/generation_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"_from_model_config": true,
"bos_token_id": 50256,
"eos_token_id": 50256,
"transformers_version": "4.31.0"
}

50001
checkpoint-7000/merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

3
checkpoint-7000/optimizer.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b2430e598ecf32ab0801a4406bed401533569256a23ed4c609bde36d8ec03921
size 995605189

3
checkpoint-7000/pytorch_model.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:98d85daa3a1cc5fbc71be46b5cf7bc29c5c0a4c51527444926342b21be9c00b6
size 497807197

3
checkpoint-7000/scheduler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a8f4d46244cc2c9ed8991bed3d8376e81f13eec0e9a9cbbc5667210391c8f8a3
size 627

23
checkpoint-7000/special_tokens_map.json Normal file
View File

@@ -0,0 +1,23 @@
{
"bos_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

100305
checkpoint-7000/tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

33
checkpoint-7000/tokenizer_config.json Normal file
View File

@@ -0,0 +1,33 @@
{
"add_bos_token": false,
"add_prefix_space": false,
"bos_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"clean_up_tokenization_spaces": true,
"eos_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"errors": "replace",
"model_max_length": 1024,
"pad_token": null,
"tokenizer_class": "GPT2Tokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

3
checkpoint-7000/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:468adcdb877ff6dc51b3bc405956aa0bec2c208955d786fcce57466c18c7be9a
size 1339

1
checkpoint-7000/vocab.json Normal file
View File

File diff suppressed because one or more lines are too long

38
config.json Normal file
View File

@@ -0,0 +1,38 @@
{
"_name_or_path": "microsoft/DialoGPT-small",
"activation_function": "gelu_new",
"architectures": [
"GPT2LMHeadModel"
],
"attn_pdrop": 0.1,
"bos_token_id": 50256,
"embd_pdrop": 0.1,
"eos_token_id": 50256,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "gpt2",
"n_ctx": 1024,
"n_embd": 768,
"n_head": 12,
"n_inner": null,
"n_layer": 12,
"n_positions": 1024,
"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,
"task_specific_params": {
"conversational": {
"max_length": 1000
}
},
"torch_dtype": "float32",
"transformers_version": "4.31.0",
"use_cache": true,
"vocab_size": 50257
}

1
eval_results.txt Normal file
View File

@@ -0,0 +1 @@
perplexity = tensor(4.6318)

6
generation_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"_from_model_config": true,
"bos_token_id": 50256,
"eos_token_id": 50256,
"transformers_version": "4.31.0"
}

50001
merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

3
pytorch_model.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d0d34ffb23bf2db92019990b6dd646194bdab0434c7180d1cc69abf3b9408f9f
size 497807197

23
special_tokens_map.json Normal file
View File

@@ -0,0 +1,23 @@
{
"bos_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

100305
tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

33
tokenizer_config.json Normal file
View File

@@ -0,0 +1,33 @@
{
"add_bos_token": false,
"add_prefix_space": false,
"bos_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"clean_up_tokenization_spaces": true,
"eos_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"errors": "replace",
"model_max_length": 1024,
"pad_token": null,
"tokenizer_class": "GPT2Tokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

3
training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:468adcdb877ff6dc51b3bc405956aa0bec2c208955d786fcce57466c18c7be9a
size 1339

1
vocab.json Normal file
View File

File diff suppressed because one or more lines are too long