ko-yoshida/exp1_averaged
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: ko-yoshida/exp1_averaged
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-13 22:18:33 +08:00
commit 2b80925998
203 changed files with 1864471 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

28
checkpoint_1000M/config.json Normal file
View File

@@ -0,0 +1,28 @@
{
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151643,
"hidden_act": "silu",
"hidden_size": 896,
"initializer_range": 0.02,
"intermediate_size": 4864,
"max_position_embeddings": 131072,
"max_window_layers": 24,
"model_type": "qwen2",
"num_attention_heads": 14,
"num_hidden_layers": 24,
"num_key_value_heads": 2,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000.0,
"sliding_window": 131072,
"tie_word_embeddings": true,
"torch_dtype": "bfloat16",
"transformers_version": "4.50.0",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 16000
}

6
checkpoint_1000M/generation_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"_from_model_config": true,
"bos_token_id": 151643,
"eos_token_id": 151643,
"transformers_version": "4.50.0"
}

3
checkpoint_1000M/model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:691d64ec5d7e115ff7cee5a9783dfb10cc355c2484b0f0becf89a5494b4bdbb4
size 1488968616

30
checkpoint_1000M/special_tokens_map.json Normal file
View File

@@ -0,0 +1,30 @@
{
"bos_token": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

64159
checkpoint_1000M/tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

62
checkpoint_1000M/tokenizer_config.json Normal file
View File

@@ -0,0 +1,62 @@
{
"added_tokens_decoder": {
"0": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<cls>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<sep>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"4": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"5": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"cls_token": null,
"eos_token": "</s>",
"extra_special_tokens": {},
"model_max_length": 1073741824,
"pad_token": "<pad>",
"sep_token": null,
"tokenizer_class": "PreTrainedTokenizer",
"unk_token": "<unk>"
}

3
checkpoint_1000M/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1ab1ed1665bc2f6a593d946896575b603edbb539efc66edb68ba77926013b50f
size 6008

28
checkpoint_100M/config.json Normal file
View File

@@ -0,0 +1,28 @@
{
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151643,
"hidden_act": "silu",
"hidden_size": 896,
"initializer_range": 0.02,
"intermediate_size": 4864,
"max_position_embeddings": 131072,
"max_window_layers": 24,
"model_type": "qwen2",
"num_attention_heads": 14,
"num_hidden_layers": 24,
"num_key_value_heads": 2,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000.0,
"sliding_window": 131072,
"tie_word_embeddings": true,
"torch_dtype": "bfloat16",
"transformers_version": "4.50.0",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 16000
}

6
checkpoint_100M/generation_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"_from_model_config": true,
"bos_token_id": 151643,
"eos_token_id": 151643,
"transformers_version": "4.50.0"
}

3
checkpoint_100M/model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ebda14ccaf2a7b31f0fdcb936aae17af51e8c445972b0947afde10e1534f5dfe
size 744500456

30
checkpoint_100M/special_tokens_map.json Normal file
View File

@@ -0,0 +1,30 @@
{
"bos_token": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

64159
checkpoint_100M/tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

62
checkpoint_100M/tokenizer_config.json Normal file
View File

@@ -0,0 +1,62 @@
{
"added_tokens_decoder": {
"0": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<cls>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<sep>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"4": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"5": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"cls_token": null,
"eos_token": "</s>",
"extra_special_tokens": {},
"model_max_length": 1073741824,
"pad_token": "<pad>",
"sep_token": null,
"tokenizer_class": "PreTrainedTokenizer",
"unk_token": "<unk>"
}

28
checkpoint_10M/config.json Normal file
View File

@@ -0,0 +1,28 @@
{
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151643,
"hidden_act": "silu",
"hidden_size": 896,
"initializer_range": 0.02,
"intermediate_size": 4864,
"max_position_embeddings": 131072,
"max_window_layers": 24,
"model_type": "qwen2",
"num_attention_heads": 14,
"num_hidden_layers": 24,
"num_key_value_heads": 2,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000.0,
"sliding_window": 131072,
"tie_word_embeddings": true,
"torch_dtype": "bfloat16",
"transformers_version": "4.50.0",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 16000
}

6
checkpoint_10M/generation_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"_from_model_config": true,
"bos_token_id": 151643,
"eos_token_id": 151643,
"transformers_version": "4.50.0"
}

3
checkpoint_10M/model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9f1440e6bf85f76ca2e3a71a0569a201aeeabd6fef5d3ecd245d1a8eefd3becf
size 744500456

30
checkpoint_10M/special_tokens_map.json Normal file
View File

@@ -0,0 +1,30 @@
{
"bos_token": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

64159
checkpoint_10M/tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

62
checkpoint_10M/tokenizer_config.json Normal file
View File

@@ -0,0 +1,62 @@
{
"added_tokens_decoder": {
"0": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<cls>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<sep>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"4": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"5": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"cls_token": null,
"eos_token": "</s>",
"extra_special_tokens": {},
"model_max_length": 1073741824,
"pad_token": "<pad>",
"sep_token": null,
"tokenizer_class": "PreTrainedTokenizer",
"unk_token": "<unk>"
}

3
checkpoint_10M/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ac4b03f2d2286a3ac924e6548ec2cdc526a085e57db86868687f8f44c1d5d35c
size 5944

28
checkpoint_1M/config.json Normal file
View File

@@ -0,0 +1,28 @@
{
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151643,
"hidden_act": "silu",
"hidden_size": 896,
"initializer_range": 0.02,
"intermediate_size": 4864,
"max_position_embeddings": 131072,
"max_window_layers": 24,
"model_type": "qwen2",
"num_attention_heads": 14,
"num_hidden_layers": 24,
"num_key_value_heads": 2,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000.0,
"sliding_window": 131072,
"tie_word_embeddings": true,
"torch_dtype": "bfloat16",
"transformers_version": "4.50.0",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 16000
}

6
checkpoint_1M/generation_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"_from_model_config": true,
"bos_token_id": 151643,
"eos_token_id": 151643,
"transformers_version": "4.50.0"
}

3
checkpoint_1M/model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ad58c500e75f5eafc06a2001f827d4ea1d7bd27936e3bdb959f3048c10c21144
size 744500456

30
checkpoint_1M/special_tokens_map.json Normal file
View File

@@ -0,0 +1,30 @@
{
"bos_token": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

64159
checkpoint_1M/tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

62
checkpoint_1M/tokenizer_config.json Normal file
View File

@@ -0,0 +1,62 @@
{
"added_tokens_decoder": {
"0": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<cls>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<sep>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"4": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"5": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"cls_token": null,
"eos_token": "</s>",
"extra_special_tokens": {},
"model_max_length": 1073741824,
"pad_token": "<pad>",
"sep_token": null,
"tokenizer_class": "PreTrainedTokenizer",
"unk_token": "<unk>"
}

3
checkpoint_1M/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ac4b03f2d2286a3ac924e6548ec2cdc526a085e57db86868687f8f44c1d5d35c
size 5944

28
checkpoint_200M/config.json Normal file
View File

@@ -0,0 +1,28 @@
{
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151643,
"hidden_act": "silu",
"hidden_size": 896,
"initializer_range": 0.02,
"intermediate_size": 4864,
"max_position_embeddings": 131072,
"max_window_layers": 24,
"model_type": "qwen2",
"num_attention_heads": 14,
"num_hidden_layers": 24,
"num_key_value_heads": 2,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000.0,
"sliding_window": 131072,
"tie_word_embeddings": true,
"torch_dtype": "bfloat16",
"transformers_version": "4.50.0",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 16000
}

6
checkpoint_200M/generation_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"_from_model_config": true,
"bos_token_id": 151643,
"eos_token_id": 151643,
"transformers_version": "4.50.0"
}

3
checkpoint_200M/model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:edff8c72de3c3df719ee8c3092fceae17f4b27dc75a422f54702c5073cb17fba
size 744500456

30
checkpoint_200M/special_tokens_map.json Normal file
View File

@@ -0,0 +1,30 @@
{
"bos_token": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

64159
checkpoint_200M/tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

62
checkpoint_200M/tokenizer_config.json Normal file
View File

@@ -0,0 +1,62 @@
{
"added_tokens_decoder": {
"0": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<cls>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<sep>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"4": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"5": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"cls_token": null,
"eos_token": "</s>",
"extra_special_tokens": {},
"model_max_length": 1073741824,
"pad_token": "<pad>",
"sep_token": null,
"tokenizer_class": "PreTrainedTokenizer",
"unk_token": "<unk>"
}

3
checkpoint_200M/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1ab1ed1665bc2f6a593d946896575b603edbb539efc66edb68ba77926013b50f
size 6008

28
checkpoint_20M/config.json Normal file
View File

@@ -0,0 +1,28 @@
{
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151643,
"hidden_act": "silu",
"hidden_size": 896,
"initializer_range": 0.02,
"intermediate_size": 4864,
"max_position_embeddings": 131072,
"max_window_layers": 24,
"model_type": "qwen2",
"num_attention_heads": 14,
"num_hidden_layers": 24,
"num_key_value_heads": 2,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000.0,
"sliding_window": 131072,
"tie_word_embeddings": true,
"torch_dtype": "bfloat16",
"transformers_version": "4.50.0",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 16000
}

6
checkpoint_20M/generation_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"_from_model_config": true,
"bos_token_id": 151643,
"eos_token_id": 151643,
"transformers_version": "4.50.0"
}

3
checkpoint_20M/model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a3b88b517a0cd2549b4437302c9a26a0c6f61c2b646651b922fbcd13de31de2a
size 744500456

30
checkpoint_20M/special_tokens_map.json Normal file
View File

@@ -0,0 +1,30 @@
{
"bos_token": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

64159
checkpoint_20M/tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

62
checkpoint_20M/tokenizer_config.json Normal file
View File

@@ -0,0 +1,62 @@
{
"added_tokens_decoder": {
"0": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<cls>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<sep>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"4": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"5": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"cls_token": null,
"eos_token": "</s>",
"extra_special_tokens": {},
"model_max_length": 1073741824,
"pad_token": "<pad>",
"sep_token": null,
"tokenizer_class": "PreTrainedTokenizer",
"unk_token": "<unk>"
}

3
checkpoint_20M/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ac4b03f2d2286a3ac924e6548ec2cdc526a085e57db86868687f8f44c1d5d35c
size 5944

28
checkpoint_2M/config.json Normal file
View File

@@ -0,0 +1,28 @@
{
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151643,
"hidden_act": "silu",
"hidden_size": 896,
"initializer_range": 0.02,
"intermediate_size": 4864,
"max_position_embeddings": 131072,
"max_window_layers": 24,
"model_type": "qwen2",
"num_attention_heads": 14,
"num_hidden_layers": 24,
"num_key_value_heads": 2,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000.0,
"sliding_window": 131072,
"tie_word_embeddings": true,
"torch_dtype": "bfloat16",
"transformers_version": "4.50.0",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 16000
}

6
checkpoint_2M/generation_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"_from_model_config": true,
"bos_token_id": 151643,
"eos_token_id": 151643,
"transformers_version": "4.50.0"
}

3
checkpoint_2M/model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:387f069fa7e10d9d564afede9efa0d812fa0ef44feb2d4e381233c7785b0f306
size 744500456

30
checkpoint_2M/special_tokens_map.json Normal file
View File

@@ -0,0 +1,30 @@
{
"bos_token": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

64159
checkpoint_2M/tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

62
checkpoint_2M/tokenizer_config.json Normal file
View File

@@ -0,0 +1,62 @@
{
"added_tokens_decoder": {
"0": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<cls>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<sep>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"4": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"5": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"cls_token": null,
"eos_token": "</s>",
"extra_special_tokens": {},
"model_max_length": 1073741824,
"pad_token": "<pad>",
"sep_token": null,
"tokenizer_class": "PreTrainedTokenizer",
"unk_token": "<unk>"
}

3
checkpoint_2M/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ac4b03f2d2286a3ac924e6548ec2cdc526a085e57db86868687f8f44c1d5d35c
size 5944

28
checkpoint_300M/config.json Normal file
View File

@@ -0,0 +1,28 @@
{
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151643,
"hidden_act": "silu",
"hidden_size": 896,
"initializer_range": 0.02,
"intermediate_size": 4864,
"max_position_embeddings": 131072,
"max_window_layers": 24,
"model_type": "qwen2",
"num_attention_heads": 14,
"num_hidden_layers": 24,
"num_key_value_heads": 2,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000.0,
"sliding_window": 131072,
"tie_word_embeddings": true,
"torch_dtype": "bfloat16",
"transformers_version": "4.50.0",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 16000
}

6
checkpoint_300M/generation_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"_from_model_config": true,
"bos_token_id": 151643,
"eos_token_id": 151643,
"transformers_version": "4.50.0"
}

3
checkpoint_300M/model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c4a308bf9f4e8a56807c483415c467e9ed2c7c78ebc23e084933a627ffee0274
size 744500456

30
checkpoint_300M/special_tokens_map.json Normal file
View File

@@ -0,0 +1,30 @@
{
"bos_token": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

64159
checkpoint_300M/tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

62
checkpoint_300M/tokenizer_config.json Normal file
View File

@@ -0,0 +1,62 @@
{
"added_tokens_decoder": {
"0": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<cls>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<sep>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"4": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"5": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"cls_token": null,
"eos_token": "</s>",
"extra_special_tokens": {},
"model_max_length": 1073741824,
"pad_token": "<pad>",
"sep_token": null,
"tokenizer_class": "PreTrainedTokenizer",
"unk_token": "<unk>"
}

3
checkpoint_300M/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1ab1ed1665bc2f6a593d946896575b603edbb539efc66edb68ba77926013b50f
size 6008

28
checkpoint_30M/config.json Normal file
View File

@@ -0,0 +1,28 @@
{
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151643,
"hidden_act": "silu",
"hidden_size": 896,
"initializer_range": 0.02,
"intermediate_size": 4864,
"max_position_embeddings": 131072,
"max_window_layers": 24,
"model_type": "qwen2",
"num_attention_heads": 14,
"num_hidden_layers": 24,
"num_key_value_heads": 2,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000.0,
"sliding_window": 131072,
"tie_word_embeddings": true,
"torch_dtype": "bfloat16",
"transformers_version": "4.50.0",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 16000
}

6
checkpoint_30M/generation_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"_from_model_config": true,
"bos_token_id": 151643,
"eos_token_id": 151643,
"transformers_version": "4.50.0"
}

3
checkpoint_30M/model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a748e0423e1433a1dfc65d400d29be5e1ea2ee4b16caae7f280eb4fd5e0d25fd
size 744500456

30
checkpoint_30M/special_tokens_map.json Normal file
View File

@@ -0,0 +1,30 @@
{
"bos_token": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

64159
checkpoint_30M/tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

62
checkpoint_30M/tokenizer_config.json Normal file
View File

@@ -0,0 +1,62 @@
{
"added_tokens_decoder": {
"0": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<cls>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<sep>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"4": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"5": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"cls_token": null,
"eos_token": "</s>",
"extra_special_tokens": {},
"model_max_length": 1073741824,
"pad_token": "<pad>",
"sep_token": null,
"tokenizer_class": "PreTrainedTokenizer",
"unk_token": "<unk>"
}

3
checkpoint_30M/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ac4b03f2d2286a3ac924e6548ec2cdc526a085e57db86868687f8f44c1d5d35c
size 5944

28
checkpoint_3M/config.json Normal file
View File

@@ -0,0 +1,28 @@
{
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151643,
"hidden_act": "silu",
"hidden_size": 896,
"initializer_range": 0.02,
"intermediate_size": 4864,
"max_position_embeddings": 131072,
"max_window_layers": 24,
"model_type": "qwen2",
"num_attention_heads": 14,
"num_hidden_layers": 24,
"num_key_value_heads": 2,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000.0,
"sliding_window": 131072,
"tie_word_embeddings": true,
"torch_dtype": "bfloat16",
"transformers_version": "4.50.0",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 16000
}

6
checkpoint_3M/generation_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"_from_model_config": true,
"bos_token_id": 151643,
"eos_token_id": 151643,
"transformers_version": "4.50.0"
}

3
checkpoint_3M/model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3f1adadee1bcbbaeb6c703d18ebf911ce32091fd81826a44a283226be552ac1a
size 744500456

30
checkpoint_3M/special_tokens_map.json Normal file
View File

@@ -0,0 +1,30 @@
{
"bos_token": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

64159
checkpoint_3M/tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

62
checkpoint_3M/tokenizer_config.json Normal file
View File

@@ -0,0 +1,62 @@
{
"added_tokens_decoder": {
"0": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<cls>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<sep>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"4": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"5": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"cls_token": null,
"eos_token": "</s>",
"extra_special_tokens": {},
"model_max_length": 1073741824,
"pad_token": "<pad>",
"sep_token": null,
"tokenizer_class": "PreTrainedTokenizer",
"unk_token": "<unk>"
}

3
checkpoint_3M/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ac4b03f2d2286a3ac924e6548ec2cdc526a085e57db86868687f8f44c1d5d35c
size 5944

28
checkpoint_400M/config.json Normal file
View File

@@ -0,0 +1,28 @@
{
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151643,
"hidden_act": "silu",
"hidden_size": 896,
"initializer_range": 0.02,
"intermediate_size": 4864,
"max_position_embeddings": 131072,
"max_window_layers": 24,
"model_type": "qwen2",
"num_attention_heads": 14,
"num_hidden_layers": 24,
"num_key_value_heads": 2,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000.0,
"sliding_window": 131072,
"tie_word_embeddings": true,
"torch_dtype": "bfloat16",
"transformers_version": "4.50.0",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 16000
}

6
checkpoint_400M/generation_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"_from_model_config": true,
"bos_token_id": 151643,
"eos_token_id": 151643,
"transformers_version": "4.50.0"
}

3
checkpoint_400M/model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8df3a4ee3d0a93f7e8076cd0940927bf5224ce9168db66b1576540f41189a004
size 744500456

30
checkpoint_400M/special_tokens_map.json Normal file
View File

@@ -0,0 +1,30 @@
{
"bos_token": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

64159
checkpoint_400M/tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

62
checkpoint_400M/tokenizer_config.json Normal file
View File

@@ -0,0 +1,62 @@
{
"added_tokens_decoder": {
"0": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<cls>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<sep>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"4": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"5": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"cls_token": null,
"eos_token": "</s>",
"extra_special_tokens": {},
"model_max_length": 1073741824,
"pad_token": "<pad>",
"sep_token": null,
"tokenizer_class": "PreTrainedTokenizer",
"unk_token": "<unk>"
}

3
checkpoint_400M/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1ab1ed1665bc2f6a593d946896575b603edbb539efc66edb68ba77926013b50f
size 6008

28
checkpoint_40M/config.json Normal file
View File

@@ -0,0 +1,28 @@
{
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151643,
"hidden_act": "silu",
"hidden_size": 896,
"initializer_range": 0.02,
"intermediate_size": 4864,
"max_position_embeddings": 131072,
"max_window_layers": 24,
"model_type": "qwen2",
"num_attention_heads": 14,
"num_hidden_layers": 24,
"num_key_value_heads": 2,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000.0,
"sliding_window": 131072,
"tie_word_embeddings": true,
"torch_dtype": "bfloat16",
"transformers_version": "4.50.0",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 16000
}

6
checkpoint_40M/generation_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"_from_model_config": true,
"bos_token_id": 151643,
"eos_token_id": 151643,
"transformers_version": "4.50.0"
}

3
checkpoint_40M/model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:54cae13908278a17b7a5d9c3900abeb4ea2111c4155f5673a0b26c00a916a359
size 744500456

30
checkpoint_40M/special_tokens_map.json Normal file
View File

@@ -0,0 +1,30 @@
{
"bos_token": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

64159
checkpoint_40M/tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

62
checkpoint_40M/tokenizer_config.json Normal file
View File

@@ -0,0 +1,62 @@
{
"added_tokens_decoder": {
"0": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<cls>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<sep>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"4": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"5": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"cls_token": null,
"eos_token": "</s>",
"extra_special_tokens": {},
"model_max_length": 1073741824,
"pad_token": "<pad>",
"sep_token": null,
"tokenizer_class": "PreTrainedTokenizer",
"unk_token": "<unk>"
}

3
checkpoint_40M/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ac4b03f2d2286a3ac924e6548ec2cdc526a085e57db86868687f8f44c1d5d35c
size 5944

28
checkpoint_4M/config.json Normal file
View File

@@ -0,0 +1,28 @@
{
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151643,
"hidden_act": "silu",
"hidden_size": 896,
"initializer_range": 0.02,
"intermediate_size": 4864,
"max_position_embeddings": 131072,
"max_window_layers": 24,
"model_type": "qwen2",
"num_attention_heads": 14,
"num_hidden_layers": 24,
"num_key_value_heads": 2,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000.0,
"sliding_window": 131072,
"tie_word_embeddings": true,
"torch_dtype": "bfloat16",
"transformers_version": "4.50.0",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 16000
}

6
checkpoint_4M/generation_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"_from_model_config": true,
"bos_token_id": 151643,
"eos_token_id": 151643,
"transformers_version": "4.50.0"
}

3
checkpoint_4M/model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0543cccf20b42d13e86b7966b24ae1cc4b77e03e1e200f4dd9e796a982148175
size 744500456

30
checkpoint_4M/special_tokens_map.json Normal file
View File

@@ -0,0 +1,30 @@
{
"bos_token": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

64159
checkpoint_4M/tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

62
checkpoint_4M/tokenizer_config.json Normal file
View File

@@ -0,0 +1,62 @@
{
"added_tokens_decoder": {
"0": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<cls>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<sep>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"4": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"5": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"cls_token": null,
"eos_token": "</s>",
"extra_special_tokens": {},
"model_max_length": 1073741824,
"pad_token": "<pad>",
"sep_token": null,
"tokenizer_class": "PreTrainedTokenizer",
"unk_token": "<unk>"
}

3
checkpoint_4M/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ac4b03f2d2286a3ac924e6548ec2cdc526a085e57db86868687f8f44c1d5d35c
size 5944

28
checkpoint_500M/config.json Normal file
View File

@@ -0,0 +1,28 @@
{
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151643,
"hidden_act": "silu",
"hidden_size": 896,
"initializer_range": 0.02,
"intermediate_size": 4864,
"max_position_embeddings": 131072,
"max_window_layers": 24,
"model_type": "qwen2",
"num_attention_heads": 14,
"num_hidden_layers": 24,
"num_key_value_heads": 2,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000.0,
"sliding_window": 131072,
"tie_word_embeddings": true,
"torch_dtype": "bfloat16",
"transformers_version": "4.50.0",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 16000
}

6
checkpoint_500M/generation_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"_from_model_config": true,
"bos_token_id": 151643,
"eos_token_id": 151643,
"transformers_version": "4.50.0"
}

3
checkpoint_500M/model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8f9f189f88aece6f72a4a0c3d8494e9da72d061a1b19951718be01773bca09d3
size 744500456

30
checkpoint_500M/special_tokens_map.json Normal file
View File

@@ -0,0 +1,30 @@
{
"bos_token": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

64159
checkpoint_500M/tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

62
checkpoint_500M/tokenizer_config.json Normal file
View File

@@ -0,0 +1,62 @@
{
"added_tokens_decoder": {
"0": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<cls>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<sep>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"4": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"5": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"cls_token": null,
"eos_token": "</s>",
"extra_special_tokens": {},
"model_max_length": 1073741824,
"pad_token": "<pad>",
"sep_token": null,
"tokenizer_class": "PreTrainedTokenizer",
"unk_token": "<unk>"
}

3
checkpoint_500M/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1ab1ed1665bc2f6a593d946896575b603edbb539efc66edb68ba77926013b50f
size 6008

28
checkpoint_50M/config.json Normal file
View File

@@ -0,0 +1,28 @@
{
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151643,
"hidden_act": "silu",
"hidden_size": 896,
"initializer_range": 0.02,
"intermediate_size": 4864,
"max_position_embeddings": 131072,
"max_window_layers": 24,
"model_type": "qwen2",
"num_attention_heads": 14,
"num_hidden_layers": 24,
"num_key_value_heads": 2,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000.0,
"sliding_window": 131072,
"tie_word_embeddings": true,
"torch_dtype": "bfloat16",
"transformers_version": "4.50.0",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 16000
}

6
checkpoint_50M/generation_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"_from_model_config": true,
"bos_token_id": 151643,
"eos_token_id": 151643,
"transformers_version": "4.50.0"
}

Some files were not shown because too many files have changed in this diff Show More