Ba2han/model-phase2-4096
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: Ba2han/model-phase2-4096
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-21 01:40:19 +08:00
commit 991566fa67
20 changed files with 911167 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

31
last-checkpoint/config.json Normal file
View File

@@ -0,0 +1,31 @@
{
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 1,
"dtype": "bfloat16",
"eos_token_id": 2,
"head_dim": 64,
"hidden_act": "silu",
"hidden_size": 768,
"initializer_range": 0.02,
"intermediate_size": 3072,
"max_position_embeddings": 8192,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 12,
"num_hidden_layers": 52,
"num_key_value_heads": 4,
"pad_token_id": 2,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 100000.0,
"tie_word_embeddings": true,
"transformers_version": "4.57.2",
"unsloth_version": "2025.11.6",
"use_cache": true,
"vocab_size": 65536
}

10
last-checkpoint/generation_config.json Normal file
View File

@@ -0,0 +1,10 @@
{
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": [
2
],
"max_length": 8192,
"pad_token_id": 2,
"transformers_version": "4.57.2"
}

3
last-checkpoint/model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a5b9ab8046ed248553208fb4482d87ffd98a0851ff8ee8f63d488b049843f01e
size 1000555808

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:dbf8869e9742511d6cecad0a698d03144aeaf3b4f31752d9b002153ef4814089
size 1101500939

3
last-checkpoint/rng_state.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f530caa6daedb167cf31416f2f3afeddccb8a9a3c2868d74ea7416e2fee3c484
size 14645

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b623777d8745bac6ce6b7c8ff251c9d01811dea498056fdd549ff6872d212262
size 1465

71
last-checkpoint/special_tokens_map.json Normal file
View File

@@ -0,0 +1,71 @@
{
"additional_special_tokens": [
"<|im_start|>",
"<|im_end>",
"<think>",
"</think>",
"source_1",
"source_2",
"source_3",
"source_4",
"source_5",
"source_6",
"source_7",
"source_8",
"source_9",
"source_10",
"<ref",
"</ref>",
"→",
"↺",
"※",
"?maybe?",
"●",
"◐",
"○",
"⚠",
"☐",
"☑",
"✓",
"⟨H≈0.1⟩",
"⟨H≈0.2⟩",
"⟨H≈0.3⟩",
"⟨H≈0.4⟩",
"⟨H≈0.5⟩",
"⟨H≈0.6⟩",
"⟨H≈0.7⟩",
"⟨H≈0.8⟩",
"⟨H≈0.9⟩",
"⟨H≈1.0⟩",
"⟨H≈1.1⟩",
"⟨H≈1.2⟩",
"⟨H≈1.3⟩",
"⟨H≈1.4⟩",
"⟨H≈1.5⟩",
"⟨H≈1.6⟩",
"⟨H≈1.7⟩",
"⟨H≈1.8⟩"
],
"bos_token": {
"content": "<|begin_of_text|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "<|end_of_text|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": "<|end_of_text|>",
"unk_token": {
"content": "[UNK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

327047
last-checkpoint/tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

452
last-checkpoint/tokenizer_config.json Normal file
View File

@@ -0,0 +1,452 @@
{
"added_tokens_decoder": {
"0": {
"content": "[UNK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<|begin_of_text|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<|end_of_text|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "[PAD]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65491": {
"content": "<|im_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65492": {
"content": "<|im_end>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65493": {
"content": "<think>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65494": {
"content": "</think>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65495": {
"content": "source_1",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65496": {
"content": "source_2",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65497": {
"content": "source_3",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65498": {
"content": "source_4",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65499": {
"content": "source_5",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65500": {
"content": "source_6",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65501": {
"content": "source_7",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65502": {
"content": "source_8",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65503": {
"content": "source_9",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65504": {
"content": "source_10",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65505": {
"content": "<ref",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65506": {
"content": "</ref>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65507": {
"content": "→",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65508": {
"content": "↺",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65509": {
"content": "※",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65510": {
"content": "?maybe?",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65511": {
"content": "●",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65512": {
"content": "◐",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65513": {
"content": "○",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65514": {
"content": "⚠",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65515": {
"content": "☐",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65516": {
"content": "☑",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65517": {
"content": "✓",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65518": {
"content": "⟨H≈0.1⟩",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65519": {
"content": "⟨H≈0.2⟩",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65520": {
"content": "⟨H≈0.3⟩",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65521": {
"content": "⟨H≈0.4⟩",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65522": {
"content": "⟨H≈0.5⟩",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65523": {
"content": "⟨H≈0.6⟩",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65524": {
"content": "⟨H≈0.7⟩",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65525": {
"content": "⟨H≈0.8⟩",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65526": {
"content": "⟨H≈0.9⟩",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65527": {
"content": "⟨H≈1.0⟩",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65528": {
"content": "⟨H≈1.1⟩",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65529": {
"content": "⟨H≈1.2⟩",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65530": {
"content": "⟨H≈1.3⟩",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65531": {
"content": "⟨H≈1.4⟩",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65532": {
"content": "⟨H≈1.5⟩",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65533": {
"content": "⟨H≈1.6⟩",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65534": {
"content": "⟨H≈1.7⟩",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65535": {
"content": "⟨H≈1.8⟩",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<|im_start|>",
"<|im_end>",
"<think>",
"</think>",
"source_1",
"source_2",
"source_3",
"source_4",
"source_5",
"source_6",
"source_7",
"source_8",
"source_9",
"source_10",
"<ref",
"</ref>",
"→",
"↺",
"※",
"?maybe?",
"●",
"◐",
"○",
"⚠",
"☐",
"☑",
"✓",
"⟨H≈0.1⟩",
"⟨H≈0.2⟩",
"⟨H≈0.3⟩",
"⟨H≈0.4⟩",
"⟨H≈0.5⟩",
"⟨H≈0.6⟩",
"⟨H≈0.7⟩",
"⟨H≈0.8⟩",
"⟨H≈0.9⟩",
"⟨H≈1.0⟩",
"⟨H≈1.1⟩",
"⟨H≈1.2⟩",
"⟨H≈1.3⟩",
"⟨H≈1.4⟩",
"⟨H≈1.5⟩",
"⟨H≈1.6⟩",
"⟨H≈1.7⟩",
"⟨H≈1.8⟩"
],
"bos_token": "<|begin_of_text|>",
"clean_up_tokenization_spaces": true,
"eos_token": "<|end_of_text|>",
"extra_special_tokens": {},
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<|end_of_text|>",
"padding_side": "right",
"tokenizer_class": "PreTrainedTokenizerFast",
"unk_token": "[UNK]"
}

255830
last-checkpoint/trainer_state.json Normal file
View File

File diff suppressed because it is too large Load Diff

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:47478d0364a9e5b4a3d11e4abd89537a080c247d5b4ca266aa2094c02d65ddf1
size 6289