ali-elganzory/Baguettotron-longsft_16k
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: ali-elganzory/Baguettotron-longsft_16k
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-04-22 03:17:25 +08:00
commit 6cb3fe09be
8 changed files with 327716 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

61
README.md Normal file
View File

@@ -0,0 +1,61 @@
---
library_name: transformers
license: other
base_model: PleIAs/Baguettotron
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: long-context-baguettotron
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# long-context-baguettotron
This model is a fine-tuned version of [PleIAs/Baguettotron](https://huggingface.co/PleIAs/Baguettotron) on the long_sft dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- total_eval_batch_size: 64
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 1.0
### Training results
### Framework versions
- Transformers 4.51.3
- Pytorch 2.7.0a0+7c8ec84dab.nv25.03
- Datasets 3.6.0
- Tokenizers 0.21.4

33
config.json Normal file
View File

@@ -0,0 +1,33 @@
{
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"head_dim": 64,
"hidden_act": "silu",
"hidden_size": 576,
"initializer_range": 0.02,
"intermediate_size": 1536,
"max_position_embeddings": 16384,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 9,
"num_hidden_layers": 80,
"num_key_value_heads": 3,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": {
"factor": 4.0,
"original_max_position_embeddings": 4096,
"rope_type": "yarn"
},
"rope_theta": 10000,
"tie_word_embeddings": true,
"torch_dtype": "bfloat16",
"transformers_version": "4.51.3",
"use_cache": false,
"vocab_size": 65536
}

6
generation_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"transformers_version": "4.51.3"
}

3
model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0efd343f2e5b43a85749dec353bb86ccc9c50d442d7714b93bc9c557898146b0
size 641995416

77
special_tokens_map.json Normal file
View File

@@ -0,0 +1,77 @@
{
"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": "<|im_end|>",
"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
}
}

327047
tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

454
tokenizer_config.json Normal file
View File

@@ -0,0 +1,454 @@
{
"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|>",
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>\n' }}{% endif %}{% endfor %}",
"clean_up_tokenization_spaces": true,
"eos_token": "<|im_end|>",
"extra_special_tokens": {},
"model_max_length": 1000000000000000019884624838656,
"pad_token": "[PAD]",
"padding_side": "right",
"split_special_tokens": false,
"tokenizer_class": "PreTrainedTokenizer",
"unk_token": "[UNK]"
}