初始化项目，由ModelHub XC社区提供模型

Model: nikitastheo/phonebabylm-phone-deu-eng-sequential_interleaved Source: Original Platform
2026-08-21 19:39:17 +08:00
commit 545953eeab
11 changed files with 2790 additions and 0 deletions
--- a/.gitattributes
+++ b/.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
--- a/README.md
+++ b/README.md
@@ -0,0 +1,24 @@
+---
+tags:
+- causal-lm
+- text-generation
+library_name: transformers
+---
+
+# nikitastheo/phonebabylm-phone-deu-eng-sequential_interleaved
+
+Trained with train_clm.py, a Hugging Face Accelerate causal-LM training script (no `Trainer`).
+
+## Training details
+
+- **Base config**: `gpt_base_config.json`
+- **Tokenizer**: `nikitastheo/phonelm-phone-deu-eng-tokenizer`
+- **Max steps**: 30000
+- **Learning rate**: 0.0001
+- **LR scheduler**: linear
+- **Warmup steps**: 3000
+- **Batch size (per device)**: 32
+- **Gradient accumulation steps**: 1
+- **Total train batch size**: 32
+- **Language switch steps**: 10000
+
--- a/config.json
+++ b/config.json
@@ -0,0 +1,33 @@
+{
+  "activation_function": "gelu",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 2,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 512,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": 3072,
+  "n_layer": 12,
+  "n_positions": 512,
+  "pad_token_id": 1,
+  "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": "4.57.6",
+  "use_cache": true,
+  "vocab_size": 71
+}
--- a/generation_config.json
+++ b/generation_config.json
@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.57.6"
+}
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4ac61b4935cc87bb04dffbd037c203334c01c8c265e93a736a0ef4990e3f61f
+size 342029952
--- a/special_tokens_map.json
+++ b/special_tokens_map.json
@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "UTT_BOUNDARY",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "UTT_BOUNDARY",
+    "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
+  }
+}
--- a/tokenizer.json
+++ b/tokenizer.json
@@ -0,0 +1,174 @@
+{
+  "version": "1.0",
+  "truncation": null,
+  "padding": null,
+  "added_tokens": [
+    {
+      "id": 0,
+      "content": "UNK",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 1,
+      "content": "PAD",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 2,
+      "content": "UTT_BOUNDARY",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  ],
+  "normalizer": {
+    "type": "Sequence",
+    "normalizers": [
+      {
+        "type": "Replace",
+        "pattern": {
+          "String": "ː"
+        },
+        "content": " ː "
+      },
+      {
+        "type": "Strip",
+        "strip_left": true,
+        "strip_right": true
+      }
+    ]
+  },
+  "pre_tokenizer": {
+    "type": "Whitespace"
+  },
+  "post_processor": {
+    "type": "TemplateProcessing",
+    "single": [
+      {
+        "SpecialToken": {
+          "id": "UTT_BOUNDARY",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      }
+    ],
+    "pair": [
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "B",
+          "type_id": 1
+        }
+      }
+    ],
+    "special_tokens": {
+      "UTT_BOUNDARY": {
+        "id": "UTT_BOUNDARY",
+        "ids": [
+          2
+        ],
+        "tokens": [
+          "UTT_BOUNDARY"
+        ]
+      }
+    }
+  },
+  "decoder": null,
+  "model": {
+    "type": "WordLevel",
+    "vocab": {
+      "UNK": 0,
+      "PAD": 1,
+      "UTT_BOUNDARY": 2,
+      "d": 3,
+      "a": 4,
+      "s": 5,
+      "WORD_BOUNDARY": 6,
+      "f": 7,
+      "ɛ": 8,
+      "ɐ": 9,
+      "k": 10,
+      "ə": 11,
+      "l": 12,
+      "v": 13,
+      "o": 14,
+      "ː": 15,
+      "n": 16,
+      "t": 17,
+      "ɪ": 18,
+      "aɪ": 19,
+      "m": 20,
+      "z": 21,
+      "e": 22,
+      "ɡ": 23,
+      "h": 24,
+      "aʊ": 25,
+      "b": 26,
+      "u": 27,
+      "x": 28,
+      "ʊ": 29,
+      "i": 30,
+      "ʃ": 31,
+      "ʏ": 32,
+      "ts": 33,
+      "ɔ": 34,
+      "p": 35,
+      "ʀ": 36,
+      "ŋ": 37,
+      "œ": 38,
+      "ç": 39,
+      "y": 40,
+      "ø": 41,
+      "j": 42,
+      "pf": 43,
+      "ʊɐ": 44,
+      "eɪ": 45,
+      "d̠ʒ": 46,
+      "ɛɪ": 47,
+      "w": 48,
+      "ɒ": 49,
+      "ã": 50,
+      "t̠ʃ": 51,
+      "tɕ": 52,
+      "ð": 53,
+      "θ": 54,
+      "ɹ": 55,
+      "əʊ": 56,
+      "ʌ": 57,
+      "eə": 58,
+      "ɔɪ": 59,
+      "l̩": 60,
+      "ʒ": 61,
+      "ʊə": 62,
+      "ɔ̃": 63,
+      "iə": 64,
+      "œ̃": 65,
+      "ʔ": 66,
+      "æ": 67,
+      "ɑ": 68,
+      "ɜ": 69,
+      "oʊ": 70
+    },
+    "unk_token": "UNK"
+  }
+}
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,37 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "UNK",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "PAD",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "UTT_BOUNDARY",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "UTT_BOUNDARY",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "UTT_BOUNDARY",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "PAD",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "UNK"
+}
--- a/train_rank0.log
+++ b/train_rank0.log
--- a/training_metadata.json
+++ b/training_metadata.json
@@ -0,0 +1,74 @@
+{
+  "input_config": {
+    "model_type": "gpt2",
+    "architectures": [
+      "GPT2LMHeadModel"
+    ],
+    "activation_function": "gelu",
+    "attn_pdrop": 0.1,
+    "embd_pdrop": 0.1,
+    "resid_pdrop": 0.1,
+    "initializer_range": 0.02,
+    "layer_norm_epsilon": 1e-05,
+    "n_embd": 768,
+    "n_inner": 3072,
+    "n_head": 12,
+    "n_layer": 12,
+    "vocab_size": 1,
+    "n_ctx": 512,
+    "n_positions": 512
+  },
+  "num_steps_switch": 10000,
+  "save_steps": [
+    1,
+    2,
+    4,
+    8,
+    16,
+    32,
+    64,
+    128,
+    256,
+    512,
+    1000,
+    2000,
+    3000,
+    4000,
+    5000,
+    6000,
+    7000,
+    8000,
+    9000,
+    10000,
+    10001,
+    10002,
+    10004,
+    10008,
+    10016,
+    10032,
+    10064,
+    10128,
+    10256,
+    10512,
+    11000,
+    12000,
+    13000,
+    14000,
+    15000,
+    16000,
+    17000,
+    18000,
+    19000,
+    20000,
+    21000,
+    22000,
+    23000,
+    24000,
+    25000,
+    26000,
+    27000,
+    28000,
+    29000,
+    30000
+  ]
+}
--- a/vocab.json
+++ b/vocab.json
@@ -0,0 +1 @@
+{"UNK":0,"PAD":1,"UTT_BOUNDARY":2,"d":3,"a":4,"s":5,"WORD_BOUNDARY":6,"f":7,"ɛ":8,"ɐ":9,"k":10,"ə":11,"l":12,"v":13,"o":14,"ː":15,"n":16,"t":17,"ɪ":18,"aɪ":19,"m":20,"z":21,"e":22,"ɡ":23,"h":24,"aʊ":25,"b":26,"u":27,"x":28,"ʊ":29,"i":30,"ʃ":31,"ʏ":32,"ts":33,"ɔ":34,"p":35,"ʀ":36,"ŋ":37,"œ":38,"ç":39,"y":40,"ø":41,"j":42,"pf":43,"ʊɐ":44,"eɪ":45,"d̠ʒ":46,"ɛɪ":47,"w":48,"ɒ":49,"ã":50,"t̠ʃ":51,"tɕ":52,"ð":53,"θ":54,"ɹ":55,"əʊ":56,"ʌ":57,"eə":58,"ɔɪ":59,"l̩":60,"ʒ":61,"ʊə":62,"ɔ̃":63,"iə":64,"œ̃":65,"ʔ":66,"æ":67,"ɑ":68,"ɜ":69,"oʊ":70}
				`@@ -0,0 +1 @@`
				{"UNK":0,"PAD":1,"UTT_BOUNDARY":2,"d":3,"a":4,"s":5,"WORD_BOUNDARY":6,"f":7,"ɛ":8,"ɐ":9,"k":10,"ə":11,"l":12,"v":13,"o":14,"ː":15,"n":16,"t":17,"ɪ":18,"aɪ":19,"m":20,"z":21,"e":22,"ɡ":23,"h":24,"aʊ":25,"b":26,"u":27,"x":28,"ʊ":29,"i":30,"ʃ":31,"ʏ":32,"ts":33,"ɔ":34,"p":35,"ʀ":36,"ŋ":37,"œ":38,"ç":39,"y":40,"ø":41,"j":42,"pf":43,"ʊɐ":44,"eɪ":45,"d̠ʒ":46,"ɛɪ":47,"w":48,"ɒ":49,"ã":50,"t̠ʃ":51,"tɕ":52,"ð":53,"θ":54,"ɹ":55,"əʊ":56,"ʌ":57,"eə":58,"ɔɪ":59,"l̩":60,"ʒ":61,"ʊə":62,"ɔ̃":63,"iə":64,"œ̃":65,"ʔ":66,"æ":67,"ɑ":68,"ɜ":69,"oʊ":70}