初始化项目，由ModelHub XC社区提供模型

Model: nikitastheo/babylm-afr-ell-sequential_interleaved
Source: Original Platform

.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

README.md

@@ -0,0 +1,24 @@
+---
+tags:
+- causal-lm
+- text-generation
+library_name: transformers
+---
+
+# nikitastheo/babylm-afr-ell-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/babylm-afr-ell-tokenizer`
+- **Max steps**: 24270
+- **Learning rate**: 0.0001
+- **LR scheduler**: linear
+- **Warmup steps**: 2427
+- **Batch size (per device)**: 32
+- **Gradient accumulation steps**: 1
+- **Total train batch size**: 32
+- **Language switch epoch**: 10
+

config.json

@@ -0,0 +1,33 @@
+{
+  "activation_function": "gelu",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 1,
+  "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": 50000,
+  "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": 51200
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 50000,
+  "transformers_version": "4.57.6"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aed1ee88306ef28094ff70cdecdb01f9f58740a1f58a6615947a50da83c2ee6d
+size 499098240

special_tokens_map.json

@@ -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
+  }
+}

training_metadata.json

@@ -0,0 +1,70 @@
+{
+  "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": 8090,
+  "save_steps": [
+    1,
+    2,
+    4,
+    8,
+    16,
+    32,
+    64,
+    128,
+    256,
+    512,
+    1000,
+    2000,
+    3000,
+    4000,
+    5000,
+    6000,
+    7000,
+    8000,
+    8090,
+    8091,
+    8092,
+    8094,
+    8098,
+    8106,
+    8122,
+    8154,
+    8218,
+    8346,
+    8602,
+    9000,
+    10000,
+    11000,
+    12000,
+    13000,
+    14000,
+    15000,
+    16000,
+    17000,
+    18000,
+    19000,
+    20000,
+    21000,
+    22000,
+    23000,
+    24000,
+    24270
+  ]
+}