commit 58778019c4d7edb151a4044976f60306d3515de1
Author: ModelHub XC <noreply@modelhub.org.cn>
Date:   Thu Oct 29 05:04:16 2026 +0800

    初始化项目，由ModelHub XC社区提供模型
    
    Model: gvadhul/byte-llama-2layer
    Source: Original Platform

diff --git a/.gitattributes b/.gitattributes
new file mode 100644
index 0000000..a6344aa
--- /dev/null
+++ 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
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..bc5f30d
--- /dev/null
+++ b/README.md
@@ -0,0 +1,199 @@
+---
+library_name: transformers
+tags: []
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
\ No newline at end of file
diff --git a/config.json b/config.json
new file mode 100644
index 0000000..3073e26
--- /dev/null
+++ b/config.json
@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "dtype": "float32",
+  "eos_token_id": 3,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 256,
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 4,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.12.1",
+  "use_cache": true,
+  "vocab_size": 256
+}
diff --git a/generation_config.json b/generation_config.json
new file mode 100644
index 0000000..91b2172
--- /dev/null
+++ b/generation_config.json
@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 3,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 0,
+  "transformers_version": "5.12.1",
+  "use_cache": true
+}
diff --git a/model.safetensors b/model.safetensors
new file mode 100644
index 0000000..d195cb1
--- /dev/null
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eadb941712bfa968cd1fd81ca78789a728e3096680342d14e035bd93350d1814
+size 8920232
diff --git a/tokenizer.json b/tokenizer.json
new file mode 100644
index 0000000..9ce2442
--- /dev/null
+++ b/tokenizer.json
@@ -0,0 +1,314 @@
+{
+  "version": "1.0",
+  "truncation": null,
+  "padding": null,
+  "added_tokens": [],
+  "normalizer": null,
+  "pre_tokenizer": {
+    "type": "ByteLevel",
+    "add_prefix_space": false,
+    "trim_offsets": true,
+    "use_regex": false
+  },
+  "post_processor": {
+    "type": "TemplateProcessing",
+    "single": [
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      }
+    ],
+    "pair": [
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "B",
+          "type_id": 1
+        }
+      }
+    ],
+    "special_tokens": {}
+  },
+  "decoder": {
+    "type": "ByteLevel",
+    "add_prefix_space": true,
+    "trim_offsets": true,
+    "use_regex": true
+  },
+  "model": {
+    "type": "BPE",
+    "dropout": null,
+    "unk_token": null,
+    "continuing_subword_prefix": null,
+    "end_of_word_suffix": null,
+    "fuse_unk": false,
+    "byte_fallback": false,
+    "ignore_merges": false,
+    "vocab": {
+      "Ā": 0,
+      "ā": 1,
+      "Ă": 2,
+      "ă": 3,
+      "Ą": 4,
+      "ą": 5,
+      "Ć": 6,
+      "ć": 7,
+      "Ĉ": 8,
+      "ĉ": 9,
+      "Ċ": 10,
+      "ċ": 11,
+      "Č": 12,
+      "č": 13,
+      "Ď": 14,
+      "ď": 15,
+      "Đ": 16,
+      "đ": 17,
+      "Ē": 18,
+      "ē": 19,
+      "Ĕ": 20,
+      "ĕ": 21,
+      "Ė": 22,
+      "ė": 23,
+      "Ę": 24,
+      "ę": 25,
+      "Ě": 26,
+      "ě": 27,
+      "Ĝ": 28,
+      "ĝ": 29,
+      "Ğ": 30,
+      "ğ": 31,
+      "Ġ": 32,
+      "!": 33,
+      "\"": 34,
+      "#": 35,
+      "$": 36,
+      "%": 37,
+      "&": 38,
+      "'": 39,
+      "(": 40,
+      ")": 41,
+      "*": 42,
+      "+": 43,
+      ",": 44,
+      "-": 45,
+      ".": 46,
+      "/": 47,
+      "0": 48,
+      "1": 49,
+      "2": 50,
+      "3": 51,
+      "4": 52,
+      "5": 53,
+      "6": 54,
+      "7": 55,
+      "8": 56,
+      "9": 57,
+      ":": 58,
+      ";": 59,
+      "<": 60,
+      "=": 61,
+      ">": 62,
+      "?": 63,
+      "@": 64,
+      "A": 65,
+      "B": 66,
+      "C": 67,
+      "D": 68,
+      "E": 69,
+      "F": 70,
+      "G": 71,
+      "H": 72,
+      "I": 73,
+      "J": 74,
+      "K": 75,
+      "L": 76,
+      "M": 77,
+      "N": 78,
+      "O": 79,
+      "P": 80,
+      "Q": 81,
+      "R": 82,
+      "S": 83,
+      "T": 84,
+      "U": 85,
+      "V": 86,
+      "W": 87,
+      "X": 88,
+      "Y": 89,
+      "Z": 90,
+      "[": 91,
+      "\\": 92,
+      "]": 93,
+      "^": 94,
+      "_": 95,
+      "`": 96,
+      "a": 97,
+      "b": 98,
+      "c": 99,
+      "d": 100,
+      "e": 101,
+      "f": 102,
+      "g": 103,
+      "h": 104,
+      "i": 105,
+      "j": 106,
+      "k": 107,
+      "l": 108,
+      "m": 109,
+      "n": 110,
+      "o": 111,
+      "p": 112,
+      "q": 113,
+      "r": 114,
+      "s": 115,
+      "t": 116,
+      "u": 117,
+      "v": 118,
+      "w": 119,
+      "x": 120,
+      "y": 121,
+      "z": 122,
+      "{": 123,
+      "|": 124,
+      "}": 125,
+      "~": 126,
+      "ġ": 127,
+      "Ģ": 128,
+      "ģ": 129,
+      "Ĥ": 130,
+      "ĥ": 131,
+      "Ħ": 132,
+      "ħ": 133,
+      "Ĩ": 134,
+      "ĩ": 135,
+      "Ī": 136,
+      "ī": 137,
+      "Ĭ": 138,
+      "ĭ": 139,
+      "Į": 140,
+      "į": 141,
+      "İ": 142,
+      "ı": 143,
+      "IJ": 144,
+      "ij": 145,
+      "Ĵ": 146,
+      "ĵ": 147,
+      "Ķ": 148,
+      "ķ": 149,
+      "ĸ": 150,
+      "Ĺ": 151,
+      "ĺ": 152,
+      "Ļ": 153,
+      "ļ": 154,
+      "Ľ": 155,
+      "ľ": 156,
+      "Ŀ": 157,
+      "ŀ": 158,
+      "Ł": 159,
+      "ł": 160,
+      "¡": 161,
+      "¢": 162,
+      "£": 163,
+      "¤": 164,
+      "¥": 165,
+      "¦": 166,
+      "§": 167,
+      "¨": 168,
+      "©": 169,
+      "ª": 170,
+      "«": 171,
+      "¬": 172,
+      "Ń": 173,
+      "®": 174,
+      "¯": 175,
+      "°": 176,
+      "±": 177,
+      "²": 178,
+      "³": 179,
+      "´": 180,
+      "µ": 181,
+      "¶": 182,
+      "·": 183,
+      "¸": 184,
+      "¹": 185,
+      "º": 186,
+      "»": 187,
+      "¼": 188,
+      "½": 189,
+      "¾": 190,
+      "¿": 191,
+      "À": 192,
+      "Á": 193,
+      "Â": 194,
+      "Ã": 195,
+      "Ä": 196,
+      "Å": 197,
+      "Æ": 198,
+      "Ç": 199,
+      "È": 200,
+      "É": 201,
+      "Ê": 202,
+      "Ë": 203,
+      "Ì": 204,
+      "Í": 205,
+      "Î": 206,
+      "Ï": 207,
+      "Ð": 208,
+      "Ñ": 209,
+      "Ò": 210,
+      "Ó": 211,
+      "Ô": 212,
+      "Õ": 213,
+      "Ö": 214,
+      "×": 215,
+      "Ø": 216,
+      "Ù": 217,
+      "Ú": 218,
+      "Û": 219,
+      "Ü": 220,
+      "Ý": 221,
+      "Þ": 222,
+      "ß": 223,
+      "à": 224,
+      "á": 225,
+      "â": 226,
+      "ã": 227,
+      "ä": 228,
+      "å": 229,
+      "æ": 230,
+      "ç": 231,
+      "è": 232,
+      "é": 233,
+      "ê": 234,
+      "ë": 235,
+      "ì": 236,
+      "í": 237,
+      "î": 238,
+      "ï": 239,
+      "ð": 240,
+      "ñ": 241,
+      "ò": 242,
+      "ó": 243,
+      "ô": 244,
+      "õ": 245,
+      "ö": 246,
+      "÷": 247,
+      "ø": 248,
+      "ù": 249,
+      "ú": 250,
+      "û": 251,
+      "ü": 252,
+      "ý": 253,
+      "þ": 254,
+      "ÿ": 255
+    },
+    "merges": []
+  }
+}
\ No newline at end of file
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000..ed59080
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,10 @@
+{
+  "backend": "tokenizers",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "Ā",
+  "tokenizer_class": "TokenizersBackend"
+}