初始化项目，由ModelHub XC社区提供模型

Model: deqing/convergent-llama-300M-adamw-isolate
Source: Original Platform

.gitattributes

@@ -0,0 +1,36 @@
+*.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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,45 @@
+---
+library_name: transformers
+tags:
+- convergent-evolution
+- fourier-features
+- number-embeddings
+license: mit
+datasets:
+- HuggingFaceFW/fineweb-edu
+---
+
+# convergent-llama-300M-adamw-isolate
+
+A 300M-parameter language model trained from scratch on **FineWeb-Edu 10BT** (~9.4B tokens, 1 epoch) as part of the *Convergent Evolution* project, which investigates how Fourier features emerge in LLM number embeddings.
+
+## Model details
+
+| | |
+|---|---|
+| **Architecture** | LLaMA-style Transformer (12 layers, 1024 hidden, 16 heads, GQA) |
+| **Parameters** | ~300M |
+| **Optimizer** | AdamW |
+| **Data perturbation** | block-diagonal attention mask (numbers cannot attend to context) |
+| **Training data** | [FineWeb-Edu](https://huggingface.co/datasets/HuggingFaceFW/fineweb-edu) sample-10BT (~9.4B tokens) |
+| **Context length** | 1024 |
+| **Tokenizer** | Llama 3 (128K vocab) |
+| **Batch size** | 512 sequences |
+
+## Training dynamics
+
+Intermediate checkpoints are saved as branches: `tokens-200M`, `tokens-400M`, ..., `tokens-9.6B`.
+
+```python
+from transformers import AutoModelForCausalLM
+
+# Load final checkpoint
+model = AutoModelForCausalLM.from_pretrained("deqing/convergent-llama-300M-adamw-isolate")
+
+# Load intermediate checkpoint (e.g., at 1B tokens)
+model = AutoModelForCausalLM.from_pretrained("deqing/convergent-llama-300M-adamw-isolate", revision="tokens-1B")
+```
+
+## Citation
+
+Paper forthcoming.

config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "dtype": "float32",
+  "eos_token_id": 128001,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "max_position_embeddings": 1024,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 8,
+  "pad_token_id": null,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 500000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.3.0",
+  "use_cache": false,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001
+  ],
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "transformers_version": "5.3.0",
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:899f4ead6c226c62e8aadd86c54851c0845c30deaa62d44f405002782f088cc8
+size 1280426144

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "is_local": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "tokenizer_class": "TokenizersBackend"
+}