初始化项目，由ModelHub XC社区提供模型

Model: EleutherAI/GPT-2-wikitext-chunks
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 +1,31 @@
+---
+license: mit
+base_model: gpt2
+datasets:
+- EleutherAI/bergson-wikitext-512-chunks
+library_name: transformers
+pipeline_tag: text-generation
+---
+
+# GPT-2 fine-tuned on bergson-wikitext-512-chunks
+
+GPT-2 (124M) fine-tuned on [EleutherAI/bergson-wikitext-512-chunks](https://huggingface.co/datasets/EleutherAI/bergson-wikitext-512-chunks)
+(WikiText-2 pre-chunked to 512-token sequences, 4,608 train chunks) using the
+[bergson](https://github.com/EleutherAI/bergson) MAGIC trainer, as the trained
+model for MAGIC attribution experiments.
+
+## Training
+
+- 4 epochs, global batch size 64 (8x data parallel), 288 steps
+- AdamW, polynomial LR schedule: lr 8e-4 (start 1e-6, end 8e-5), 25% warmup, fp32
+- Loss on held-out `test[:4]` chunks: 3.22 (base gpt2: 3.62)
+
+## Files
+
+- Standard HF model + tokenizer files
+- `bergson_config.yaml` — the fully-resolved bergson run config (all fields incl. defaults) that produced this model; rerun with `python -m bergson bergson_config.yaml`
+- `optimizer.pt` — AdamW second moments (`exp_avg_sq`) at the final training
+  step, in bergson's `optimizer.pt` normalizer format
+  (`{"state": {idx: {"exp_avg_sq": ...}}, "param_groups": [...]}` with `idx`
+  indexing deduplicated `model.named_parameters()`), for gradient
+  normalization in attribution runs.

bergson_config.yaml

@@ -0,0 +1,80 @@
+steps:
+- magic:
+    run_path: runs/gpt2_wikitext_512chunks
+    overwrite: false
+    model: gpt2
+    precision: fp32
+    revision: null
+    distributed:
+      nnode: 1
+      nproc_per_node: 8
+      node_rank: null
+    fsdp: false
+    peft_init_kwargs: ''
+    model_kwargs: ''
+    data:
+      dataset: EleutherAI/bergson-wikitext-512-chunks
+      split: train
+      subset: null
+      prompt_column: text
+      completion_column: ''
+      conversation_column: ''
+      reward_column: ''
+      skip_nan_rewards: false
+      truncation: false
+      format_template: ''
+      data_kwargs: ''
+      chunk_length: 0
+    tokenizer: ''
+    drop_columns: true
+    max_tokens: null
+    use_tf32_matmuls: false
+    debug: false
+    lr_schedule:
+      lr: 0.0008
+      lr_scheduler_type: polynomial
+      lr_start: 1.0e-06
+      lr_end: 8.0e-05
+      warmup_steps: 0.25
+      num_cycles: 0.5
+      power: 1.0
+    batch_size: 64
+    num_epochs: 4
+    seed: 42
+    adam_beta1: 0.95
+    adam_beta2: 0.975
+    eps_root: 1.0e-08
+    optimizer: adamw
+    save_optimizer_state: false
+    weight_decay: 0.01
+    grad_checkpointing: false
+    resume: true
+    wandb_project: magic
+    query:
+      dataset: EleutherAI/bergson-wikitext-512-chunks
+      split: test[3:4]
+      subset: null
+      prompt_column: text
+      completion_column: ''
+      conversation_column: ''
+      reward_column: ''
+      skip_nan_rewards: false
+      truncation: false
+      format_template: ''
+      data_kwargs: ''
+      chunk_length: 0
+    query_method: mean
+    num_subsets: 400
+    subset_strategy: random
+    exclude_zero_scores: false
+    save_retrained_models: true
+    subset_fraction: 0.01
+    save_mode: sqrt
+    backward_save_every: 0
+    cleanup_ckpts: false
+    per_token: false
+    skip_validation: false
+metadata:
+  bergson_version: 0.9.1
+  created: '2026-07-08T06:06:06+00:00'
+  git_sha: 7178d50f

config.json

@@ -0,0 +1,41 @@
+{
+  "activation_function": "gelu_new",
+  "add_cross_attention": false,
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "pad_token_id": null,
+  "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,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.13.0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "5.13.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:624499a022a7e5a47b1ddb6998e9f232d12b0d3f0834d60e233b7b8b5efdd4d5
+size 497774208

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e02a34b0fc618c38d29964fa96a80a1b67cae7502b186530d2c1e64cd3d102d8
+size 497801419

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 1024,
+  "pad_token": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}