初始化项目，由ModelHub XC社区提供模型

Model: iamshnoo/combined_only_url_with_metadata_1b_step2k
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 +1,79 @@
+---
+pipeline_tag: text-generation
+library_name: transformers
+tags:
+- text-generation
+- metadata-localization
+- metadata-ablation
+- 1b
+- with-metadata
+- pretraining
+- intermediate-checkpoint
+---
+
+# combined_only_url_with_metadata_1b_step2k
+
+## Summary
+
+This repo contains the url 1b step2k model exported from the 2k checkpoint for the metadata localization project. It was trained from scratch on the project corpus, using the Llama 3.2 tokenizer and vocabulary.
+
+## Variant Metadata
+
+- Stage: `pretrain`
+- Family: `metadata_ablation`
+- Size: `1b`
+- Metadata condition: `with_metadata`
+- Checkpoint export: `2k`
+- Base model lineage: `Trained from scratch; tokenizer/vocabulary from meta-llama/Llama-3.2-1B`
+
+## Weights & Biases Provenance
+
+- Run name: `24/12/2025_22:00:55_combined_only_url_with_metadata_1b`
+- Internal run URL: `https://wandb.ai/iamshnoo/nanotron/runs/mgsf3ei7`
+- Note: the Weights & Biases workspace is private; public readers should use the summarized metrics and configuration below.
+- State: `finished`
+- Runtime: `114h 11m 7s`
+
+## Run Summary
+
+- `KPI/train_lm_loss`: `2.0952`
+- `KPI/train_perplexity`: `8.1273`
+- `KPI/val_loss`: `2.088`
+- `KPI/val_perplexity`: `8.0687`
+- `KPI/consumed_tokens/train`: `41,943,040,000`
+- `_step`: `10,000`
+
+## Training Configuration
+
+- `train_steps`: `10,000`
+- `sequence_length`: `2,048`
+- `micro_batch_size`: `8`
+- `batch_accumulation_per_replica`: `64`
+- `learning_rate`: `0.003`
+- `min_decay_lr`: `0.0003`
+- `checkpoint_interval`: `1,000`
+
+## Training Curves
+
+Static plots below were exported from the private Weights & Biases run and embedded here for public access.
+
+### Train Loss
+
+![Train Loss](assets/train_loss.png)
+
+### Validation Perplexity
+
+![Validation Perplexity](assets/val_perplexity.png)
+
+### Throughput
+
+![Throughput](assets/tokens_per_sec.png)
+
+## Project Context
+
+This model is part of the metadata localization release. Related checkpoints and variants are grouped in the public Hugging Face collection [Metadata Conditioned LLMs](https://huggingface.co/collections/iamshnoo/metadata-conditioned-llms).
+- Training data source: [News on the Web (NOW) Corpus](https://www.english-corpora.org/now/)
+- Project repository: [https://github.com/iamshnoo/metadata_localization](https://github.com/iamshnoo/metadata_localization)
+- Paper: [https://arxiv.org/abs/2601.15236](https://arxiv.org/abs/2601.15236)
+
+Last synced: `2026-04-02 14:43:41 UTC`

config.json

@@ -0,0 +1,29 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 16,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.56.2",
+  "use_cache": true,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.56.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68573838417866d816e4feb39210aeed39ecff32ab4ea0e056cb0ae059783618
+size 2694992488

special_tokens_map.json

@@ -0,0 +1,16 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920