Add pre_1850 LoRA adapter (1 epoch)

README.md

@@ -0,0 +1,42 @@
+---
+base_model: TextMachineProject/NewsBERT_1800-1920
+library_name: peft
+tags:
+  - lora
+  - bert
+  - masked-language-modeling
+---
+
+# NewsBERT pre-1850 LoRA adapter (1 epoch)
+
+A LoRA adapter for [TextMachineProject/NewsBERT_1800-1920](https://huggingface.co/TextMachineProject/NewsBERT_1800-1920),
+fine-tuned for one epoch on newspaper text (pre-1850)
+from the [Heritage Made Digital (HMD14)](https://www.bl.uk/collection-guides/heritage-made-digital)
+and [Living with Machines (LwM)](https://livingwithmachines.ac.uk/) collections.
+
+## Training details
+
+- **Period**: pre-1850
+- **Base model**: `TextMachineProject/NewsBERT_1800-1920`
+- **Method**: LoRA (PEFT), target modules: `query`, `value`, `word_embeddings`
+- **LoRA rank**: 16, alpha: 32, dropout: 0.05
+- **Task**: Masked Language Modelling (15% masking probability)
+- **Sequence length**: 128 tokens (sliding window, stride 96)
+- **Epochs**: 1
+- **Batch size**: 256
+
+## Usage
+
+```python
+from transformers import AutoTokenizer, AutoModelForMaskedLM
+from peft import PeftModel
+
+base = AutoModelForMaskedLM.from_pretrained("TextMachineProject/NewsBERT_1800-1920")
+tokenizer = AutoTokenizer.from_pretrained("TextMachineProject/NewsBERT_1800-1920")
+model = PeftModel.from_pretrained(base, "TextMachineProject/NewsBERT_pre_1850_lora_1epoch")
+```
+
+## Notes
+
+This is a 1-epoch checkpoint uploaded for evaluation purposes. Further training
+is ongoing; updated adapters will be released separately.

adapter_config.json

@@ -0,0 +1,44 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "TextMachineProject/NewsBERT_1800-1920",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "value",
+    "word_embeddings",
+    "query"
+  ],
+  "target_parameters": null,
+  "task_type": "FEATURE_EXTRACTION",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8447adc4c704eadfe3b654207ee5718f18f39647e2c68dc69b3383b6faac0b25
+size 4368936