First commit

README.md

@@ -1,3 +1,57 @@
+
+# TRL Model
+
+This is a [TRL language model](https://github.com/huggingface/trl) that has been fine-tuned with reinforcement learning to guide the model outputs according to a value, function, or human feedback. The model can be used for text generation.
+
+## Usage
+
+This model is a part of a study explained here on document expansion using Doc2Query. Please cite the paper if you use it.
+To use this model for inference, first install the TRL library:
+
+```bash
+pip install trl
+```
+
+You can then generate text as follows:
+
+```python
+from transformers import pipeline
+
+generator = pipeline("text-generation", model="watheq/d2q_monoELECTRA_1400")
+outputs = generator("Hello, my llama is cute")
+```
+
+If you want to use the model for training or to obtain the outputs from the value head, load the model as follows:
+
+```python
+from transformers import AutoTokenizer
+from trl import AutoModelForCausalLMWithValueHead
+
+tokenizer = AutoTokenizer.from_pretrained("watheq/d2q_monoELECTRA_1400")
+model = AutoModelForCausalLMWithValueHead.from_pretrained("watheq/d2q_monoELECTRA_1400")
+
+inputs = tokenizer("Coffee is a beverage brewed from roasted coffee beans. Coffee has a stimulating effect on humans, primarily due to its caffeine content.", return_tensors="pt")
+outputs = model(**inputs, labels=inputs["input_ids"])
+```
+
+
+
+## Citation
+
+If you used any piece of this repository, please consider citing our work :
+
+```plaintext
+@inproceedings{mansour2024revisit,
+  title={Revisiting Document Expansion and Filtering for Effective First-Stage Retrieval},
+  author={Mansour, Watheq and Zhuang, Shengyao and Zhuang, Guido and Mackenzie, Joel},
+  booktitle = {Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval},
+  year={2024},
+  publisher = {Association for Computing Machinery},
+  series = {SIGIR '24}
+}
+```
+
+
 ---
 license: cc-by-4.0
 ---

config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "castorini/doc2query-t5-base-msmarco",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 3072,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "relu",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "relu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": false,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 200,
+      "min_length": 30,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "summarize: "
+    },
+    "translation_en_to_de": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to German: "
+    },
+    "translation_en_to_fr": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to French: "
+    },
+    "translation_en_to_ro": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to Romanian: "
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 32128
+}