upload model

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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

@@ -1,3 +1,56 @@
----
-license: apache-2.0
----
+# RankingGPT-bloom-560m
+
+RankingGPT is a text ranker based on large language models with significant in-domain and out-domain effectiveness.
+We provide RankingGPT in different sizes and types, including bloom-560m, bloom-1b1, bloom-3b, bloom-7b, llama2-7b, baichuan2-7b and qwen-7b.
+
+More details please refer to our [paper](https://arxiv.org/abs/2311.16720) and [github](https://github.com/Alibaba-NLP/RankingGPT).
+
+
+## Usage
+
+Code example
+```python
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+tokenizer = AutoTokenizer.from_pretrained('RankingGPT-bloom-560m')
+model = AutoModelForCausalLM.from_pretrained('RankingGPT-bloom-560m').eval()
+
+query='when should a baby walk'
+document='Most babies start to walk around 13 months, but your baby may start walking as early as 9 or 10 months or as late as 15 or 16 months.'
+
+context=f'Document: {document} Query:'
+example=context+query
+
+context_enc = tokenizer.encode(context, add_special_tokens=False)
+continuation_enc = tokenizer.encode(query, add_special_tokens=False)
+model_input = torch.tensor(context_enc+continuation_enc[:-1])
+continuation_len = len(continuation_enc)
+input_len, = model_input.shape
+
+
+with torch.no_grad():
+    logprobs = torch.nn.functional.log_softmax(model(model_input.unsqueeze(dim=0))[0], dim=-1)[0]
+
+logprobs = logprobs[input_len-continuation_len:]
+logprobs = torch.gather(logprobs, 1, torch.tensor(continuation_enc).unsqueeze(-1)).squeeze(-1)
+score = torch.sum(logprobs)/logprobs.shape[0]
+
+print(f"Document: {document[:20] + '...'} Score: {score}")
+```
+
+
+### Citation
+
+If you find our paper or models helpful, please consider citing them as follows:
+
+```
+@misc{zhang2023rankinggpt,
+      title={RankingGPT: Empowering Large Language Models in Text Ranking with Progressive Enhancement}, 
+      author={Longhui Zhang and Yanzhao Zhang and Dingkun Long and Pengjun Xie and Meishan Zhang and Min Zhang},
+      year={2023},
+      eprint={2311.16720},
+      archivePrefix={arXiv},
+      primaryClass={cs.IR}
+}
+```

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "bigscience/bloom-560m",
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "BloomForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "attention_softmax_in_fp32": true,
+  "bias_dropout_fusion": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "masked_softmax_fusion": true,
+  "model_type": "bloom",
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "offset_alibi": 100,
+  "pad_token_id": 3,
+  "pretraining_tp": 1,
+  "skip_bias_add": true,
+  "skip_bias_add_qkv": false,
+  "slow_but_exact": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.29.0",
+  "unk_token_id": 0,
+  "use_cache": true,
+  "vocab_size": 250880
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 3,
+  "transformers_version": "4.29.0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daff937349f9c8bbc30bb810544328c0fa1bb4ba95537c32d08b3696e744d2fd
+size 2236951031

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f6efc66e73f1fd69da4f436e48befb519fdff3fe18910850c1d41bd862293a5
+size 14500443

tokenizer_config.json

@@ -0,0 +1,11 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "tokenizer_class": "BloomTokenizer",
+  "unk_token": "<unk>"
+}