0311

1_Pooling/config.json

@@ -0,0 +1,9 @@
+{
+ "word_embedding_dimension": 4096,
+ "pooling_mode_cls_token": false,
+ "pooling_mode_mean_tokens": true,
+ "pooling_mode_max_tokens": false,
+ "pooling_mode_mean_sqrt_len_tokens": false,
+ "pooling_mode_weightedmean_tokens": false,
+ "pooling_mode_lasttoken": false
+}

README.md

@@ -0,0 +1,128 @@
+---
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+- transformers
+---
+
+# {MODEL_NAME}
+
+This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 4096 dimensional dense vector space and can be used for tasks like clustering or semantic search.
+
+<!--- Describe your model here -->
+
+## Usage (Sentence-Transformers)
+
+Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
+
+```
+pip install -U sentence-transformers
+```
+
+Then you can use the model like this:
+
+```python
+from sentence_transformers import SentenceTransformer
+sentences = ["This is an example sentence", "Each sentence is converted"]
+
+model = SentenceTransformer('{MODEL_NAME}')
+embeddings = model.encode(sentences)
+print(embeddings)
+```
+
+
+
+## Usage (HuggingFace Transformers)
+Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
+
+```python
+from transformers import AutoTokenizer, AutoModel
+import torch
+
+
+#Mean Pooling - Take attention mask into account for correct averaging
+def mean_pooling(model_output, attention_mask):
+ token_embeddings = model_output[0] #First element of model_output contains all token embeddings
+ input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
+ return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
+
+
+# Sentences we want sentence embeddings for
+sentences = ['This is an example sentence', 'Each sentence is converted']
+
+# Load model from HuggingFace Hub
+tokenizer = AutoTokenizer.from_pretrained('{MODEL_NAME}')
+model = AutoModel.from_pretrained('{MODEL_NAME}')
+
+# Tokenize sentences
+encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
+
+# Compute token embeddings
+with torch.no_grad():
+ model_output = model(**encoded_input)
+
+# Perform pooling. In this case, mean pooling.
+sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
+
+print("Sentence embeddings:")
+print(sentence_embeddings)
+```
+
+
+
+## Evaluation Results
+
+<!--- Describe how your model was evaluated -->
+
+For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
+
+
+## Training
+The model was trained with the parameters:
+
+**DataLoader**:
+
+`torch.utils.data.dataloader.DataLoader` of length 32 with parameters:
+```
+{'batch_size': 2, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
+```
+
+**Loss**:
+
+`sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss` with parameters:
+ ```
+ {'scale': 20.0, 'similarity_fct': 'cos_sim'}
+ ```
+
+Parameters of the fit()-Method:
+```
+{
+ "epochs": 5,
+ "evaluation_steps": 0,
+ "evaluator": "NoneType",
+ "max_grad_norm": 1,
+ "optimizer_class": "<class 'transformers.optimization.AdamW'>",
+ "optimizer_params": {
+ "lr": 5e-05
+ },
+ "scheduler": "WarmupLinear",
+ "steps_per_epoch": null,
+ "warmup_steps": 1000,
+ "weight_decay": 0.01
+}
+```
+
+
+## Full Model Architecture
+```
+SentenceTransformer(
+ (0): Transformer({'max_seq_length': 300, 'do_lower_case': False}) with Transformer model: GPTNeoXModel 
+ (1): Pooling({'word_embedding_dimension': 4096, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False})
+)
+```
+
+## Citing & Authors
+
+<!--- Describe where people can find more information -->

config.json

@@ -0,0 +1,27 @@
+{
+ "_name_or_path": "/volume/SGPT-trained/SGPT-5.8B-ezct-genq-4k-epoch5/",
+ "architectures": [
+ "GPTNeoXModel"
+ ],
+ "bos_token_id": 0,
+ "classifier_dropout": 0.1,
+ "eos_token_id": 2,
+ "hidden_act": "gelu",
+ "hidden_size": 4096,
+ "initializer_range": 0.02,
+ "intermediate_size": 16384,
+ "layer_norm_eps": 1e-05,
+ "max_position_embeddings": 2048,
+ "model_type": "gpt_neox",
+ "num_attention_heads": 16,
+ "num_hidden_layers": 28,
+ "num_steps": "global_step320000",
+ "rotary_emb_base": 10000,
+ "rotary_pct": 0.25,
+ "tie_word_embeddings": false,
+ "torch_dtype": "float32",
+ "transformers_version": "4.25.1",
+ "use_cache": true,
+ "use_parallel_residual": true,
+ "vocab_size": 30080
+}

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+ "__version__": {
+ "sentence_transformers": "2.1.0",
+ "transformers": "4.25.1",
+ "pytorch": "2.0.1"
+ }
+}

modules.json

@@ -0,0 +1,14 @@
+[
+ {
+ "idx": 0,
+ "name": "0",
+ "path": "",
+ "type": "deepsearfing.modeling.SGPT_training.sgpt.biencoder.nli_msmarco.sentence_transformers.sentence_transformers.models.Transformer"
+ },
+ {
+ "idx": 1,
+ "name": "1",
+ "path": "1_Pooling",
+ "type": "deepsearfing.modeling.SGPT_training.sgpt.biencoder.nli_msmarco.sentence_transformers.sentence_transformers.models.Pooling"
+ }
+]

pytorch_model-00001-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60ba91af0aea1317469af1183d5c7de2138699a983aa560c69b29bc9d05926b9
+size 9941007112

pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5e6450bb1cc573b8e495496be89cf96cbabe5f78ec9c1c33ee8507f99b70bd
+size 9989343734

pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a5890b7d46c8e1f33d28274744a521ec27e584f005005fbe81598a8ae7ee693
+size 3234646701

pytorch_model.bin.index.json

@@ -0,0 +1,430 @@
+{
+ "metadata": {
+ "total_size": 23164849776
+ },
+ "weight_map": {
+ "embed_in.weight": "pytorch_model-00001-of-00003.bin",
+ "final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
+ "final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
+ "layers.0.attention.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.0.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.0.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.0.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
+ "layers.0.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.0.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.0.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+ "layers.0.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.1.attention.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.1.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.1.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.1.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
+ "layers.1.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.1.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.1.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+ "layers.1.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.1.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.1.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.10.attention.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.10.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.10.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.10.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
+ "layers.10.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.10.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.10.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+ "layers.10.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.10.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.10.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.10.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.10.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.11.attention.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.11.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.11.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.11.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
+ "layers.11.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.11.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.11.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+ "layers.11.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.11.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.11.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.11.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.11.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.12.attention.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.12.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.12.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.12.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
+ "layers.12.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.12.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.12.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+ "layers.12.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.12.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.12.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.12.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.13.attention.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.13.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.13.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.13.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
+ "layers.13.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.13.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.13.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+ "layers.13.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.13.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.13.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.13.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.14.attention.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.14.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.14.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.14.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
+ "layers.14.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.14.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.14.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+ "layers.14.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.14.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.14.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.14.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.15.attention.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.15.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.15.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.15.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
+ "layers.15.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.15.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.15.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+ "layers.15.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.15.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.15.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.15.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.15.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.16.attention.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.16.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.16.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.16.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
+ "layers.16.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.16.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.16.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+ "layers.16.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.16.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.16.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.16.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.16.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.16.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.17.attention.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.17.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.17.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.17.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
+ "layers.17.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.17.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.17.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+ "layers.17.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.17.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.17.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.17.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.17.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.17.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.18.attention.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.18.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.18.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.18.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
+ "layers.18.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.18.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.18.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+ "layers.18.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.18.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.18.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.18.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.18.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.18.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.19.attention.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.19.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.19.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.19.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
+ "layers.19.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.19.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.19.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+ "layers.19.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.19.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.19.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.19.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.19.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.19.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.2.attention.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.2.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.2.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.2.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
+ "layers.2.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.2.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.2.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+ "layers.2.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.2.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.2.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.20.attention.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.20.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.20.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.20.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
+ "layers.20.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.20.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.20.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+ "layers.20.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.20.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.20.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.20.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.20.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.20.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.21.attention.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.21.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.21.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.21.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
+ "layers.21.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.21.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.21.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+ "layers.21.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.21.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.21.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.21.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.21.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.21.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.22.attention.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.22.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.22.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.22.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
+ "layers.22.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.22.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.22.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+ "layers.22.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.22.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.22.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.22.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.22.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.22.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.23.attention.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.23.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.23.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.23.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
+ "layers.23.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.23.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.23.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+ "layers.23.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.23.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.23.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.23.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.23.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.23.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.23.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.24.attention.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.24.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
+ "layers.24.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+ "layers.24.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
+ "layers.24.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
+ "layers.24.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+ "layers.24.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+ "layers.24.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.24.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.24.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
+ "layers.24.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+ "layers.24.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
+ "layers.24.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
+ "layers.24.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+ "layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+ "layers.25.attention.bias": "pytorch_model-00003-of-00003.bin",
+ "layers.25.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
+ "layers.25.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+ "layers.25.attention.masked_bias": "pytorch_model-00003-of-00003.bin",
+ "layers.25.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
+ "layers.25.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+ "layers.25.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+ "layers.25.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+ "layers.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+ "layers.25.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
+ "layers.25.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+ "layers.25.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
+ "layers.25.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
+ "layers.25.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+ "layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+ "layers.26.attention.bias": "pytorch_model-00003-of-00003.bin",
+ "layers.26.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
+ "layers.26.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+ "layers.26.attention.masked_bias": "pytorch_model-00003-of-00003.bin",
+ "layers.26.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
+ "layers.26.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+ "layers.26.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+ "layers.26.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+ "layers.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+ "layers.26.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
+ "layers.26.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+ "layers.26.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
+ "layers.26.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
+ "layers.26.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+ "layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+ "layers.27.attention.bias": "pytorch_model-00003-of-00003.bin",
+ "layers.27.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
+ "layers.27.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+ "layers.27.attention.masked_bias": "pytorch_model-00003-of-00003.bin",
+ "layers.27.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
+ "layers.27.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+ "layers.27.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+ "layers.27.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+ "layers.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+ "layers.27.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
+ "layers.27.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+ "layers.27.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
+ "layers.27.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
+ "layers.27.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+ "layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+ "layers.3.attention.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.3.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.3.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.3.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
+ "layers.3.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.3.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.3.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+ "layers.3.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.3.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.3.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.4.attention.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.4.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.4.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.4.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
+ "layers.4.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.4.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.4.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+ "layers.4.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.4.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.4.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.5.attention.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.5.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.5.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.5.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
+ "layers.5.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.5.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.5.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+ "layers.5.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.5.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.5.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.5.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.6.attention.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.6.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.6.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.6.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
+ "layers.6.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.6.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.6.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+ "layers.6.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.6.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.6.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.6.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.6.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.7.attention.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.7.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.7.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.7.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
+ "layers.7.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.7.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.7.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+ "layers.7.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.7.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.7.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.7.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.7.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.7.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.8.attention.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.8.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.8.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.8.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
+ "layers.8.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.8.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.8.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+ "layers.8.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.8.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.8.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.8.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.8.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.8.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.9.attention.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.9.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.9.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.9.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
+ "layers.9.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.9.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.9.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+ "layers.9.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.9.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.9.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.9.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.9.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+ "layers.9.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+ "layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin"
+ }
+}

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+ "max_seq_length": 300,
+ "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,11 @@
+{
+ "additional_special_tokens": [
+ "<|endoftext|>",
+ "<|sep|>",
+ "<|acc|>",
+ "<|tel|>",
+ "<|rrn|>"
+ ],
+ "eos_token": "<|endoftext|>",
+ "pad_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+ "clean_up_tokenization_spaces": true,
+ "eos_token": "<|endoftext|>",
+ "model_max_length": 1000000000000000019884624838656,
+ "name_or_path": "/volume/SGPT-trained/SGPT-5.8B-ezct-genq-4k-epoch5/",
+ "pad_token": "<|endoftext|>",
+ "special_tokens_map_file": "/volume/SGPT-5.8B-wiki-mirae-epoch5/special_tokens_map.json",
+ "tokenizer_class": "PreTrainedTokenizerFast"
+}