Add new SentenceTransformer model.

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "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,
+  "include_prompt": true
+}

README.md

@@ -0,0 +1,130 @@
+---
+library_name: sentence-transformers
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+- transformers
+
+---
+
+# eunyounglee/EEVE-LLM2VEC-MNTP-STS-qa-2-adapter
+
+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('eunyounglee/EEVE-LLM2VEC-MNTP-STS-qa-2-adapter')
+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('eunyounglee/EEVE-LLM2VEC-MNTP-STS-qa-2-adapter')
+model = AutoModel.from_pretrained('eunyounglee/EEVE-LLM2VEC-MNTP-STS-qa-2-adapter')
+
+# 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=eunyounglee/EEVE-LLM2VEC-MNTP-STS-qa-2-adapter)
+
+
+## Training
+The model was trained with the parameters:
+
+**DataLoader**:
+
+`torch.utils.data.dataloader.DataLoader` of length 251 with parameters:
+```
+{'batch_size': 4, '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": 1,
+    "evaluation_steps": 1000,
+    "evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator",
+    "max_grad_norm": 1,
+    "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
+    "optimizer_params": {
+        "lr": 2e-05
+    },
+    "scheduler": "WarmupLinear",
+    "steps_per_epoch": null,
+    "warmup_steps": 76,
+    "weight_decay": 0.01
+}
+```
+
+
+## Full Model Architecture
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 4096, 'do_lower_case': False}) with Transformer model: LlamaModel 
+  (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, 'include_prompt': True})
+)
+```
+
+## Citing & Authors
+
+<!--- Describe where people can find more information -->

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "eunyounglee/EEVE-LLM2Vec-MNTP-1",
+  "architectures": [
+    "LlamaModel"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 32000,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "use_cache": false,
+  "vocab_size": 40960
+}

config_sentence_transformers.json

@@ -0,0 +1,9 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.7.0",
+    "transformers": "4.40.1",
+    "pytorch": "2.2.1+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null
+}

model-00001-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76533755c58f92a8f5ff727b168615b9113b71ae3501e49a611eefe647b3d2a5
+size 4798419544

model-00002-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8097c205613f534490597262c94c3b018644d75b23ebf13366736e9cca9aff7
+size 4999812760

model-00003-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8b038064bcbf9e166df66f0afedab6e6ab15bb3f0708ea0083440f2d56b7a02
+size 4999812808

model-00004-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66953e479443ee15c45e6bb80280b0422266e86d201638f23b4083090c82ff08
+size 4832007216

model-00005-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5501209f598bf80870b881b9cb4214c7d4f7741a91cca30054742990901350f8
+size 4999812808

model-00006-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c40284baebeb712d10d7fd05fc6e4c84f0d1d28b5cb94e4a4064f0e35ad4990d
+size 4999812808

model-00007-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4b08b8f6b87d3298c5a7c4014365306c48a2f8998e82af23328d2f3cd9e9fbe
+size 4832007216

model-00008-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:839ac986ccdedcb81ed50d5205c8974cc6c41ac2b8ec65f618b2b72fa9d94d37
+size 4999812808

model-00009-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2edc086c3b8e4ee9eb375fd815c1e4902b39229a86889eddee00dd1ae7345c14
+size 3087158696

model.safetensors.index.json

@@ -0,0 +1,441 @@
+{
+  "metadata": {
+    "total_size": 42548609024
+  },
+  "weight_map": {
+    "embed_tokens.weight": "model-00001-of-00009.safetensors",
+    "layers.0.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "layers.0.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.0.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.0.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.0.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "layers.0.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.0.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.0.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.0.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.1.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "layers.1.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.1.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.1.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.1.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "layers.1.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.1.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.1.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.1.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.10.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "layers.10.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.10.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.10.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.10.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "layers.10.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.10.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.10.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.10.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.11.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "layers.11.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.11.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.11.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.11.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "layers.11.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.11.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.11.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.11.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.12.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "layers.12.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.12.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.12.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.12.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "layers.12.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.12.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.12.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.12.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.13.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "layers.13.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.13.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.13.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.13.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "layers.13.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.13.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.13.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.13.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.14.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "layers.14.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.14.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.14.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.14.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "layers.14.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.14.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.14.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.14.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.15.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "layers.15.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.15.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.15.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.15.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "layers.15.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.15.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.15.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.15.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.16.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "layers.16.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.16.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.16.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.16.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "layers.16.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.16.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.16.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.16.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "layers.17.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "layers.17.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.17.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.17.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.17.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "layers.17.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.17.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.17.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.17.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.18.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "layers.18.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.18.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.18.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.18.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "layers.18.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.18.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.18.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.18.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.19.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "layers.19.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.19.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.19.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.19.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "layers.19.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.19.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.19.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.19.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.2.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "layers.2.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.2.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.2.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.2.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "layers.2.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.2.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.2.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.2.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.20.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "layers.20.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.20.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.20.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.20.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "layers.20.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.20.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.20.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.20.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.21.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "layers.21.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.21.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.21.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.21.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "layers.21.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.21.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.21.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.21.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "layers.22.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "layers.22.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.22.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.22.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.22.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "layers.22.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.22.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.22.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.22.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.23.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "layers.23.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.23.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.23.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.23.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "layers.23.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.23.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.23.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.23.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.24.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "layers.24.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.24.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.24.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.24.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "layers.24.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.24.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.24.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.24.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.25.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "layers.25.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.25.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.25.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.25.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "layers.25.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.25.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.25.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.25.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.26.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "layers.26.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.26.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.26.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.26.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "layers.26.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.26.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.26.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.26.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.27.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "layers.27.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.27.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.27.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.27.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "layers.27.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.27.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.27.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.27.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "layers.28.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "layers.28.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.28.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.28.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.28.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "layers.28.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.28.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.28.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.28.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.29.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "layers.29.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.29.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.29.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.29.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "layers.29.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.29.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.29.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.29.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.3.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "layers.3.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.3.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.3.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.3.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "layers.3.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.3.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.3.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.3.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.30.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "layers.30.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.30.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.30.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.30.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "layers.30.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.30.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.30.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.30.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.31.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "layers.31.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.31.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.31.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.31.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "layers.31.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.31.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.31.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.31.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.32.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "layers.32.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.32.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.32.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.32.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "layers.32.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.32.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.32.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.32.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.33.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "layers.33.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.33.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.33.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.33.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "layers.33.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.33.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.33.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.33.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "layers.34.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "layers.34.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.34.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.34.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.34.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "layers.34.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.34.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.34.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.34.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.35.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "layers.35.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.35.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.35.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.35.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "layers.35.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.35.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.35.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.35.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.36.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "layers.36.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.36.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.36.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.36.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "layers.36.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.36.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.36.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.36.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.37.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "layers.37.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.37.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.37.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.37.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "layers.37.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.37.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.37.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.37.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.38.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "layers.38.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.38.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.38.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.38.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "layers.38.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.38.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.38.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.38.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "layers.39.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "layers.39.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.39.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.39.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.39.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "layers.39.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.39.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.39.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.39.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.4.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "layers.4.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.4.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.4.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.4.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "layers.4.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.4.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.4.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.4.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "layers.40.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "layers.40.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.40.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.40.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.40.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "layers.40.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.40.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.40.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.40.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.41.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "layers.41.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.41.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.41.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.41.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "layers.41.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.41.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.41.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.41.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.42.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "layers.42.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.42.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.42.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.42.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "layers.42.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.42.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.42.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.42.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.43.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "layers.43.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.43.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.43.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.43.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "layers.43.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.43.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.43.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.43.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.44.input_layernorm.weight": "model-00009-of-00009.safetensors",
+    "layers.44.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.44.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.44.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.44.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+    "layers.44.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.44.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.44.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.44.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "layers.45.input_layernorm.weight": "model-00009-of-00009.safetensors",
+    "layers.45.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.45.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.45.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.45.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+    "layers.45.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.45.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.45.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.45.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.46.input_layernorm.weight": "model-00009-of-00009.safetensors",
+    "layers.46.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.46.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.46.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.46.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+    "layers.46.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.46.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.46.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.46.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.47.input_layernorm.weight": "model-00009-of-00009.safetensors",
+    "layers.47.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.47.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.47.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.47.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+    "layers.47.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.47.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.47.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.47.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
+    "layers.5.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "layers.5.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.5.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.5.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.5.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "layers.5.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.5.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.5.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.5.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.6.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "layers.6.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.6.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.6.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.6.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "layers.6.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.6.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.6.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.6.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.7.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "layers.7.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.7.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.7.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.7.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "layers.7.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.7.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.7.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.7.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.8.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "layers.8.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.8.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.8.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.8.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "layers.8.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.8.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.8.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.8.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.9.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "layers.9.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.9.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.9.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.9.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "layers.9.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.9.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.9.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "layers.9.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "norm.weight": "model-00009-of-00009.safetensors"
+  }
+}

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 4096,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "_",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,62 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "28730": {
+      "content": "_",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = 'You are a helpful assistant.' %}{% endif %}{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in loop_messages %}{% if loop.index0 == 0 %}{{'<|im_start|>system\n' + system_message + '<|im_end|>\n'}}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "legacy": true,
+  "mask_token": "_",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}