Initial commit

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+    "word_embedding_dimension": 4096,
+    "pooling_mode_cls_token": false,
+    "pooling_mode_mean_tokens": false,
+    "pooling_mode_max_tokens": false,
+    "pooling_mode_mean_sqrt_len_tokens": false,
+    "pooling_mode_weightedmean_tokens": false,
+    "pooling_mode_lasttoken": true,
+    "include_prompt": true
+}

README.md

@@ -1,3 +1,51 @@
----
-license: apache-2.0
----
+---
+language:
+- en
+license: apache-2.0
+tags:
+- sentence-transformers
+- sentence-similarity
+- transformers
+---
+
+## LGAI-Embedding-Preview
+
+we have trained the **LGAI-Embedding-Preview** model based on the [Mistral-7B](https://huggingface.co/mistralai/Mistral-7B-v0.1) LLM model.
+
+The initial goal is to reproduce the baseline model and check the workflow for uploading results:
+  - [x] Checkpoint
+  - [x] technical report
+
+
+## MTEB
+Inference is performed with in-context examples for MTEB evaluation.
+
+
+## Model Information
+- Model Size: 7B
+- Embedding Dimension: 4096
+- Max Input Tokens: 32k
+
+
+## Requirements
+```
+transformers>=4.48.3
+```
+
+
+## Citation
+
+If you find this repository useful, please consider citing it.
+
+
+```
+@misc{choi2025lgannaembeddingtechnicalreport,
+      title={LG-ANNA-Embedding technical report}, 
+      author={Jooyoung Choi and Hyun Kim and Hansol Jang and Changwook Jun and Kyunghoon Bae and Hyewon Choi and Stanley Jungkyu Choi and Honglak Lee and Chulmin Yun},
+      year={2025},
+      eprint={2506.07438},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2506.07438}, 
+}
+```

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<instruct>": 32000,
+  "<query>": 32001,
+  "<response>": 32002
+}

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "annamodels/LGAI-Embedding-Preview",
+  "architectures": [
+    "MistralModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.3",
+  "use_cache": false,
+  "vocab_size": 32003
+}

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:905969f8e44d3048179116fa2d92d8399e571bfe1c62a998c278aa13a0c6f86b
+size 4987245800

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:088a1c08fb9b591e0345f81c5b312bde2ccc75f4076e289bcbaa0e38bc3d8927
+size 4899116152

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e74625bbe91c13246e296d5956efbf86f2ef7f7cc1121f06e208948d654571b
+size 4999812808

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:836e2a453ba9d7d05cbdbb86a9f679e12ca3bc7d6af35ee26268091fb831dbe5
+size 4999812808

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f65d3e53c9f663999542686e06e22dc6d5638d676a12e33266469038a9c871b5
+size 4832007216

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d4558cf8e74e91ce01b46055591c83ac5c2879db9a1b67c0a4670864b52bdea
+size 3724726552

model.safetensors.index.json

@@ -0,0 +1,297 @@
+{
+  "metadata": {
+    "total_size": 28442689536
+  },
+  "weight_map": {
+    "embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.10.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "layers.10.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.10.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "layers.11.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.11.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.11.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.11.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.16.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "layers.16.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.16.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.16.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.17.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "layers.17.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.17.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.17.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.17.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "layers.19.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.19.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.22.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "layers.22.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.22.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.22.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.22.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.23.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "layers.23.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.23.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.23.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.23.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.24.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "layers.25.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.27.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "layers.27.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.27.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.28.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "layers.28.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.28.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.28.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.28.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "layers.28.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.28.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.28.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.28.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.29.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.29.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.29.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "layers.29.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.29.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.29.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.29.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.30.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "layers.30.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.30.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.30.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.30.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "layers.30.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.30.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.30.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.30.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.31.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "layers.31.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.31.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.31.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "layers.31.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.31.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.5.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "norm.weight": "model-00006-of-00006.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": 32768,
+    "do_lower_case": false
+  }

special_tokens_map.json

@@ -0,0 +1,35 @@
+{
+  "additional_special_tokens": [
+    "<instruct>",
+    "<query>",
+    "<response>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,72 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": true,
+  "add_prefix_space": true,
+  "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
+    },
+    "32000": {
+      "content": "<instruct>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<query>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<instruct>",
+    "<query>",
+    "<response>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 32768,
+  "pad_token": "<unk>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}