Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,15 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+imgs/bright-performance.png filter=lfs diff=lfs merge=lfs -text
+search_results/examples/biology-examples.json filter=lfs diff=lfs merge=lfs -text
+search_results/examples/earth_science-examples.json filter=lfs diff=lfs merge=lfs -text
+search_results/examples/economics-examples.json filter=lfs diff=lfs merge=lfs -text
+search_results/examples/leetcode-examples.json filter=lfs diff=lfs merge=lfs -text
+search_results/examples/pony-examples.json filter=lfs diff=lfs merge=lfs -text
+search_results/examples/psychology-examples.json filter=lfs diff=lfs merge=lfs -text
+search_results/examples/robotics-examples.json filter=lfs diff=lfs merge=lfs -text
+search_results/examples/stackoverflow-examples.json filter=lfs diff=lfs merge=lfs -text
+search_results/examples/sustainable_living-examples.json filter=lfs diff=lfs merge=lfs -text
+search_results/examples/theoremqa_questions-examples.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

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

@@ -0,0 +1,182 @@
+---
+tags:
+- feature-extraction
+- sentence-similarity
+- sentence-transformers
+- transformers
+license: apache-2.0
+---
+
+
+<div align="center">
+<h1> ReasonEmbed: Enhanced Text Embeddings for Reasoning-Intensive Document Retrieval </h1>
+</div>
+
+<p align="center">
+  <a href="https://arxiv.org/abs/2510.08252" target="_blank" rel="noopener noreferrer">
+    <img src="https://img.shields.io/badge/arXiv-2510.08252-B31B1B.svg?style=flat-square&logo=arxiv&logoColor=white" alt="arXiv:2510.08252">
+  </a>
+</p>
+
+We propose **ReasonEmbed**, a new text embedding model for reasoning-intensive document retrieval based on innovations of how synthetic data is generated and used. For more details please refer to our Github: [ReasonEmbed](https://github.com/VectorSpaceLab/agentic-search/tree/main/ReasonEmbed) and our [paper](https://arxiv.org/abs/2510.08252).
+
+
+## Introduction
+
+This repository hosts the model **reason-embed-basic-qwen3-8b-0928**, which is fine-tuned based on [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) using the basic InfoNCE loss on our synthetic dataset. It achieves an nDCG@10 of 37.1 on the [BRIGHT](https://brightbenchmark.github.io/) benchmark with original query, demonstrating its strong capability in reasoning-intensive retrieval tasks.
+
+The search results on BRIGHT are available [here](./search_results/examples/). We also provide the evaluation [script](./evaluation_scripts/eval_bright_short.sh) to reproduce the results.
+
+![bright-performance](./imgs/bright-performance.png)
+
+## Usage 
+
+### Using FlagEmbedding
+```
+git clone https://github.com/FlagOpen/FlagEmbedding.git
+cd FlagEmbedding
+pip install -e .
+```
+
+```python
+from FlagEmbedding import FlagLLMModel
+queries = [
+    # taken from BRIGHT TheoT dataset, qid: examples-TheoremQA_wenhuchen/eigen_value1.json
+    "Imagine you have a magical box that transforms any object you put inside it, where the object is represented by the column vector x = (x_1, x_2). The box's transformation can be represented by the matrix A = [[5, 4], [1, 2]], so when given an object x, the box outputs the new object Ax. On some special objects, this new object is just a constant multiple of the original object, λx = (λx_1, λx_2). Find both possible values of λ where this occurs — note that these are the box's eigenvalues.",
+    # taken from BRIGHT TheoT dataset, qid: examples-TheoremQA_maxku/ipnetwork13-hammingdist.json
+    "Imagine you're comparing three digital images that are extremely simplified down to a grid of 5 pixels each, represented by either black (0) or white (1) pixels. The images are as follows: Image A: 00000, Image B: 10101, and Image C: 01010. By counting the number of pixels that differ between each pair of images, find the smallest number of differing pixels."
+]
+documents = [
+    # taken from BRIGHT TheoT dataset, docid: 2723
+    "\\begin{definition}[Definition:Eigenvector/Linear Operator]\nLet $K$ be a field.\nLet $V$ be a vector space over $K$. \nLet $A : V \\to V$ be a linear operator.\nLet $\\lambda \\in K$ be an eigenvalue of $A$.\nA non-zero vector $v \\in V$ is an '''eigenvector corresponding to $\\lambda$''' {{iff}}:\n:$v \\in \\map \\ker {A - \\lambda I}$\nwhere: \n:$I : V \\to V$ is the identity mapping on $V$\n:$\\map \\ker {A - \\lambda I}$ denotes the kernel of $A - \\lambda I$.\nThat is, {{iff}}: \n:$A v = \\lambda v$\n\\end{definition}",
+    # taken from BRIGHT TheoT dataset, docid: 14101
+    "\\section{Error Correction Capability of Linear Code}\nTags: Linear Codes\n\n\\begin{theorem}\nLet $C$ be a linear code.\nLet $C$ have a minimum distance $d$.\nThen $C$ corrects $e$ transmission errors for all $e$ such that $2 e + 1 \\le d$.\n\\end{theorem}\n\n\\begin{proof}\nLet $C$ be a linear code whose master code is $V$.\nLet $c \\in C$ be a transmitted codeword.\nLet $v$ be the received word from $c$.\nBy definition, $v$ is an element of $V$.\nLet $v$ have a distance $e$ from $c$, where $2 e + 1 \\le d$.\nThus there have been $e$ transmission errors.\n{{AimForCont}} $c_1$ is a codeword of $C$, distinct from $c$, such that $\\map d {v, c_1} \\le e$.\nThen:\n{{begin-eqn}}\n{{eqn | l = \\map d {c, c_1}\n      | o = \\le\n      | r = \\map d {c, v} + \\map d {v, c_1}\n      | c = \n}}\n{{eqn | o = \\le\n      | r = e + e\n      | c = \n}}\n{{eqn | o = <\n      | r = d\n      | c = \n}}\n{{end-eqn}}\nSo $c_1$ has a distance from $c$ less than $d$.\nBut $C$ has a minimum distance $d$.\nThus $c_1$ cannot be a codeword of $C$.\nFrom this contradiction it follows that there is no codeword of $C$ closer to $v$ than $c$.\nHence there is a unique codeword of $C$ which has the smallest distance from $v$.\nHence it can be understood that $C$ has corrected the transmission errors of $v$.\n{{Qed}}\n\\end{proof}\n\n"
+]
+model = FlagLLMModel("hanhainebula/reason-embed-basic-qwen3-8b-0928", 
+                     query_instruction_for_retrieval="Given a Math problem, retrieve relevant theorems that help answer the problem.",
+                     query_instruction_format="Instruct: {}\nQuery: {}",
+                     devices="cuda:0",  # set devices to "cuda:0" for testing on a single GPU
+                     use_fp16=True) # Setting use_fp16 to True speeds up computation with a slight performance degradation
+embeddings_1 = model.encode_queries(queries)
+embeddings_2 = model.encode_corpus(documents)
+similarity = embeddings_1 @ embeddings_2.T
+print(similarity)
+```
+
+
+### Using Sentence Transformers
+
+```python
+from sentence_transformers import SentenceTransformer
+import torch
+
+# Load the model, optionally in float16 precision for faster inference
+model = SentenceTransformer("hanhainebula/reason-embed-basic-qwen3-8b-0928", model_kwargs={"torch_dtype": torch.float16})
+
+
+queries = [
+    # taken from BRIGHT TheoT dataset, qid: examples-TheoremQA_wenhuchen/eigen_value1.json
+    "Imagine you have a magical box that transforms any object you put inside it, where the object is represented by the column vector x = (x_1, x_2). The box's transformation can be represented by the matrix A = [[5, 4], [1, 2]], so when given an object x, the box outputs the new object Ax. On some special objects, this new object is just a constant multiple of the original object, λx = (λx_1, λx_2). Find both possible values of λ where this occurs — note that these are the box's eigenvalues.",
+    # taken from BRIGHT TheoT dataset, qid: examples-TheoremQA_maxku/ipnetwork13-hammingdist.json
+    "Imagine you're comparing three digital images that are extremely simplified down to a grid of 5 pixels each, represented by either black (0) or white (1) pixels. The images are as follows: Image A: 00000, Image B: 10101, and Image C: 01010. By counting the number of pixels that differ between each pair of images, find the smallest number of differing pixels."
+]
+documents = [
+    # taken from BRIGHT TheoT dataset, docid: 2723
+    "\\begin{definition}[Definition:Eigenvector/Linear Operator]\nLet $K$ be a field.\nLet $V$ be a vector space over $K$. \nLet $A : V \\to V$ be a linear operator.\nLet $\\lambda \\in K$ be an eigenvalue of $A$.\nA non-zero vector $v \\in V$ is an '''eigenvector corresponding to $\\lambda$''' {{iff}}:\n:$v \\in \\map \\ker {A - \\lambda I}$\nwhere: \n:$I : V \\to V$ is the identity mapping on $V$\n:$\\map \\ker {A - \\lambda I}$ denotes the kernel of $A - \\lambda I$.\nThat is, {{iff}}: \n:$A v = \\lambda v$\n\\end{definition}",
+    # taken from BRIGHT TheoT dataset, docid: 14101
+    "\\section{Error Correction Capability of Linear Code}\nTags: Linear Codes\n\n\\begin{theorem}\nLet $C$ be a linear code.\nLet $C$ have a minimum distance $d$.\nThen $C$ corrects $e$ transmission errors for all $e$ such that $2 e + 1 \\le d$.\n\\end{theorem}\n\n\\begin{proof}\nLet $C$ be a linear code whose master code is $V$.\nLet $c \\in C$ be a transmitted codeword.\nLet $v$ be the received word from $c$.\nBy definition, $v$ is an element of $V$.\nLet $v$ have a distance $e$ from $c$, where $2 e + 1 \\le d$.\nThus there have been $e$ transmission errors.\n{{AimForCont}} $c_1$ is a codeword of $C$, distinct from $c$, such that $\\map d {v, c_1} \\le e$.\nThen:\n{{begin-eqn}}\n{{eqn | l = \\map d {c, c_1}\n      | o = \\le\n      | r = \\map d {c, v} + \\map d {v, c_1}\n      | c = \n}}\n{{eqn | o = \\le\n      | r = e + e\n      | c = \n}}\n{{eqn | o = <\n      | r = d\n      | c = \n}}\n{{end-eqn}}\nSo $c_1$ has a distance from $c$ less than $d$.\nBut $C$ has a minimum distance $d$.\nThus $c_1$ cannot be a codeword of $C$.\nFrom this contradiction it follows that there is no codeword of $C$ closer to $v$ than $c$.\nHence there is a unique codeword of $C$ which has the smallest distance from $v$.\nHence it can be understood that $C$ has corrected the transmission errors of $v$.\n{{Qed}}\n\\end{proof}\n\n"
+]
+
+query_embeddings = model.encode(queries, prompt="Instruct: Given a Math problem, retrieve relevant theorems that help answer the problem.\nQuery: ")
+document_embeddings = model.encode(documents)
+
+# Compute the (cosine) similarity between the query and document embeddings
+similarity = model.similarity(query_embeddings, document_embeddings)
+print(similarity)
+```
+
+
+### Using HuggingFace Transformers
+```python
+import torch
+import torch.nn.functional as F
+
+from torch import Tensor
+from transformers import AutoTokenizer, AutoModel
+
+
+def last_token_pool(last_hidden_states: Tensor,
+                 attention_mask: Tensor) -> Tensor:
+    left_padding = (attention_mask[:, -1].sum() == attention_mask.shape[0])
+    if left_padding:
+        return last_hidden_states[:, -1]
+    else:
+        sequence_lengths = attention_mask.sum(dim=1) - 1
+        batch_size = last_hidden_states.shape[0]
+        return last_hidden_states[torch.arange(batch_size, device=last_hidden_states.device), sequence_lengths]
+
+
+def get_detailed_instruct(task_description: str, query: str) -> str:
+    return f'Instruct: {task_description}\nQuery: {query}'
+
+
+def tokenize_texts(tokenizer, texts, max_length: int, device: str):
+    batch_dict = tokenizer(texts, max_length=max_length, padding=True, truncation=True, return_tensors='pt', pad_to_multiple_of=8)
+    batch_dict = {k: v.to(device) for k, v in batch_dict.items()}
+    return batch_dict
+
+
+task = 'Given a Math problem, retrieve relevant theorems that help answer the problem.'
+queries = [
+    # taken from BRIGHT TheoT dataset, qid: examples-TheoremQA_wenhuchen/eigen_value1.json
+    "Imagine you have a magical box that transforms any object you put inside it, where the object is represented by the column vector x = (x_1, x_2). The box's transformation can be represented by the matrix A = [[5, 4], [1, 2]], so when given an object x, the box outputs the new object Ax. On some special objects, this new object is just a constant multiple of the original object, λx = (λx_1, λx_2). Find both possible values of λ where this occurs — note that these are the box's eigenvalues.",
+    # taken from BRIGHT TheoT dataset, qid: examples-TheoremQA_maxku/ipnetwork13-hammingdist.json
+    "Imagine you're comparing three digital images that are extremely simplified down to a grid of 5 pixels each, represented by either black (0) or white (1) pixels. The images are as follows: Image A: 00000, Image B: 10101, and Image C: 01010. By counting the number of pixels that differ between each pair of images, find the smallest number of differing pixels."
+]
+queries = [get_detailed_instruct(task, q) for q in queries]
+documents = [
+    # taken from BRIGHT TheoT dataset, docid: 2723
+    "\\begin{definition}[Definition:Eigenvector/Linear Operator]\nLet $K$ be a field.\nLet $V$ be a vector space over $K$. \nLet $A : V \\to V$ be a linear operator.\nLet $\\lambda \\in K$ be an eigenvalue of $A$.\nA non-zero vector $v \\in V$ is an '''eigenvector corresponding to $\\lambda$''' {{iff}}:\n:$v \\in \\map \\ker {A - \\lambda I}$\nwhere: \n:$I : V \\to V$ is the identity mapping on $V$\n:$\\map \\ker {A - \\lambda I}$ denotes the kernel of $A - \\lambda I$.\nThat is, {{iff}}: \n:$A v = \\lambda v$\n\\end{definition}",
+    # taken from BRIGHT TheoT dataset, docid: 14101
+    "\\section{Error Correction Capability of Linear Code}\nTags: Linear Codes\n\n\\begin{theorem}\nLet $C$ be a linear code.\nLet $C$ have a minimum distance $d$.\nThen $C$ corrects $e$ transmission errors for all $e$ such that $2 e + 1 \\le d$.\n\\end{theorem}\n\n\\begin{proof}\nLet $C$ be a linear code whose master code is $V$.\nLet $c \\in C$ be a transmitted codeword.\nLet $v$ be the received word from $c$.\nBy definition, $v$ is an element of $V$.\nLet $v$ have a distance $e$ from $c$, where $2 e + 1 \\le d$.\nThus there have been $e$ transmission errors.\n{{AimForCont}} $c_1$ is a codeword of $C$, distinct from $c$, such that $\\map d {v, c_1} \\le e$.\nThen:\n{{begin-eqn}}\n{{eqn | l = \\map d {c, c_1}\n      | o = \\le\n      | r = \\map d {c, v} + \\map d {v, c_1}\n      | c = \n}}\n{{eqn | o = \\le\n      | r = e + e\n      | c = \n}}\n{{eqn | o = <\n      | r = d\n      | c = \n}}\n{{end-eqn}}\nSo $c_1$ has a distance from $c$ less than $d$.\nBut $C$ has a minimum distance $d$.\nThus $c_1$ cannot be a codeword of $C$.\nFrom this contradiction it follows that there is no codeword of $C$ closer to $v$ than $c$.\nHence there is a unique codeword of $C$ which has the smallest distance from $v$.\nHence it can be understood that $C$ has corrected the transmission errors of $v$.\n{{Qed}}\n\\end{proof}\n\n"
+]
+
+tokenizer = AutoTokenizer.from_pretrained("hanhainebula/reason-embed-basic-qwen3-8b-0928")
+model = AutoModel.from_pretrained("hanhainebula/reason-embed-basic-qwen3-8b-0928")
+model.eval()
+
+device = "cuda:0"   # set device to "cuda:0" for testing on a single GPU
+model.to(device)
+model.half()
+
+max_length = 512
+# Tokenize the input texts
+query_batch_dict = tokenize_texts(tokenizer, queries, max_length, device)
+doc_batch_dict = tokenize_texts(tokenizer, documents, max_length, device)
+
+with torch.no_grad():
+    query_outputs = model(**query_batch_dict)
+    query_embeddings = last_token_pool(query_outputs.last_hidden_state, query_batch_dict['attention_mask'])
+    
+    doc_outputs = model(**doc_batch_dict)
+    doc_embeddings = last_token_pool(doc_outputs.last_hidden_state, doc_batch_dict['attention_mask'])
+
+# normalize embeddings
+query_embeddings = F.normalize(query_embeddings, p=2, dim=1)
+doc_embeddings = F.normalize(doc_embeddings, p=2, dim=1)
+scores = (query_embeddings @ doc_embeddings.T) * 100
+print(scores.cpu().tolist())
+```
+
+
+## Citation
+
+If you find this repository useful, please consider giving a star ⭐ and citation:
+```
+@article{chen2025reasonembed,
+  title={ReasonEmbed: Enhanced Text Embeddings for Reasoning-Intensive Document Retrieval},
+  author={Chen, Jianlyu and Lan, Junwei and Li, Chaofan and Lian, Defu and Liu, Zheng},
+  journal={arXiv preprint arXiv:2510.08252},
+  year={2025}
+}
+```

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "Qwen3Model"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

config_sentence_transformers.json

@@ -0,0 +1,8 @@
+{
+    "prompts": {
+        "query": "Instruct: Given a query, retrieve documents that can help answer the query.\nQuery: ",
+        "document": ""
+    },
+    "default_prompt_name": null,
+    "similarity_fn_name": "cosine"
+}

evaluation_scripts/eval_bright_short.sh

@@ -0,0 +1,49 @@
+if [ -z "$HF_HUB_CACHE" ]; then
+    export HF_HUB_CACHE="$HOME/.cache/huggingface/hub"
+fi
+
+# full datasets
+dataset_names="biology earth_science economics psychology robotics stackoverflow sustainable_living leetcode pony aops theoremqa_questions theoremqa_theorems"
+
+model_args="\
+    --embedder_name_or_path hanhainebula/reason-embed-basic-qwen3-8b-0928 \
+    --embedder_model_class decoder-only-base \
+    --query_instruction_format_for_retrieval 'Instruct: {}\nQuery: {}' \
+    --pooling_method last_token \
+    --devices cuda:0 cuda:1 cuda:2 cuda:3 cuda:4 cuda:5 cuda:6 cuda:7 \
+    --cache_dir $HF_HUB_CACHE \
+    --embedder_batch_size 8 \
+    --embedder_query_max_length 8192 \
+    --embedder_passage_max_length 8192 \
+"
+
+split_list=("examples" "gpt4_reason")
+
+for split in "${split_list[@]}"; do
+    eval_args="\
+        --task_type short \
+        --use_special_instructions True \
+        --eval_name bright_short \
+        --dataset_dir ./bright_short/data \
+        --dataset_names $dataset_names \
+        --splits $split \
+        --corpus_embd_save_dir ./bright_short/corpus_embd \
+        --output_dir ./bright_short/search_results/$split \
+        --search_top_k 2000 \
+        --cache_path $HF_HUB_CACHE \
+        --overwrite False \
+        --k_values 1 10 100 \
+        --eval_output_method markdown \
+        --eval_output_path ./bright_short/eval_results_$split.md \
+        --eval_metrics ndcg_at_10 recall_at_10 recall_at_100 \
+    "
+
+    cmd="python -m FlagEmbedding.evaluation.bright \
+        $eval_args \
+        $model_args \
+    "
+
+    echo $cmd
+    eval $cmd
+
+done

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23735afff7b5c593498770ad7aae03015c654b15704b3b96ff6942749fb1db90
+size 4972454136

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:445fa2ef4c1a6e1017c065b81d7f093d1e2bd0c38fbcbf66d9eb103110cba7eb
+size 4832048200

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:116e3da92c066e1882e1542ac6f6bee5c6ed5d7c7628370ef20cdc7f14bda11e
+size 4832048248

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acc49af2f5ef9bb6110d36d283985b09dce57e84f18b16e77e57083959c1518d
+size 4999855080

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:493967c31db9e3797c6fd5fc333594d72f0d620c8834e7d67b96f51026b499a7
+size 4832048272

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a7d880cb754b2e9eb5bfde7f6e5a4d20a499aeea9b6c5626777cfd3329ca407
+size 4832048264

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48ae6a7506557bd220521094305cb815782bea7bcc9721db8aa38719330bede4
+size 973163080

model.safetensors.index.json

@@ -0,0 +1,405 @@
+{
+  "metadata": {
+    "total_size": 30273622016
+  },
+  "weight_map": {
+    "embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "layers.0.self_attn.k_norm.weight": "model-00001-of-00007.safetensors",
+    "layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "layers.0.self_attn.q_norm.weight": "model-00001-of-00007.safetensors",
+    "layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "layers.1.self_attn.k_norm.weight": "model-00001-of-00007.safetensors",
+    "layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "layers.1.self_attn.q_norm.weight": "model-00001-of-00007.safetensors",
+    "layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "layers.10.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
+    "layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "layers.10.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
+    "layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "layers.11.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
+    "layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "layers.11.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
+    "layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "layers.12.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
+    "layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "layers.12.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
+    "layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "layers.13.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "layers.13.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
+    "layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "layers.13.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
+    "layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "layers.14.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "layers.14.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "layers.14.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "layers.14.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "layers.14.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
+    "layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "layers.14.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
+    "layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "layers.15.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "layers.15.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "layers.15.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
+    "layers.15.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "layers.15.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "layers.15.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
+    "layers.15.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "layers.15.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "layers.16.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
+    "layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "layers.16.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
+    "layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "layers.17.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
+    "layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "layers.17.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
+    "layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "layers.18.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "layers.18.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
+    "layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "layers.18.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
+    "layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "layers.19.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "layers.19.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "layers.19.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "layers.19.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "layers.19.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
+    "layers.19.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "layers.19.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
+    "layers.19.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "layers.2.self_attn.k_norm.weight": "model-00001-of-00007.safetensors",
+    "layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "layers.2.self_attn.q_norm.weight": "model-00001-of-00007.safetensors",
+    "layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "layers.20.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "layers.20.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "layers.20.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "layers.20.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "layers.20.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "layers.20.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
+    "layers.20.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "layers.20.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "layers.20.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
+    "layers.20.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "layers.20.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "layers.21.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "layers.21.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "layers.21.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "layers.21.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "layers.21.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "layers.21.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
+    "layers.21.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "layers.21.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "layers.21.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
+    "layers.21.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "layers.21.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "layers.22.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
+    "layers.22.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "layers.22.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "layers.22.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
+    "layers.22.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "layers.22.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "layers.23.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
+    "layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "layers.23.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
+    "layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "layers.24.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "layers.24.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "layers.24.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "layers.24.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "layers.24.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "layers.24.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
+    "layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "layers.24.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "layers.24.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
+    "layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "layers.25.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "layers.25.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "layers.25.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "layers.25.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "layers.25.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "layers.25.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
+    "layers.25.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "layers.25.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "layers.25.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
+    "layers.25.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "layers.25.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "layers.26.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "layers.26.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "layers.26.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "layers.26.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "layers.26.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "layers.26.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
+    "layers.26.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "layers.26.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "layers.26.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
+    "layers.26.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "layers.26.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "layers.27.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "layers.27.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "layers.27.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "layers.27.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "layers.27.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "layers.27.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
+    "layers.27.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "layers.27.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "layers.27.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
+    "layers.27.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "layers.27.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "layers.28.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "layers.28.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "layers.28.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "layers.28.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "layers.28.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "layers.28.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
+    "layers.28.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "layers.28.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "layers.28.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
+    "layers.28.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "layers.28.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "layers.29.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "layers.29.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "layers.29.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "layers.29.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "layers.29.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "layers.29.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
+    "layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "layers.29.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "layers.29.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
+    "layers.29.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "layers.29.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "layers.3.self_attn.k_norm.weight": "model-00001-of-00007.safetensors",
+    "layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "layers.3.self_attn.q_norm.weight": "model-00001-of-00007.safetensors",
+    "layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "layers.30.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "layers.30.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "layers.30.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "layers.30.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "layers.30.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "layers.30.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
+    "layers.30.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "layers.30.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "layers.30.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
+    "layers.30.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "layers.30.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "layers.31.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "layers.31.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "layers.31.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "layers.31.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "layers.31.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "layers.31.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
+    "layers.31.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "layers.31.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "layers.31.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
+    "layers.31.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "layers.31.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "layers.32.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "layers.32.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "layers.32.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "layers.32.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "layers.32.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "layers.32.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
+    "layers.32.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "layers.32.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "layers.32.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
+    "layers.32.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "layers.32.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "layers.33.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "layers.33.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "layers.33.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "layers.33.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "layers.33.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "layers.33.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
+    "layers.33.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "layers.33.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "layers.33.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
+    "layers.33.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "layers.33.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "layers.34.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "layers.34.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "layers.34.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "layers.34.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "layers.34.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "layers.34.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
+    "layers.34.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "layers.34.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "layers.34.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
+    "layers.34.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "layers.34.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "layers.35.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "layers.35.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "layers.35.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
+    "layers.35.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+    "layers.35.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "layers.35.self_attn.k_norm.weight": "model-00007-of-00007.safetensors",
+    "layers.35.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "layers.35.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+    "layers.35.self_attn.q_norm.weight": "model-00007-of-00007.safetensors",
+    "layers.35.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "layers.35.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "layers.4.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
+    "layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "layers.4.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
+    "layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "layers.5.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
+    "layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "layers.5.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
+    "layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "layers.6.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
+    "layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "layers.6.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
+    "layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "layers.7.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
+    "layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "layers.7.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
+    "layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "layers.8.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "layers.8.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
+    "layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "layers.8.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
+    "layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "layers.9.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "layers.9.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
+    "layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "layers.9.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
+    "layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "norm.weight": "model-00007-of-00007.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"
+    }
+]

search_results/examples/EVAL/eval_results.json

@@ -0,0 +1,206 @@
+{
+    "earth_science-examples": {
+        "ndcg_at_1": 0.57759,
+        "ndcg_at_10": 0.55426,
+        "ndcg_at_100": 0.64815,
+        "map_at_1": 0.23269,
+        "map_at_10": 0.44959,
+        "map_at_100": 0.49319,
+        "recall_at_1": 0.23269,
+        "recall_at_10": 0.58342,
+        "recall_at_100": 0.87067,
+        "precision_at_1": 0.57759,
+        "precision_at_10": 0.2181,
+        "precision_at_100": 0.03966,
+        "mrr_at_1": 0.57759,
+        "mrr_at_10": 0.67135,
+        "mrr_at_100": 0.67713
+    },
+    "theoremqa_questions-examples": {
+        "ndcg_at_1": 0.39691,
+        "ndcg_at_10": 0.4124,
+        "ndcg_at_100": 0.45757,
+        "map_at_1": 0.22809,
+        "map_at_10": 0.37578,
+        "map_at_100": 0.38535,
+        "recall_at_1": 0.22809,
+        "recall_at_10": 0.45814,
+        "recall_at_100": 0.64633,
+        "precision_at_1": 0.39691,
+        "precision_at_10": 0.09639,
+        "precision_at_100": 0.01309,
+        "mrr_at_1": 0.39691,
+        "mrr_at_10": 0.43798,
+        "mrr_at_100": 0.44688
+    },
+    "pony-examples": {
+        "ndcg_at_1": 0.24107,
+        "ndcg_at_10": 0.18695,
+        "ndcg_at_100": 0.27913,
+        "map_at_1": 0.0161,
+        "map_at_10": 0.05544,
+        "map_at_100": 0.09322,
+        "recall_at_1": 0.0161,
+        "recall_at_10": 0.09518,
+        "recall_at_100": 0.38397,
+        "precision_at_1": 0.24107,
+        "precision_at_10": 0.16696,
+        "precision_at_100": 0.07187,
+        "mrr_at_1": 0.24107,
+        "mrr_at_10": 0.37267,
+        "mrr_at_100": 0.38838
+    },
+    "robotics-examples": {
+        "ndcg_at_1": 0.28713,
+        "ndcg_at_10": 0.31993,
+        "ndcg_at_100": 0.40945,
+        "map_at_1": 0.14029,
+        "map_at_10": 0.23822,
+        "map_at_100": 0.26881,
+        "recall_at_1": 0.14029,
+        "recall_at_10": 0.37368,
+        "recall_at_100": 0.708,
+        "precision_at_1": 0.28713,
+        "precision_at_10": 0.11386,
+        "precision_at_100": 0.0298,
+        "mrr_at_1": 0.28713,
+        "mrr_at_10": 0.37628,
+        "mrr_at_100": 0.38883
+    },
+    "aops-examples": {
+        "ndcg_at_1": 0.13514,
+        "ndcg_at_10": 0.13305,
+        "ndcg_at_100": 0.21311,
+        "map_at_1": 0.03062,
+        "map_at_10": 0.07937,
+        "map_at_100": 0.10056,
+        "recall_at_1": 0.03062,
+        "recall_at_10": 0.1598,
+        "recall_at_100": 0.39924,
+        "precision_at_1": 0.13514,
+        "precision_at_10": 0.07207,
+        "precision_at_100": 0.01946,
+        "mrr_at_1": 0.13514,
+        "mrr_at_10": 0.20256,
+        "mrr_at_100": 0.21432
+    },
+    "sustainable_living-examples": {
+        "ndcg_at_1": 0.35185,
+        "ndcg_at_10": 0.37341,
+        "ndcg_at_100": 0.48528,
+        "map_at_1": 0.13027,
+        "map_at_10": 0.27505,
+        "map_at_100": 0.32648,
+        "recall_at_1": 0.13027,
+        "recall_at_10": 0.45011,
+        "recall_at_100": 0.80612,
+        "precision_at_1": 0.35185,
+        "precision_at_10": 0.16019,
+        "precision_at_100": 0.0375,
+        "mrr_at_1": 0.35185,
+        "mrr_at_10": 0.43959,
+        "mrr_at_100": 0.4535
+    },
+    "leetcode-examples": {
+        "ndcg_at_1": 0.28169,
+        "ndcg_at_10": 0.32309,
+        "ndcg_at_100": 0.38938,
+        "map_at_1": 0.17535,
+        "map_at_10": 0.25267,
+        "map_at_100": 0.26771,
+        "recall_at_1": 0.17535,
+        "recall_at_10": 0.41808,
+        "recall_at_100": 0.69519,
+        "precision_at_1": 0.28169,
+        "precision_at_10": 0.07254,
+        "precision_at_100": 0.01254,
+        "mrr_at_1": 0.28169,
+        "mrr_at_10": 0.37478,
+        "mrr_at_100": 0.38255
+    },
+    "economics-examples": {
+        "ndcg_at_1": 0.29126,
+        "ndcg_at_10": 0.33832,
+        "ndcg_at_100": 0.43577,
+        "map_at_1": 0.13804,
+        "map_at_10": 0.23934,
+        "map_at_100": 0.29841,
+        "recall_at_1": 0.13804,
+        "recall_at_10": 0.35798,
+        "recall_at_100": 0.72009,
+        "precision_at_1": 0.29126,
+        "precision_at_10": 0.15049,
+        "precision_at_100": 0.04738,
+        "mrr_at_1": 0.29126,
+        "mrr_at_10": 0.37666,
+        "mrr_at_100": 0.38917
+    },
+    "stackoverflow-examples": {
+        "ndcg_at_1": 0.30769,
+        "ndcg_at_10": 0.34329,
+        "ndcg_at_100": 0.44943,
+        "map_at_1": 0.12812,
+        "map_at_10": 0.26281,
+        "map_at_100": 0.30158,
+        "recall_at_1": 0.12812,
+        "recall_at_10": 0.43316,
+        "recall_at_100": 0.77889,
+        "precision_at_1": 0.30769,
+        "precision_at_10": 0.12222,
+        "precision_at_100": 0.03265,
+        "mrr_at_1": 0.2906,
+        "mrr_at_10": 0.3824,
+        "mrr_at_100": 0.39268
+    },
+    "biology-examples": {
+        "ndcg_at_1": 0.50485,
+        "ndcg_at_10": 0.54407,
+        "ndcg_at_100": 0.62536,
+        "map_at_1": 0.16222,
+        "map_at_10": 0.43293,
+        "map_at_100": 0.46687,
+        "recall_at_1": 0.16222,
+        "recall_at_10": 0.63582,
+        "recall_at_100": 0.91484,
+        "precision_at_1": 0.50485,
+        "precision_at_10": 0.22524,
+        "precision_at_100": 0.03301,
+        "mrr_at_1": 0.49515,
+        "mrr_at_10": 0.61066,
+        "mrr_at_100": 0.61562
+    },
+    "theoremqa_theorems-examples": {
+        "ndcg_at_1": 0.34211,
+        "ndcg_at_10": 0.47592,
+        "ndcg_at_100": 0.54161,
+        "map_at_1": 0.18499,
+        "map_at_10": 0.39117,
+        "map_at_100": 0.41019,
+        "recall_at_1": 0.18499,
+        "recall_at_10": 0.65116,
+        "recall_at_100": 0.89583,
+        "precision_at_1": 0.34211,
+        "precision_at_10": 0.11974,
+        "precision_at_100": 0.01763,
+        "mrr_at_1": 0.34211,
+        "mrr_at_10": 0.45854,
+        "mrr_at_100": 0.46713
+    },
+    "psychology-examples": {
+        "ndcg_at_1": 0.36634,
+        "ndcg_at_10": 0.45155,
+        "ndcg_at_100": 0.52282,
+        "map_at_1": 0.16264,
+        "map_at_10": 0.33572,
+        "map_at_100": 0.38264,
+        "recall_at_1": 0.16264,
+        "recall_at_10": 0.52951,
+        "recall_at_100": 0.8142,
+        "precision_at_1": 0.36634,
+        "precision_at_10": 0.19406,
+        "precision_at_100": 0.04168,
+        "mrr_at_1": 0.36634,
+        "mrr_at_10": 0.47711,
+        "mrr_at_100": 0.48678
+    }
+}

search_results/examples/biology-examples.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ead63978ceaeaa9ca7e7cf76464526d81ec047109cabad6504da5a95640e84a
+size 16553924

search_results/examples/earth_science-examples.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b95f0afc233ab8cf863c35c04e32196626de3dc0ff07dff4c8870d27f5636e56
+size 18149221

search_results/examples/economics-examples.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcac89b03a3b96e453a89aef3f900f5d6bb24cc25ccf6511505205ec85bbac01
+size 16603020

search_results/examples/leetcode-examples.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8249e274e39aee71f58c32c5b51c0c2829e2f8d1f53f590ef3baa217f94b0725
+size 18343911

search_results/examples/pony-examples.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ac2ed1eb076819107e71f5f9599910a3979dea760573670146cb428bee09feb
+size 14638419

search_results/examples/psychology-examples.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab7aafa65d1315d0c4343b7cdd79af81a7efefb89f3bdac43358cb91ac16ca8c
+size 15426558

search_results/examples/robotics-examples.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6988daa347380112bf9946b28bbd8c79eb31700392ea515c04e4e1a9e7c7232
+size 14420958

search_results/examples/stackoverflow-examples.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db846b983ed8559a381e46947319ecc33c1439212b8961c87771cb6f1e71cee6
+size 19083238

search_results/examples/sustainable_living-examples.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d6ed4c57913ba4e7cf5080a09748891c0a5ecb4b9e310a4bf6de109170f2605
+size 17535724

search_results/examples/theoremqa_questions-examples.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c92a819c01d84eaa07822693f1a5e0f016073ea86d21c37b964615216f2aacd
+size 14691895

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4689bbafe5096d0a16cf2849ede8c67a98d4925bde8eba491f4a6839b1954fc6
+size 11423803

tokenizer_config.json

@@ -0,0 +1,245 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": true,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set content = message.content %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in message.content %}\n                {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "max_length": 512,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "stride": 0,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": null
+}