Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,25 @@ 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
+search_results/gpt4_reason/biology-gpt4_reason.json filter=lfs diff=lfs merge=lfs -text
+search_results/gpt4_reason/earth_science-gpt4_reason.json filter=lfs diff=lfs merge=lfs -text
+search_results/gpt4_reason/economics-gpt4_reason.json filter=lfs diff=lfs merge=lfs -text
+search_results/gpt4_reason/leetcode-gpt4_reason.json filter=lfs diff=lfs merge=lfs -text
+search_results/gpt4_reason/pony-gpt4_reason.json filter=lfs diff=lfs merge=lfs -text
+search_results/gpt4_reason/psychology-gpt4_reason.json filter=lfs diff=lfs merge=lfs -text
+search_results/gpt4_reason/robotics-gpt4_reason.json filter=lfs diff=lfs merge=lfs -text
+search_results/gpt4_reason/stackoverflow-gpt4_reason.json filter=lfs diff=lfs merge=lfs -text
+search_results/gpt4_reason/sustainable_living-gpt4_reason.json filter=lfs diff=lfs merge=lfs -text
+search_results/gpt4_reason/theoremqa_questions-gpt4_reason.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,144 @@
+---
+tags:
+- feature-extraction
+- sentence-similarity
+- transformers
+license: apache-2.0
+---
+
+
+<h1 align="center">BGE-Reasoner-Embed</h1>
+
+
+
+For more details please refer to our Github: [BGE-Reasoner](https://github.com/FlagOpen/FlagEmbedding/tree/master/research/BGE_Reasoner).
+
+**BGE-Reasoner-Embed-Qwen3-8B-0923** is an embedding model trained for reasoning-intensive retrieval tasks, based on [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B). It achieves an nDCG@10 of 37.2 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](https://huggingface.co/BAAI/bge-reasoner-embed-qwen3-8b-0923/tree/main/search_results).
+
+## 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("BAAI/bge-reasoner-embed-qwen3-8b-0923", 
+                     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)
+# [[0.8228 0.5386]
+#  [0.575  0.6533]]
+```
+
+
+### 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("BAAI/bge-reasoner-embed-qwen3-8b-0923")
+model = AutoModel.from_pretrained("BAAI/bge-reasoner-embed-qwen3-8b-0923")
+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())
+# [[82.25, 53.84375], [57.53125, 65.3125]]
+```
+
+
+## Evaluation  
+
+BGE-Reasoner-Embed-Qwen3-8B-0923 exhibits strong performance in reasoning-intensive retrieval tasks, as demonstrated by its results (nDCG@10 = 37.2 using original query) on the BRIGHT benchmark.
+
+<img src="./imgs/bright-performance.png" alt="BRIGHT Performance" style="zoom:200%;" />
+
+
+## Citation
+
+If you find this repository useful, please consider giving a star :star: and citation
+
+```
+To be added
+```

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
+}

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"
+  }
+}

search_results/examples/EVAL/eval_results.json

@@ -0,0 +1,146 @@
+{
+    "biology-examples": {
+        "ndcg_at_1": 0.50485,
+        "ndcg_at_10": 0.54407,
+        "map_at_1": 0.16222,
+        "map_at_10": 0.43293,
+        "recall_at_1": 0.16222,
+        "recall_at_10": 0.63582,
+        "precision_at_1": 0.50485,
+        "precision_at_10": 0.22524,
+        "mrr_at_1": 0.49515,
+        "mrr_at_10": 0.61066
+    },
+    "theoremqa_theorems-examples": {
+        "ndcg_at_1": 0.34211,
+        "ndcg_at_10": 0.47592,
+        "map_at_1": 0.18499,
+        "map_at_10": 0.39117,
+        "recall_at_1": 0.18499,
+        "recall_at_10": 0.65116,
+        "precision_at_1": 0.34211,
+        "precision_at_10": 0.11974,
+        "mrr_at_1": 0.34211,
+        "mrr_at_10": 0.45854
+    },
+    "psychology-examples": {
+        "ndcg_at_1": 0.36634,
+        "ndcg_at_10": 0.45155,
+        "map_at_1": 0.16264,
+        "map_at_10": 0.33572,
+        "recall_at_1": 0.16264,
+        "recall_at_10": 0.52951,
+        "precision_at_1": 0.36634,
+        "precision_at_10": 0.19406,
+        "mrr_at_1": 0.36634,
+        "mrr_at_10": 0.47711
+    },
+    "robotics-examples": {
+        "ndcg_at_1": 0.28713,
+        "ndcg_at_10": 0.31993,
+        "map_at_1": 0.14029,
+        "map_at_10": 0.23822,
+        "recall_at_1": 0.14029,
+        "recall_at_10": 0.37368,
+        "precision_at_1": 0.28713,
+        "precision_at_10": 0.11386,
+        "mrr_at_1": 0.28713,
+        "mrr_at_10": 0.37628
+    },
+    "aops-examples": {
+        "ndcg_at_1": 0.13514,
+        "ndcg_at_10": 0.13305,
+        "map_at_1": 0.03062,
+        "map_at_10": 0.07937,
+        "recall_at_1": 0.03062,
+        "recall_at_10": 0.1598,
+        "precision_at_1": 0.13514,
+        "precision_at_10": 0.07207,
+        "mrr_at_1": 0.13514,
+        "mrr_at_10": 0.20256
+    },
+    "sustainable_living-examples": {
+        "ndcg_at_1": 0.35185,
+        "ndcg_at_10": 0.37341,
+        "map_at_1": 0.13027,
+        "map_at_10": 0.27505,
+        "recall_at_1": 0.13027,
+        "recall_at_10": 0.45011,
+        "precision_at_1": 0.35185,
+        "precision_at_10": 0.16019,
+        "mrr_at_1": 0.35185,
+        "mrr_at_10": 0.43959
+    },
+    "leetcode-examples": {
+        "ndcg_at_1": 0.28169,
+        "ndcg_at_10": 0.32309,
+        "map_at_1": 0.17535,
+        "map_at_10": 0.25267,
+        "recall_at_1": 0.17535,
+        "recall_at_10": 0.41808,
+        "precision_at_1": 0.28169,
+        "precision_at_10": 0.07254,
+        "mrr_at_1": 0.28169,
+        "mrr_at_10": 0.37478
+    },
+    "earth_science-examples": {
+        "ndcg_at_1": 0.57759,
+        "ndcg_at_10": 0.55426,
+        "map_at_1": 0.23269,
+        "map_at_10": 0.44959,
+        "recall_at_1": 0.23269,
+        "recall_at_10": 0.58342,
+        "precision_at_1": 0.57759,
+        "precision_at_10": 0.2181,
+        "mrr_at_1": 0.57759,
+        "mrr_at_10": 0.67135
+    },
+    "economics-examples": {
+        "ndcg_at_1": 0.29126,
+        "ndcg_at_10": 0.33832,
+        "map_at_1": 0.13804,
+        "map_at_10": 0.23934,
+        "recall_at_1": 0.13804,
+        "recall_at_10": 0.35798,
+        "precision_at_1": 0.29126,
+        "precision_at_10": 0.15049,
+        "mrr_at_1": 0.29126,
+        "mrr_at_10": 0.37666
+    },
+    "theoremqa_questions-examples": {
+        "ndcg_at_1": 0.39691,
+        "ndcg_at_10": 0.4124,
+        "map_at_1": 0.22809,
+        "map_at_10": 0.37578,
+        "recall_at_1": 0.22809,
+        "recall_at_10": 0.45814,
+        "precision_at_1": 0.39691,
+        "precision_at_10": 0.09639,
+        "mrr_at_1": 0.39691,
+        "mrr_at_10": 0.43798
+    },
+    "stackoverflow-examples": {
+        "ndcg_at_1": 0.30769,
+        "ndcg_at_10": 0.34329,
+        "map_at_1": 0.12812,
+        "map_at_10": 0.26281,
+        "recall_at_1": 0.12812,
+        "recall_at_10": 0.43316,
+        "precision_at_1": 0.30769,
+        "precision_at_10": 0.12222,
+        "mrr_at_1": 0.2906,
+        "mrr_at_10": 0.3824
+    },
+    "pony-examples": {
+        "ndcg_at_1": 0.24107,
+        "ndcg_at_10": 0.1903,
+        "map_at_1": 0.0161,
+        "map_at_10": 0.05666,
+        "recall_at_1": 0.0161,
+        "recall_at_10": 0.09687,
+        "precision_at_1": 0.24107,
+        "precision_at_10": 0.17054,
+        "mrr_at_1": 0.24107,
+        "mrr_at_10": 0.37504
+    }
+}

search_results/examples/biology-examples.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73ff1cf7ff2e2aaaf8c4589982ae31198a58744ee5aba0393a10a4c4cb040f1c
+size 16553902

search_results/examples/earth_science-examples.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3c02bb3fd382207d49a63897dd34ec396c9e1175e35921fd3c1b95fcf5620f2
+size 18149199

search_results/examples/economics-examples.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca54dce3b507334fd5fb1752bc7979ce1ffc19529339f04e3b02bc3aeea77e65
+size 16602998

search_results/examples/leetcode-examples.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5605b0a3e4529214669438e02af8060bdc07cd168872742e0b13b0f16422b0c0
+size 18343889

search_results/examples/pony-examples.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2df5caf0f85432924ec0848713162cce488c6f63f63c2da36907c4aab1981c2c
+size 14633844

search_results/examples/psychology-examples.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27abb7eeb6ef1fd323c8d0edd4693711ccb2f3ab475ad7cb852d79486ec64c15
+size 15426536

search_results/examples/robotics-examples.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccaa49fe930eef8a75a4f95775041d720fd98f590ee4a2e43639d85060f0f841
+size 14420936

search_results/examples/stackoverflow-examples.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8583c0c7ad3583159cdbfe1af10f6d7d02867d1d966a649517158809a0cdcdf
+size 19083216

search_results/examples/sustainable_living-examples.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:424f15ba7d04f4e36a09940fe5ca4c8e1186904cb8cf828341121911aa4a2f74
+size 17535702

search_results/examples/theoremqa_questions-examples.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11ef6db56d097e389508bece9f359d2e5cac0a5d9c5966343fa0d20475366e84
+size 14691873

search_results/gpt4_reason/EVAL/eval_results.json

@@ -0,0 +1,146 @@
+{
+    "biology-gpt4_reason": {
+        "ndcg_at_1": 0.58252,
+        "ndcg_at_10": 0.6238,
+        "map_at_1": 0.20161,
+        "map_at_10": 0.52321,
+        "recall_at_1": 0.20161,
+        "recall_at_10": 0.70649,
+        "precision_at_1": 0.58252,
+        "precision_at_10": 0.24757,
+        "mrr_at_1": 0.57282,
+        "mrr_at_10": 0.67721
+    },
+    "stackoverflow-gpt4_reason": {
+        "ndcg_at_1": 0.33333,
+        "ndcg_at_10": 0.39248,
+        "map_at_1": 0.15138,
+        "map_at_10": 0.3128,
+        "recall_at_1": 0.15138,
+        "recall_at_10": 0.48351,
+        "precision_at_1": 0.33333,
+        "precision_at_10": 0.13761,
+        "mrr_at_1": 0.34188,
+        "mrr_at_10": 0.43379
+    },
+    "sustainable_living-gpt4_reason": {
+        "ndcg_at_1": 0.36111,
+        "ndcg_at_10": 0.40345,
+        "map_at_1": 0.15859,
+        "map_at_10": 0.3077,
+        "recall_at_1": 0.15859,
+        "recall_at_10": 0.47684,
+        "precision_at_1": 0.36111,
+        "precision_at_10": 0.16944,
+        "mrr_at_1": 0.36111,
+        "mrr_at_10": 0.46219
+    },
+    "leetcode-gpt4_reason": {
+        "ndcg_at_1": 0.23239,
+        "ndcg_at_10": 0.28348,
+        "map_at_1": 0.14894,
+        "map_at_10": 0.21761,
+        "recall_at_1": 0.14894,
+        "recall_at_10": 0.37946,
+        "precision_at_1": 0.23239,
+        "precision_at_10": 0.0662,
+        "mrr_at_1": 0.23239,
+        "mrr_at_10": 0.31958
+    },
+    "pony-gpt4_reason": {
+        "ndcg_at_1": 0.4375,
+        "ndcg_at_10": 0.31629,
+        "map_at_1": 0.02577,
+        "map_at_10": 0.09796,
+        "recall_at_1": 0.02577,
+        "recall_at_10": 0.1572,
+        "precision_at_1": 0.4375,
+        "precision_at_10": 0.27321,
+        "mrr_at_1": 0.4375,
+        "mrr_at_10": 0.58011
+    },
+    "aops-gpt4_reason": {
+        "ndcg_at_1": 0.0991,
+        "ndcg_at_10": 0.12337,
+        "map_at_1": 0.02301,
+        "map_at_10": 0.07287,
+        "recall_at_1": 0.02301,
+        "recall_at_10": 0.15546,
+        "precision_at_1": 0.0991,
+        "precision_at_10": 0.07748,
+        "mrr_at_1": 0.0991,
+        "mrr_at_10": 0.17159
+    },
+    "theoremqa_questions-gpt4_reason": {
+        "ndcg_at_1": 0.39175,
+        "ndcg_at_10": 0.39407,
+        "map_at_1": 0.2268,
+        "map_at_10": 0.36037,
+        "recall_at_1": 0.2268,
+        "recall_at_10": 0.42649,
+        "precision_at_1": 0.39175,
+        "precision_at_10": 0.08918,
+        "mrr_at_1": 0.39175,
+        "mrr_at_10": 0.42989
+    },
+    "theoremqa_theorems-gpt4_reason": {
+        "ndcg_at_1": 0.31579,
+        "ndcg_at_10": 0.41518,
+        "map_at_1": 0.18061,
+        "map_at_10": 0.34361,
+        "recall_at_1": 0.18061,
+        "recall_at_10": 0.55138,
+        "precision_at_1": 0.31579,
+        "precision_at_10": 0.10526,
+        "mrr_at_1": 0.31579,
+        "mrr_at_10": 0.41206
+    },
+    "earth_science-gpt4_reason": {
+        "ndcg_at_1": 0.68966,
+        "ndcg_at_10": 0.62277,
+        "map_at_1": 0.27438,
+        "map_at_10": 0.51581,
+        "recall_at_1": 0.27438,
+        "recall_at_10": 0.62818,
+        "precision_at_1": 0.68966,
+        "precision_at_10": 0.23966,
+        "mrr_at_1": 0.68966,
+        "mrr_at_10": 0.75591
+    },
+    "economics-gpt4_reason": {
+        "ndcg_at_1": 0.25243,
+        "ndcg_at_10": 0.35251,
+        "map_at_1": 0.1225,
+        "map_at_10": 0.24774,
+        "recall_at_1": 0.1225,
+        "recall_at_10": 0.39583,
+        "precision_at_1": 0.25243,
+        "precision_at_10": 0.16214,
+        "mrr_at_1": 0.25243,
+        "mrr_at_10": 0.36646
+    },
+    "psychology-gpt4_reason": {
+        "ndcg_at_1": 0.43564,
+        "ndcg_at_10": 0.49823,
+        "map_at_1": 0.19875,
+        "map_at_10": 0.37395,
+        "recall_at_1": 0.19875,
+        "recall_at_10": 0.56675,
+        "precision_at_1": 0.43564,
+        "precision_at_10": 0.20396,
+        "mrr_at_1": 0.43564,
+        "mrr_at_10": 0.55344
+    },
+    "robotics-gpt4_reason": {
+        "ndcg_at_1": 0.30693,
+        "ndcg_at_10": 0.3438,
+        "map_at_1": 0.13674,
+        "map_at_10": 0.25764,
+        "recall_at_1": 0.13674,
+        "recall_at_10": 0.39831,
+        "precision_at_1": 0.30693,
+        "precision_at_10": 0.12277,
+        "mrr_at_1": 0.30693,
+        "mrr_at_10": 0.40114
+    }
+}

search_results/gpt4_reason/biology-gpt4_reason.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a314b2948bd2a48f44d4d949645051600cd1cba4e600dc9b89c31753570e4c8a
+size 16518223

search_results/gpt4_reason/earth_science-gpt4_reason.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f2fa207b74ef2808c22bbed1d086941cd177cd442c26b7ea8cdd4991bce3411
+size 18093660

search_results/gpt4_reason/economics-gpt4_reason.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41293661ab3cec60d7620fe33a4689ccbd0f5b67ee5f8dbf5ba589fb0f70fb0f
+size 16558285

search_results/gpt4_reason/leetcode-gpt4_reason.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4520f31f78b5d0543af77eee8c7f29ddfe7d3c17960778ca654893490fac36d9
+size 18454399

search_results/gpt4_reason/pony-gpt4_reason.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9f79f2d325a64c1362fcf7cc7707b6ddb3adfbd164c246bb70dcac003d7765f
+size 14625227

search_results/gpt4_reason/psychology-gpt4_reason.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1347e9db837913ab175f6b5daee4b8e1e3babb69ba3a43396a5b49cec2655d0d
+size 15322577

search_results/gpt4_reason/robotics-gpt4_reason.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fd310df6a895d2d566674614b1976af7a85248ceca02e583d7c2b61bcde49d2
+size 14451325

search_results/gpt4_reason/stackoverflow-gpt4_reason.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f98cedc37011e2e1900a716e3330342562bf028dfd6ea6fd056a7c1b44fb293
+size 19155033

search_results/gpt4_reason/sustainable_living-gpt4_reason.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef85268f068dccb8f806d7f6d5deeb748e9d72f7ca82cd092ee3c93b4b9d52fd
+size 17382433

search_results/gpt4_reason/theoremqa_questions-gpt4_reason.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96c0abc7644d10c4a13532f2420a6a3ef9d952917ef422e7cb0658b199f783c2
+size 14333959

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
+}