Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,61 @@
+---
+license: apache-2.0
+language:
+- en
+base_model:
+- Qwen/Qwen3-4B
+pipeline_tag: text-ranking
+tags:
+- finance
+- legal
+- code
+- stem
+- medical
+library_name: sentence-transformers
+---
+
+<img src="https://i.imgur.com/oxvhvQu.png"/>
+
+# Releasing zeroentropy/zerank-1-small
+
+In search enginers, [rerankers are crucial](https://www.zeroentropy.dev/blog/what-is-a-reranker-and-do-i-need-one) for improving the accuracy of your retrieval system.
+
+This 1.7B reranker is the smaller version of our flagship model [zeroentropy/zerank-1](https://huggingface.co/zeroentropy/zerank-1). Though the model is over 2x smaller, it maintains nearly the same standard of performance, continuing to outperform other popular rerankers, and displaying massive accuracy gains over traditional vector search.
+
+We release this model under the open-source Apache 2.0 license, in order to support the open-source community and push the frontier of what's possible with open-source models.
+
+## How to Use
+
+```python
+from sentence_transformers import CrossEncoder
+
+model = CrossEncoder("zeroentropy/zerank-1-small", trust_remote_code=True)
+
+query_documents = [
+    ("What is 2+2?", "4"),
+    ("What is 2+2?", "The answer is definitely 1 million"),
+]
+
+scores = model.predict(query_documents)
+
+print(scores)
+```
+
+The model can also be inferenced using ZeroEntropy's [/models/rerank](https://docs.zeroentropy.dev/api-reference/models/rerank) endpoint.
+
+## Evaluations
+
+NDCG@10 scores between `zerank-1-small` and competing closed-source proprietary rerankers. Since we are evaluating rerankers, OpenAI's `text-embedding-3-small` is used as an initial retriever for the Top 100 candidate documents.
+
+| Task           | Embedding | cohere-rerank-v3.5 | Salesforce/Llama-rank-v1 | **zerank-1-small** | zerank-1 |
+|----------------|-----------|--------------------|--------------------------|----------------|----------|
+| Code           |    0.678  |       0.724        |           0.694          |      **0.730**     |   0.754  |
+| Conversational |    0.250  |       0.571        |           0.484          |      **0.556**     |   0.596  |
+| Finance        |    0.839  |       0.824        |           0.828          |      **0.861**     |   0.894  |
+| Legal          |    0.703  |       0.804        |           0.767          |      **0.817**     |   0.821  |
+| Medical        |    0.619  |       0.750        |           0.719          |      **0.773**     |   0.796  |
+| STEM           |    0.401  |       0.510        |           0.595          |      **0.680**     |   0.694  |
+
+Comparing BM25 and Hybrid Search without and with `zerank-1-small`:
+
+<img src="https://cdn-uploads.huggingface.co/production/uploads/67776f9dcd9c9435499eafc8/2GPVHFrI39FspnSNklhsM.png" alt="Description" width="400"/> <img src="https://cdn-uploads.huggingface.co/production/uploads/67776f9dcd9c9435499eafc8/dwYo2D7hoL8QiE8u3yqr9.png" alt="Description" width="400"/>

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 +1,69 @@
+{
+  "architectures": [
+    "Qwen3ForSequenceClassification"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "modeling_zeranker.ZEConfig"
+  },
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "id2label": {
+    "0": "Yes"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "label2id": {
+    "Yes": 0
+  },
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 40960,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float16",
+  "transformers_version": "4.53.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.51.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82054da4aaac67d0fa861c3a015661de695d64f37914e859e81c04b36bb5dab9
+size 3441189480

modeling_zeranker.py

@@ -0,0 +1,214 @@
+from sentence_transformers import CrossEncoder as _CE
+
+import math
+from typing import cast, Any
+import types
+
+import torch
+from transformers.configuration_utils import PretrainedConfig
+from transformers.models.auto.configuration_auto import AutoConfig
+from transformers.models.auto.modeling_auto import AutoModelForCausalLM
+from transformers.models.auto.tokenization_auto import AutoTokenizer
+from transformers.models.gemma3.modeling_gemma3 import (
+    Gemma3ForCausalLM,
+    Gemma3ForConditionalGeneration,
+)
+from transformers.models.llama.modeling_llama import LlamaForCausalLM
+from transformers.models.qwen3.modeling_qwen3 import Qwen3ForCausalLM
+from transformers.tokenization_utils_base import BatchEncoding
+from transformers.tokenization_utils_fast import PreTrainedTokenizerFast
+
+# pyright: reportUnknownMemberType=false
+# pyright: reportUnknownVariableType=false
+
+MODEL_PATH = "zeroentropy/zerank-1-small"
+PER_DEVICE_BATCH_SIZE_TOKENS = 15_000
+global_device = (
+    torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
+)
+
+
+def format_pointwise_datapoints(
+    tokenizer: PreTrainedTokenizerFast,
+    query_documents: list[tuple[str, str]],
+) -> BatchEncoding:
+    input_texts: list[str] = []
+    for query, document in query_documents:
+        system_prompt = f"""
+{query}
+""".strip()
+        user_message = f"""
+{document}
+""".strip()
+        messages = [
+            {"role": "system", "content": system_prompt},
+            {"role": "user", "content": user_message},
+        ]
+        input_text = tokenizer.apply_chat_template(
+            messages,
+            tokenize=False,
+            add_generation_prompt=True,
+        )
+        assert isinstance(input_text, str)
+        input_texts.append(input_text)
+
+    batch_inputs = tokenizer(
+        input_texts,
+        padding=True,
+        return_tensors="pt",
+    )
+    return batch_inputs
+
+
+def load_model(
+    device: torch.device | None = None,
+) -> tuple[
+    PreTrainedTokenizerFast,
+    LlamaForCausalLM
+    | Gemma3ForConditionalGeneration
+    | Gemma3ForCausalLM
+    | Qwen3ForCausalLM,
+]:
+    if device is None:
+        device = global_device
+
+    config = AutoConfig.from_pretrained(MODEL_PATH)
+    assert isinstance(config, PretrainedConfig)
+
+    model = AutoModelForCausalLM.from_pretrained(
+        MODEL_PATH,
+        torch_dtype="auto",
+        quantization_config=None,
+        device_map={"": device},
+    )
+    if config.model_type == "llama":
+        model.config.attn_implementation = "flash_attention_2"
+    assert isinstance(
+        model,
+        LlamaForCausalLM
+        | Gemma3ForConditionalGeneration
+        | Gemma3ForCausalLM
+        | Qwen3ForCausalLM,
+    )
+
+    tokenizer = cast(
+        AutoTokenizer,
+        AutoTokenizer.from_pretrained(
+            MODEL_PATH,
+            padding_side="right",
+        ),
+    )
+    assert isinstance(tokenizer, PreTrainedTokenizerFast)
+
+    if tokenizer.pad_token is None:
+        tokenizer.pad_token = tokenizer.eos_token
+
+    return tokenizer, model
+
+
+def predict(
+    self,
+    query_documents: list[tuple[str, str]] | None = None,
+    *,
+    sentences: Any = None,
+    batch_size: Any = None,
+    show_progress_bar: Any = None,
+    activation_fn: Any = None,
+    apply_softmax: Any = None,
+    convert_to_numpy: Any = None,
+    convert_to_tensor: Any = None,
+) -> list[float]:
+    if query_documents is None:
+        if sentences is None:
+            raise ValueError("query_documents or sentences must be provided")
+        query_documents = [[sentence[0], sentence[1]] for sentence in sentences]
+
+    if not hasattr(self, "inner_model"):
+        self.inner_tokenizer, self.inner_model = load_model(global_device)
+        self.inner_model.gradient_checkpointing_enable()
+        self.inner_model.eval()
+        self.inner_yes_token_id = self.inner_tokenizer.encode(
+            "Yes", add_special_tokens=False
+        )[0]
+
+    model = self.inner_model
+    tokenizer = self.inner_tokenizer
+
+    query_documents = [
+        (query[:2_000], document[:10_000]) for query, document in query_documents
+    ]
+    # Sort
+    permutation = list(range(len(query_documents)))
+    permutation.sort(
+        key=lambda i: -len(query_documents[i][0]) - len(query_documents[i][1])
+    )
+    query_documents = [query_documents[i] for i in permutation]
+
+    # Extract document batches from this line of datapoints
+    max_length = 0
+    batches: list[list[tuple[str, str]]] = []
+    for query, document in query_documents:
+        if (
+            len(batches) == 0
+            or (len(batches[-1]) + 1) * max(max_length, len(query) + len(document))
+            > PER_DEVICE_BATCH_SIZE_TOKENS
+        ):
+            batches.append([])
+            max_length = 0
+
+        batches[-1].append((query, document))
+        max_length = max(max_length, 20 + len(query) + len(document))
+
+    # Inference all of the document batches
+    all_logits: list[float] = []
+    for batch in batches:
+        batch_inputs = format_pointwise_datapoints(
+            tokenizer,
+            batch,
+        )
+
+        batch_inputs = batch_inputs.to(global_device)
+
+        try:
+            outputs = model(**batch_inputs, use_cache=False)
+        except torch.OutOfMemoryError:
+            print(f"GPU OOM! {torch.cuda.memory_reserved()}")
+            torch.cuda.empty_cache()
+            print(f"GPU After OOM Cache Clear: {torch.cuda.memory_reserved()}")
+            outputs = model(**batch_inputs, use_cache=False)
+
+        # Extract the logits
+        logits = cast(torch.Tensor, outputs.logits)
+        attention_mask = cast(torch.Tensor, batch_inputs.attention_mask)
+        last_positions = attention_mask.sum(dim=1) - 1
+
+        batch_size = logits.shape[0]
+        batch_indices = torch.arange(batch_size, device=global_device)
+        last_logits = logits[batch_indices, last_positions]
+
+        yes_logits = last_logits[:, self.inner_yes_token_id]
+        all_logits.extend([float(logit) / 5.0 for logit in yes_logits])
+
+    def sigmoid(x: float) -> float:
+        return 1 / (1 + math.exp(-x))
+
+    scores = [sigmoid(logit) for logit in all_logits]
+
+    # Unsort by indices
+    scores = [score for _, score in sorted(zip(permutation, scores, strict=True))]
+
+    return scores
+
+
+def to_device(self: _CE, new_device: torch.device) -> None:
+    global global_device
+    global_device = new_device
+
+
+_CE.predict = predict
+
+from transformers import Qwen3Config
+
+ZEConfig = Qwen3Config
+
+_CE.to = to_device

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:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,241 @@
+{
+  "add_bos_token": false,
+  "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 message.content is string 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.content is string %}\n        {%- set content = message.content %}\n    {%- else %}\n        {%- set content = '' %}\n    {%- endif %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is string %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in content %}\n                {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n                {%- set content = content.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        {{- 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": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}