model-implementation

.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 +1,56 @@
+Pair Checkpoint of the 0.6B V5 model
+
+## vLLM Example
+
+```python
+from vllm import LLM
+import torch
+import torch.nn.functional as F
+import numpy as np
+
+def cosine_similarity(x, y):
+    """Compute cosine similarity between two tensors."""
+    x = F.normalize(x, p=2, dim=1)
+    y = F.normalize(y, p=2, dim=1)
+    return x @ y.T
+
+llm = LLM(
+    model='jinaai/jina-embeddings-v5-text-0.6B-pair-ckpt',
+    task="embed",
+)
+print("Model loaded successfully!")
+
+# Example texts to encode
+example_texts = [
+    "The quantum entanglement of particles across vast cosmic distances reveals the profound interconnectedness of the universe.",
+    "In the depths of the ocean, bioluminescent creatures create their own constellations in an eternal midnight sky.",
+    "A neural network dreams in patterns, finding beauty in the chaos of data streams and learning to see the world through numbers.",
+    "The ancient library contained scrolls written in languages forgotten by time, each page holding secrets of civilizations long vanished.",
+    "Through the telescope, galaxies spiral like cosmic whirlpools, each one a universe of possibilities waiting to be explored.",
+]
+
+print(f"\nEncoding {len(example_texts)} texts...")
+
+# Encode with vLLM's embed method (uses last token pooling)
+outputs = llm.embed(example_texts)
+
+# Collect embeddings into a single tensor
+emb_list = []
+for i, out in enumerate(outputs):
+    vec = out.outputs.embedding
+    vec = torch.tensor(vec)        
+    emb_list.append(vec)
+embeddings = torch.stack(emb_list, dim=0)
+
+# Convert to numpy for analysis
+embeddings_np = embeddings.cpu().numpy()
+
+# Print results
+print(f"\nEmbeddings shape: {embeddings_np.shape}")
+print(f"Embedding dimension: {embeddings_np.shape[1]}")
+
+# Compute cosine similarity matrix
+similarity_matrix = cosine_similarity(embeddings, embeddings)
+print(f"\nCosine similarity matrix:")
+print(similarity_matrix.cpu().numpy())
+```

adapters/classification/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "jinaai/jina-embeddings-v5-text-0.6B-pair-ckpt",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": "gaussian",
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "q_proj",
+    "v_proj",
+    "up_proj",
+    "down_proj",
+    "k_proj",
+    "o_proj"
+  ],
+  "task_type": "FEATURE_EXTRACTION",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapters/classification/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b24f771642c4ff176fb9cbace80b25c0424e9d2eabfe9733cba62cce8776f25c
+size 40420208

adapters/clustering/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "jinaai/jina-embeddings-v5-text-0.6B-pair-ckpt",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": "gaussian",
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "down_proj",
+    "k_proj",
+    "v_proj",
+    "up_proj",
+    "o_proj",
+    "gate_proj"
+  ],
+  "task_type": "FEATURE_EXTRACTION",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapters/clustering/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf90e940983952b150b568144edd7864751ec77b68e6a9761da744e4a0494067
+size 40420208

adapters/retrieval/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "jinaai/jina-embeddings-v5-text-0.6B-pair-ckpt",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": "gaussian",
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "down_proj",
+    "v_proj",
+    "up_proj",
+    "k_proj",
+    "gate_proj"
+  ],
+  "task_type": "FEATURE_EXTRACTION",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapters/retrieval/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcba841f9ba14502651e6d8be257b3a9b556948ff26a3b082029a2e7c36ad5e1
+size 40420208

adapters/text-matching/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "jinaai/jina-embeddings-v5-text-0.6B-pair-ckpt",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": "gaussian",
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "k_proj",
+    "v_proj",
+    "gate_proj",
+    "down_proj",
+    "q_proj",
+    "o_proj"
+  ],
+  "task_type": "FEATURE_EXTRACTION",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapters/text-matching/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d33ac2a046dfb40215ed123d893224ec2d85361a714ece60b2db0b0bd1e7781
+size 40420208

config.json

@@ -0,0 +1,34 @@
+{
+  "auto_map": {
+    "AutoConfig": "configuration_jina_embeddings_v5.JinaEmbeddingsV5Config",
+    "AutoModel": "modeling_jina_embeddings_v5.JinaEmbeddingsV5Model"
+  },
+  "architectures": [
+    "JinaEmbeddingsV5Model"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": 3500000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

configuration_jina_embeddings_v5.py

@@ -0,0 +1,5 @@
+from transformers import Qwen3Config
+
+
+class JinaEmbeddingsV5Config(Qwen3Config):
+    model_type = "jina_embeddings_v5"

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": "4.51.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d4a1c4cc61a71dfaf7ef189845d3ca485a30a42f73a623a4e8aa8d9498b28cc
+size 1192133208

modeling_jina_embeddings_v5.py

@@ -0,0 +1,112 @@
+from typing import Any, List, Optional
+import os
+
+import torch
+import torch.nn.functional as F
+
+from huggingface_hub import snapshot_download
+from transformers import AutoTokenizer
+from transformers.modeling_utils import PreTrainedModel
+from transformers.models.qwen3 import Qwen3Config, Qwen3Model
+from peft import PeftMixedModel, PeftConfig
+
+class JinaEmbeddingsV5Model(PeftMixedModel):
+    @classmethod
+    def register_for_auto_class(cls, auto_class="AutoModel"):
+        return PreTrainedModel.register_for_auto_class.__func__(cls, auto_class)
+    
+    @classmethod
+    def from_pretrained(cls, pretrained_model_name_or_path: str, *args, **kwargs):
+        base_config = Qwen3Config.from_pretrained(
+            pretrained_model_name_or_path,
+        )
+        base_model = Qwen3Model.from_pretrained(
+            pretrained_model_name_or_path,
+            config=base_config,
+            attn_implementation='flash_attention_2',
+            dtype=torch.bfloat16,
+        )
+        kwargs = dict[str, Any](kwargs)
+        kwargs.pop("config", None)
+        if os.path.isdir(base_model.name_or_path):
+            adapters_dir = os.path.join(base_model.name_or_path, "adapters")
+        else:
+            adapter_cache_path = snapshot_download(
+                repo_id=base_model.name_or_path,
+                allow_patterns=["adapters/*"],
+            )
+            adapters_dir = os.path.join(adapter_cache_path, "adapters")
+        adapter_names = ["retrieval", "text-matching", "classification", "clustering"]
+
+        adapter_paths = {
+            name: os.path.join(adapters_dir, name)
+            for name in adapter_names
+        }
+
+        peft_config = PeftConfig.from_pretrained(adapter_paths["retrieval"], **kwargs)
+        model = cls(base_model, peft_config, adapter_name="retrieval")
+        model._pretrained_path = pretrained_model_name_or_path
+        for adapter_name in adapter_names:
+            model.load_adapter(
+                adapter_paths[adapter_name],
+                adapter_name=adapter_name,
+                **kwargs,
+            )
+
+        model.tokenizer = AutoTokenizer.from_pretrained(
+            pretrained_model_name_or_path,
+            trust_remote_code=True,
+        )
+        return model
+
+    def encode(
+        self,
+        texts: List[str],
+        task: str,
+        prompt_name: Optional[str] = "document",
+        truncate_dim: Optional[int] = None,
+        max_length: Optional[int] = None,
+    ) -> List[torch.Tensor]:
+        if task not in {"retrieval", "classification", "text-matching", "clustering"}:
+            raise ValueError(f"Unknown task: {task}")
+
+        if prompt_name is None:
+            prompt_name = "document"
+        if prompt_name not in {"query", "document"}:
+            raise ValueError(f"Unknown prompt_name: {prompt_name}")
+
+        prefix = "Query: " if prompt_name == "query" else "Document: "
+        inputs = [f"{prefix}{text}" for text in texts]
+
+        if not hasattr(self, "tokenizer") or self.tokenizer is None:
+            raise ValueError("Tokenizer not found on model. Load with from_pretrained().")
+
+        batch = self.tokenizer(
+            inputs,
+            return_tensors="pt",
+            padding=True,
+            truncation=True,
+            max_length=max_length,
+        )
+        device = next(self.parameters()).device
+        batch = {k: v.to(device) for k, v in batch.items()}
+        print(batch['input_ids'])
+        self.set_adapter([task])
+        with torch.no_grad():
+            outputs = self(**batch)
+            hidden = outputs.last_hidden_state
+            mask = batch.get("attention_mask")
+            if mask is None:
+                pooled = hidden[:, -1]
+            else:
+                sequence_lengths = mask.sum(dim=1) - 1
+                pooled = hidden[
+                    torch.arange(hidden.shape[0], device=hidden.device),
+                    sequence_lengths,
+                ]
+
+            if truncate_dim is not None:
+                pooled = pooled[:, :truncate_dim]
+            embeddings = F.normalize(pooled, p=2, dim=-1)
+
+        return embeddings

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "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",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}