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 +1,272 @@
+---
+base_model:
+- huihui-ai/Huihui-Qwen3-4B-Instruct-2507-abliterated
+license: apache-2.0
+license_link: https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507/blob/main/LICENSE
+pipeline_tag: text-generation
+library_name: transformers
+tags:
+- torchao-my-repo
+- abliterated
+- uncensored
+---
+# huihui-ai/Huihui-Qwen3-4B-Instruct-2507-abliterated (Quantized)
+
+## Description
+This model is a quantized version of the original model [`huihui-ai/Huihui-Qwen3-4B-Instruct-2507-abliterated`](https://huggingface.co/huihui-ai/Huihui-Qwen3-4B-Instruct-2507-abliterated). 
+
+It's quantized using the TorchAO library using the [torchao-my-repo](https://huggingface.co/spaces/pytorch/torchao-my-repo) space.
+
+## Quantization Details
+- **Quantization Type**: Int8WeightOnly
+- **Group Size**: 64
+
+
+
+# 📄 Original Model Information
+
+
+# huihui-ai/Huihui-Qwen3-4B-Instruct-2507-abliterated
+
+This is an uncensored version of [Qwen/Qwen3-4B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507) created with abliteration (see [remove-refusals-with-transformers](https://github.com/Sumandora/remove-refusals-with-transformers) to know more about it).
+This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens. 
+
+Ablation was performed using a new and faster method, which yields better results.
+
+## ollama
+
+You can use [huihui_ai/qwen3-abliterated:4b-instruct-2507-q4_K_M](https://ollama.com/huihui_ai/qwen3-abliterated:4b-instruct-2507-q4_K_M) directly, 
+```
+ollama run huihui_ai/qwen3-abliterated:4b-instruct-2507-q4_K_M
+```
+
+
+## Usage
+You can use this model in your applications by loading it with Hugging Face's `transformers` library:
+
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig, TextStreamer
+import torch
+import os
+import signal
+import random
+import numpy as np
+import time
+from collections import Counter
+
+cpu_count = os.cpu_count()
+print(f"Number of CPU cores in the system: {cpu_count}")
+half_cpu_count = cpu_count // 2
+os.environ["MKL_NUM_THREADS"] = str(half_cpu_count)
+os.environ["OMP_NUM_THREADS"] = str(half_cpu_count)
+torch.set_num_threads(half_cpu_count)
+
+print(f"PyTorch threads: {torch.get_num_threads()}")
+print(f"MKL threads: {os.getenv('MKL_NUM_THREADS')}")
+print(f"OMP threads: {os.getenv('OMP_NUM_THREADS')}")
+
+# Load the model and tokenizer
+NEW_MODEL_ID = "huihui-ai/Huihui-Qwen3-4B-Instruct-2507-abliterated"
+print(f"Load Model {NEW_MODEL_ID} ... ")
+quant_config_4 = BitsAndBytesConfig(
+    load_in_4bit=True,
+    bnb_4bit_compute_dtype=torch.bfloat16,
+    bnb_4bit_use_double_quant=True,
+    llm_int8_enable_fp32_cpu_offload=True,
+)
+
+model = AutoModelForCausalLM.from_pretrained(
+    NEW_MODEL_ID, 
+    device_map="balanced", 
+    trust_remote_code=True,
+    quantization_config=quant_config_4,
+    torch_dtype=torch.bfloat16,
+    low_cpu_mem_usage=True,
+)
+#print(model)
+#print(model.config)
+
+tokenizer = AutoTokenizer.from_pretrained(NEW_MODEL_ID, trust_remote_code=True)
+if tokenizer.pad_token is None:
+    tokenizer.pad_token = tokenizer.eos_token
+tokenizer.pad_token_id = tokenizer.eos_token_id
+
+messages = []
+skip_prompt=True
+skip_special_tokens=True
+do_sample = True
+
+class CustomTextStreamer(TextStreamer):
+    def __init__(self, tokenizer, skip_prompt=True, skip_special_tokens=True):
+        super().__init__(tokenizer, skip_prompt=skip_prompt, skip_special_tokens=skip_special_tokens)
+        self.generated_text = ""
+        self.stop_flag = False
+        self.init_time = time.time()  # Record initialization time
+        self.end_time = None  # To store end time
+        self.first_token_time = None  # To store first token generation time
+        self.token_count = 0  # To track total tokens
+
+    def on_finalized_text(self, text: str, stream_end: bool = False):
+        if self.first_token_time is None and text.strip():  # Set first token time on first non-empty text
+            self.first_token_time = time.time()
+        self.generated_text += text
+        # Count tokens in the generated text
+        tokens = self.tokenizer.encode(text, add_special_tokens=False)
+        self.token_count += len(tokens)
+        print(text, end="", flush=True)
+        if stream_end:
+            self.end_time = time.time()  # Record end time when streaming ends
+        if self.stop_flag:
+            raise StopIteration
+
+    def stop_generation(self):
+        self.stop_flag = True
+        self.end_time = time.time()  # Record end time when generation is stopped
+
+    def get_metrics(self):
+        """Returns initialization time, first token time, first token latency, end time, total time, total tokens, and tokens per second."""
+        if self.end_time is None:
+            self.end_time = time.time()  # Set end time if not already set
+        total_time = self.end_time - self.init_time  # Total time from init to end
+        tokens_per_second = self.token_count / total_time if total_time > 0 else 0
+        first_token_latency = (self.first_token_time - self.init_time) if self.first_token_time is not None else None
+        metrics = {
+            "init_time": self.init_time,
+            "first_token_time": self.first_token_time,
+            "first_token_latency": first_token_latency,
+            "end_time": self.end_time,
+            "total_time": total_time,  # Total time in seconds
+            "total_tokens": self.token_count,
+            "tokens_per_second": tokens_per_second
+        }
+        return metrics
+        
+def generate_stream(model, tokenizer, messages, skip_prompt, skip_special_tokens, do_sample, max_new_tokens):
+    input_ids = tokenizer.apply_chat_template(
+        messages,
+        tokenize=True,
+        add_generation_prompt=True,
+        return_tensors="pt"
+    )
+    attention_mask = torch.ones_like(input_ids, dtype=torch.long)
+    tokens = input_ids.to(model.device) 
+    attention_mask = attention_mask.to(model.device)
+
+    streamer = CustomTextStreamer(tokenizer, skip_prompt=skip_prompt, skip_special_tokens=skip_special_tokens)
+
+    def signal_handler(sig, frame):
+        streamer.stop_generation()
+        print("\n[Generation stopped by user with Ctrl+C]")
+
+    signal.signal(signal.SIGINT, signal_handler)
+
+    generate_kwargs = {}
+    if do_sample:
+        generate_kwargs = {
+              "do_sample": do_sample,
+              "max_length": max_new_tokens,
+              "temperature": 0.7,
+              "top_k": 20,
+              "top_p": 0.8,
+              "repetition_penalty": 1.2,
+              "no_repeat_ngram_size": 2
+        }
+    else:
+        generate_kwargs = {
+              "do_sample": do_sample,
+              "max_length": max_new_tokens,
+              "repetition_penalty": 1.2,
+              "no_repeat_ngram_size": 2
+        }
+  
+          
+    print("Response: ", end="", flush=True)
+    try:
+        generated_ids = model.generate(
+            tokens,
+            attention_mask=attention_mask,
+            #use_cache=False,
+            pad_token_id=tokenizer.pad_token_id,
+            streamer=streamer,
+            **generate_kwargs
+        )
+        del generated_ids
+    except StopIteration:
+        print("\n[Stopped by user]")
+
+    del input_ids, attention_mask
+    torch.cuda.empty_cache()
+    signal.signal(signal.SIGINT, signal.SIG_DFL)
+
+    return streamer.generated_text, streamer.stop_flag, streamer.get_metrics()
+
+while True:
+    print(f"skip_prompt: {skip_prompt}")
+    print(f"skip_special_tokens: {skip_special_tokens}")
+    print(f"do_sample: {do_sample}")
+    
+    user_input = input("User: ").strip()
+    if user_input.lower() == "/exit":
+        print("Exiting chat.")
+        break
+    if user_input.lower() == "/clear":
+        messages = []
+        print("Chat history cleared. Starting a new conversation.")
+        continue
+    if user_input.lower() == "/skip_prompt":
+        skip_prompt = not skip_prompt
+        continue
+    if user_input.lower() == "/skip_special_tokens":
+        skip_special_tokens = not skip_special_tokens
+        continue
+    if user_input.lower() == "/do_sample":
+        do_sample = not do_sample
+        continue
+    if not user_input:
+        print("Input cannot be empty. Please enter something.")
+        continue
+    
+
+    messages.append({"role": "user", "content": user_input})
+    activated_experts = []
+    response, stop_flag, metrics = generate_stream(model, tokenizer, messages, skip_prompt, skip_special_tokens, do_sample, 40960)
+    print("\n\nMetrics:")
+    for key, value in metrics.items():
+        print(f"  {key}: {value}")
+
+    print("", flush=True)
+    if stop_flag:
+        continue
+    messages.append({"role": "assistant", "content": response})
+
+
+```
+
+### Usage Warnings
+
+
+ - **Risk of Sensitive or Controversial Outputs**: This model’s safety filtering has been significantly reduced, potentially generating sensitive, controversial, or inappropriate content. Users should exercise caution and rigorously review generated outputs.
+
+ - **Not Suitable for All Audiences**: Due to limited content filtering, the model’s outputs may be inappropriate for public settings, underage users, or applications requiring high security.
+
+ - **Legal and Ethical Responsibilities**: Users must ensure their usage complies with local laws and ethical standards. Generated content may carry legal or ethical risks, and users are solely responsible for any consequences.
+
+ - **Research and Experimental Use**: It is recommended to use this model for research, testing, or controlled environments, avoiding direct use in production or public-facing commercial applications.
+
+ - **Monitoring and Review Recommendations**: Users are strongly advised to monitor model outputs in real-time and conduct manual reviews when necessary to prevent the dissemination of inappropriate content.
+
+ - **No Default Safety Guarantees**: Unlike standard models, this model has not undergone rigorous safety optimization. huihui.ai bears no responsibility for any consequences arising from its use.
+
+
+### Donation
+
+If you like it, please click 'like' and follow us for more updates.  
+You can follow [x.com/support_huihui](https://x.com/support_huihui) to get the latest model information from huihui.ai.
+
+##### Your donation helps us continue our further development and improvement, a cup of coffee can do it.
+- bitcoin（BTC):
+```
+  bc1qqnkhuchxw0zqjh2ku3lu4hq45hc6gy84uk70ge
+```
+- Support our work on Ko-fi (https://ko-fi.com/huihuiai)!

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 +1,83 @@
+{
+  "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": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 9728,
+  "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",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 262144,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "quantization_config": {
+    "modules_to_not_convert": null,
+    "quant_method": "torchao",
+    "quant_type": {
+      "default": {
+        "_data": {
+          "group_size": null,
+          "set_inductor_config": true
+        },
+        "_type": "Int8WeightOnlyConfig",
+        "_version": 1
+      }
+    },
+    "quant_type_kwargs": {}
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 5000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1601d80f2efe3d95a838f74133c1c2306b6de4e84cddafb6dcd501a9cc2560a5
+size 4422998410

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 +1,240 @@
+{
+  "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{%- endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 262144,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}