Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ 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
+quantization_config.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,219 @@
+---
+library_name: transformers
+license: apache-2.0
+license_link: https://huggingface.co/Qwen/Qwen3-30B-A3B/blob/main/LICENSE
+pipeline_tag: text-generation
+base_model:
+- Qwen/Qwen3-30B-A3B
+tags:
+- chat
+- abliterated
+- uncensored
+extra_gated_prompt: >-
+    **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.
+
+
+---
+
+# huihui-ai/Qwen3-30B-A3B-abliterated
+
+
+This is an uncensored version of [Qwen/Qwen3-30B-A3B](https://huggingface.co/Qwen/Qwen3-30B-A3B) 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. 
+
+## ollama
+
+You can use [huihui_ai/qwen3-abliterated:30b](https://ollama.com/huihui_ai/qwen3-abliterated:30b) directly, 
+```
+ollama run huihui_ai/qwen3-abliterated:30b
+```
+
+## Usage
+You can use this model in your applications by loading it with Hugging Face's `transformers` library:
+You can try using **/no_think** to toggle think mode, but it’s not guaranteed to work every time.
+
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig, TextStreamer
+import torch
+import os
+import signal
+
+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/Qwen3-30B-A3B-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_int14_enable_fp32_cpu_offload=True,
+)
+
+model = AutoModelForCausalLM.from_pretrained(
+    NEW_MODEL_ID,
+    device_map="auto",
+    trust_remote_code=True,
+    #quantization_config=quant_config_4,
+    torch_dtype=torch.bfloat16
+)
+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 = []
+enable_thinking = True
+skip_prompt=True
+skip_special_tokens=True
+
+def apply_chat_template(tokenizer, messages, enable_thinking, add_generation_prompt=True):
+    input_ids = tokenizer.apply_chat_template(
+        messages,
+        tokenize=False,
+        add_generation_prompt=add_generation_prompt,
+    )
+    if not enable_thinking:
+        input_ids += "\n<think>\n\n</think>\n"
+    return input_ids
+
+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
+
+    def on_finalized_text(self, text: str, stream_end: bool = False):
+        self.generated_text += text
+        print(text, end="", flush=True)
+        if self.stop_flag:
+            raise StopIteration
+
+    def stop_generation(self):
+        self.stop_flag = True
+
+def generate_stream(model, tokenizer, messages, enable_thinking, skip_prompt, skip_special_tokens, max_new_tokens):
+    formatted_prompt = apply_chat_template(tokenizer, messages, enable_thinking)
+    input_ids = tokenizer(
+        formatted_prompt,
+        return_tensors="pt",
+        return_attention_mask=True,
+        padding=False
+    )
+    
+    tokens = input_ids['input_ids'].to(model.device)
+    attention_mask = input_ids['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)
+    
+    print("Response: ", end="", flush=True)
+    try:
+        generated_ids = model.generate(
+            tokens,
+            attention_mask=attention_mask,
+            use_cache=False,
+            max_new_tokens=max_new_tokens,
+            do_sample=True,
+            pad_token_id=tokenizer.pad_token_id,
+            streamer=streamer
+        )
+        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
+
+while True:
+    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() == "/no_think":
+        if enable_thinking:
+            enable_thinking = False
+            print("Thinking = False.")
+        else:
+            enable_thinking = True
+            print("Thinking = True.")        
+        continue
+    if user_input.lower() == "/skip_prompt":
+        if skip_prompt:
+            skip_prompt = False
+            print("skip_prompt = False.")
+        else:
+            skip_prompt = True
+            print("skip_prompt = True.")        
+        continue
+    if user_input.lower() == "/skip_special_tokens":
+        if skip_special_tokens:
+            skip_special_tokens = False
+            print("skip_special_tokens = False.")
+        else:
+            skip_special_tokens = True
+            print("skip_special_tokens = True.")        
+        continue
+    if not user_input:
+        print("Input cannot be empty. Please enter something.")
+        continue
+    messages.append({"role": "user", "content": user_input})
+    response, stop_flag = generate_stream(model, tokenizer, messages, enable_thinking, skip_prompt, skip_special_tokens, 14192)
+    print("", flush=True)
+    if stop_flag:
+        continue
+    messages.append({"role": "assistant", "content": response})
+```
+
+## Specific usage
+You can achieve better results using AblationDecoderLayer. For specific usage, please refer to the file [load-Qwen3-30B-A3B-abliterated.py](https://huggingface.co/huihui-ai/Qwen3-30B-A3B-abliterated/blob/main/load-Qwen3-30B-A3B-abliterated.py).
+
+The candidate layers can be 16(final_refusal_dir.pt).
+You can try using **/no_think** to toggle think mode.
+
+
+### 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):
+```
+  bc1qqnkhuchxw0zqjh2ku3lu14hq145hc6gy1414uk70ge
+```

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 +1,49 @@
+{
+    "architectures": [
+        "Qwen3MoeForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "decoder_sparse_step": 1,
+    "eos_token_id": 151645,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 2048,
+    "initializer_range": 0.02,
+    "intermediate_size": 6144,
+    "max_position_embeddings": 40960,
+    "max_window_layers": 48,
+    "mlp_only_layers": [],
+    "model_type": "qwen3_moe",
+    "moe_intermediate_size": 768,
+    "norm_topk_prob": true,
+    "num_attention_heads": 32,
+    "num_experts": 128,
+    "num_experts_per_tok": 8,
+    "num_hidden_layers": 48,
+    "num_key_value_heads": 4,
+    "output_router_logits": false,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": null,
+    "rope_theta": 1000000.0,
+    "router_aux_loss_coef": 0.001,
+    "sliding_window": null,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.51.3",
+    "use_cache": true,
+    "use_sliding_window": false,
+    "vocab_size": 151936,
+    "quantization_config": {
+        "quant_method": "exl3",
+        "version": "0.0.2",
+        "bits": 4.0,
+        "head_bits": 8,
+        "calibration": {
+            "rows": 100,
+            "cols": 2048
+        },
+        "out_scales": "auto"
+    }
+}

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"
+}

gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

load-Qwen3-30B-A3B-abliterated.py

@@ -0,0 +1,174 @@
+from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig, TextStreamer
+import torch
+import torch.nn as nn
+import os
+import signal
+from typing import Optional, Tuple
+import einops
+import jaxtyping
+
+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
+MODEL_ID = "Qwen/Qwen3-30B-A3B"
+print(f"Load Model {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(
+    MODEL_ID,
+    device_map="auto",
+    trust_remote_code=True,
+    quantization_config=quant_config_4,
+    torch_dtype=torch.bfloat16
+)
+
+tokenizer = AutoTokenizer.from_pretrained(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 = []
+enable_thinking = True
+skip_prompt=True
+skip_special_tokens=True
+
+def direction_ablation_hook(activation: jaxtyping.Float[torch.Tensor, "... d_act"],
+                            direction: jaxtyping.Float[torch.Tensor, "d_act"]):
+    proj = einops.einsum(activation, direction.view(-1, 1), '... d_act, d_act single -> ... single') * direction
+    return activation - proj
+
+class AblationDecoderLayer(nn.Module):
+    def __init__(self, original_layer, refusal_dir):
+        super(AblationDecoderLayer, self).__init__()
+        self.original_layer = original_layer
+        self.refusal_dir = refusal_dir
+
+    def forward(self, *args, **kwargs):
+        hidden_states = args[0]
+        ablated = direction_ablation_hook(hidden_states, self.refusal_dir.to(hidden_states.device)).to(hidden_states.device)
+        args = (ablated,) + args[1:]
+        return self.original_layer.forward(*args, **kwargs)
+
+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
+
+    def on_finalized_text(self, text: str, stream_end: bool = False):
+        self.generated_text += text
+        print(text, end="", flush=True)
+        if self.stop_flag:
+            raise StopIteration
+
+    def stop_generation(self):
+        self.stop_flag = True
+
+def generate_stream(model, tokenizer, messages, enable_thinking, skip_prompt, skip_special_tokens, max_new_tokens):
+    input_ids = tokenizer.apply_chat_template(
+        messages,
+        tokenize=True,
+        enable_thinking = enable_thinking,
+        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)
+    
+    print("Response: ", end="", flush=True)
+    try:
+        generated_ids = model.generate(
+            tokens,
+            attention_mask=attention_mask,
+            use_cache=False,
+            max_new_tokens=max_new_tokens,
+            do_sample=True,
+            pad_token_id=tokenizer.pad_token_id,
+            streamer=streamer
+        )
+        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
+
+
+
+final_refusal_dirs= torch.load(MODEL_ID + "/final_refusal_dirs.pt", map_location='cpu', weights_only=True)
+# candidate layer, 16, 21 ...
+candidate_layer = 16
+
+refusal_dir = final_refusal_dirs[candidate_layer]
+
+for idx in range(len(model.model.layers)):
+    model.model.layers[idx] = AblationDecoderLayer(model.model.layers[idx], refusal_dir)
+
+while True:
+    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() == "/no_think":
+        if enable_thinking:
+            enable_thinking = False
+            print("Thinking = False.")
+        else:
+            enable_thinking = True
+            print("Thinking = True.")        
+        continue
+    if user_input.lower() == "/skip_prompt":
+        if skip_prompt:
+            skip_prompt = False
+            print("skip_prompt = False.")
+        else:
+            skip_prompt = True
+            print("skip_prompt = True.")        
+        continue
+    if user_input.lower() == "/skip_special_tokens":
+        if skip_special_tokens:
+            skip_special_tokens = False
+            print("skip_special_tokens = False.")
+        else:
+            skip_special_tokens = True
+            print("skip_special_tokens = True.")        
+        continue
+    if not user_input:
+        print("Input cannot be empty. Please enter something.")
+        continue
+    messages.append({"role": "user", "content": user_input})
+    response, stop_flag = generate_stream(model, tokenizer, messages, enable_thinking, skip_prompt, skip_special_tokens, 8192)
+    print("", flush=True)
+    if stop_flag:
+        continue
+    messages.append({"role": "assistant", "content": response})

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c30dab1216e517b9195ba159b2a5270d9e6b0b75b772eb90435d167d6909f0b7
+size 8479696528

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3880ca2fbaf8c036edde7e9e1ebf7c7f6c6b5c9bb9c6c5693ca07b6532be7232
+size 7540222304

quantization_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da44d3c511b4e8698e8fbaf8ef8f232178193f972b31bf4abe52fd697abe29e0
+size 18426475

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