huihui-ai/Huihui-MiroThinker-v1.0-30B-abliterated
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: huihui-ai/Huihui-MiroThinker-v1.0-30B-abliterated
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-09 01:19:56 +08:00
commit 04c4a9fe45
25 changed files with 171055 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
.gitattributes vendored Normal file
View File

@@ -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

270
README.md Normal file
View File

@@ -0,0 +1,270 @@
---
library_name: transformers
pipeline_tag: text-generation
license: mit
language:
- en
base_model:
- miromind-ai/MiroThinker-v1.0-30B
tags:
- agent
- open-source
- miromind
- deep-research
- chat
- abliterated
- uncensored
---
# huihui-ai/Huihui-MiroThinker-v1.0-30B-abliterated
This is an uncensored version of [miromind-ai/MiroThinker-v1.0-30B](https://huggingface.co/miromind-ai/MiroThinker-v1.0-30B) 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/mirothinker1-abliterated:30b](https://ollama.com/huihui_ai/mirothinker1-abliterated:30b) directly,
```
ollama run huihui_ai/mirothinker1-abliterated:30b
```
## Usage
You can use this model in your applications by loading it with Hugging Face's `transformers` library:
```python
#!/usr/bin/env python
# -*- coding: utf-8 -*-
import argparse
from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig, TextStreamer
import torch
import os
import signal
import time
def parse_args():
parser = argparse.ArgumentParser(
description="Load HuggingFace model."
)
parser.add_argument(
"--base_model",
type=str,
default="huihui-ai/Huihui-MiroThinker-v1.0-30B-abliterated",
help="HuggingFace repo or local path of the base model.",
)
parser.add_argument(
"--dtype",
type=str,
default="bfloat16",
choices=["float16", "bfloat16", "float32"],
help="Data type for loading the base model (default: bfloat16).",
)
parser.add_argument(
"--device_map",
type=str,
default="auto",
help="Device map for model loading (e.g. 'cpu', 'auto').",
)
return parser.parse_args()
def main():
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')}")
args = parse_args()
# Load the model and tokenizer
print(f"Load Model {args.base_model} ... ")
quant_config_4 = BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_compute_dtype=torch.bfloat16,
bnb_4bit_quant_type="nf4" if args.device_map == "cpu" else "fp4",
bnb_4bit_use_double_quant=True,
llm_int8_enable_fp32_cpu_offload=True,
)
torch_dtype = {
"float16": torch.float16,
"bfloat16": torch.bfloat16,
"float32": torch.float32,
}[args.dtype]
model = AutoModelForCausalLM.from_pretrained(
args.base_model,
dtype=torch_dtype,
device_map=args.device_map,
trust_remote_code=True,
#quantization_config=quant_config_4,
#attn_implementation="eager",
)
tokenizer = AutoTokenizer.from_pretrained(args.base_model, trust_remote_code=True)
tokenizer.padding_side = 'left'
tokenizer.pad_token = tokenizer.eos_token
tokenizer.pad_token_id = tokenizer.eos_token_id
messages = []
skip_prompt=True
skip_special_tokens=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()
if stream_end:
self.end_time = time.time() # Record end time when streaming ends
self.generated_text += text
self.token_count += 1
print(text, end="", flush=True)
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, max_new_tokens):
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True,
)
inputs = tokenizer(
text,
return_tensors="pt",
).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(
**inputs,
max_new_tokens=max_new_tokens,
#pad_token_id=tokenizer.pad_token_id,
#eos_token_id=tokenizer.eos_token_id,
streamer=streamer
)
del generated_ids
except StopIteration:
print("\n[Stopped by user]")
del inputs
torch.cuda.empty_cache()
signal.signal(signal.SIGINT, signal.SIG_DFL)
return streamer.generated_text, streamer.stop_flag, streamer.get_metrics()
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() == "/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, metrics = generate_stream(model, tokenizer, messages, skip_prompt, skip_special_tokens, 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})
if __name__ == "__main__":
main()
```
### 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
##### Your donation helps us continue our further development and improvement, a cup of coffee can do it.
- bitcoin:
```
bc1qqnkhuchxw0zqjh2ku3lu4hq45hc6gy84uk70ge
```
- Support our work on [Ko-fi](https://ko-fi.com/huihuiai)!

28
added_tokens.json Normal file
View File

@@ -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
}

94
chat_template.jinja Normal file
View File

@@ -0,0 +1,94 @@
{%- if tools %}
{{- '<|im_start|>system\n' }}
{%- if messages[0].role == 'system' %}
{{- messages[0].content + '\n\n' }}
{%- endif %}
{{- "# 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>" }}
{%- for tool in tools %}
{{- "\n" }}
{{- tool | tojson }}
{%- endfor %}
{{- "\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" }}
{%- else %}
{%- if messages[0].role == 'system' %}
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
{%- for forward_message in messages %}
{%- set index = (messages|length - 1) - loop.index0 %}
{%- set message = messages[index] %}
{%- set current_content = message.content if message.content is not none else '' %}
{%- set tool_start = '<tool_response>' %}
{%- set tool_start_length = tool_start|length %}
{%- set start_of_message = current_content[:tool_start_length] %}
{%- set tool_end = '</tool_response>' %}
{%- set tool_end_length = tool_end|length %}
{%- set start_pos = (current_content|length) - tool_end_length %}
{%- if start_pos < 0 %}
{%- set start_pos = 0 %}
{%- endif %}
{%- set end_of_message = current_content[start_pos:] %}
{%- if ns.multi_step_tool and message.role == "user" and not(start_of_message == tool_start and end_of_message == tool_end) %}
{%- set ns.multi_step_tool = false %}
{%- set ns.last_query_index = index %}
{%- endif %}
{%- endfor %}
{%- for message in messages %}
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
{%- elif message.role == "assistant" %}
{%- set content = message.content %}
{%- set reasoning_content = '' %}
{%- if message.reasoning_content is defined and message.reasoning_content is not none %}
{%- set reasoning_content = message.reasoning_content %}
{%- else %}
{%- if '</think>' in message.content %}
{%- set content = (message.content.split('</think>')|last).lstrip('\n') %}
{%- set reasoning_content = (message.content.split('</think>')|first).rstrip('\n') %}
{%- set reasoning_content = (reasoning_content.split('<think>')|last).lstrip('\n') %}
{%- endif %}
{%- endif %}
{%- if loop.index0 > ns.last_query_index %}
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
{%- else %}
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
{%- endif %}
{%- if message.tool_calls %}
{%- for tool_call in message.tool_calls %}
{%- if (loop.first and content) or (not loop.first) %}
{{- '\n' }}
{%- endif %}
{%- if tool_call.function %}
{%- set tool_call = tool_call.function %}
{%- endif %}
{{- '<tool_call>\n{"name": "' }}
{{- tool_call.name }}
{{- '", "arguments": ' }}
{%- if tool_call.arguments is string %}
{{- tool_call.arguments }}
{%- else %}
{{- tool_call.arguments | tojson }}
{%- endif %}
{{- '}\n</tool_call>' }}
{%- endfor %}
{%- endif %}
{{- '<|im_end|>\n' }}
{%- elif message.role == "tool" %}
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
{{- '<|im_start|>user' }}
{%- endif %}
{{- '\n<tool_response>\n' }}
{{- message.content }}
{{- '\n</tool_response>' }}
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
{{- '<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- endfor %}
{%- if add_generation_prompt %}
{{- '<|im_start|>assistant\n' }}
{%- if enable_thinking is defined and enable_thinking is false %}
{{- '<think>\n\n</think>\n\n' }}
{%- endif %}
{%- endif %}

38
config.json Normal file
View File

@@ -0,0 +1,38 @@
{
"architectures": [
"Qwen3MoeForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 151643,
"decoder_sparse_step": 1,
"dtype": "bfloat16",
"eos_token_id": 151645,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 6144,
"max_position_embeddings": 262144,
"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": 10000000,
"router_aux_loss_coef": 0.001,
"sliding_window": null,
"tie_word_embeddings": false,
"transformers_version": "4.57.1",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151936
}

13
generation_config.json Normal file
View File

@@ -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": "4.57.1"
}

151388
merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

3
model-00001-of-00013.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:96c1ab48ccd6e08e6165164b0c96e7414832a8b76715edda72e0373f2c713e8c
size 4997184968

3
model-00002-of-00013.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:48e76dea1232b89fea236b155f6b70958fa08c0f3426ef060cc80398c27a039d
size 4997741608

3
model-00003-of-00013.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:17f068ab38f362d9773df60b916f25b77c51ade2ac088af6cbff0588585e0f3c
size 4997742208

3
model-00004-of-00013.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b4c8ef7cd581e6cb0ef7fc0f962249cf20843d642910acf3ca01c8370b382704
size 4997743184

3
model-00005-of-00013.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a146039289a70440a59418561c6caca737915ed367f30313f9b1d6c9ab774bb6
size 4997743184

3
model-00006-of-00013.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8c1e0187e8523a83c4290489beea8d6e713d60419263b57d223aad42a133b076
size 4997743184

3
model-00007-of-00013.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3bbeab80083e9e50575ffdf9af4492bfee791901a39484f157a1c3bdb393a125
size 4997743184

3
model-00008-of-00013.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f078d5412b6038169b78e57d4a52bf3169946d3f6166298d313d2a190d9720e9
size 4997743184

3
model-00009-of-00013.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cd477a59e153b922528fdb0b009f1e81096c28aa970060a1b2091877ecce0876
size 4997743184

3
model-00010-of-00013.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:33e4e9e6538c5a72cbbe9507ea6202bffe49becc73cd28d73bf3e458825983bd
size 4997743184

3
model-00011-of-00013.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8e10d188c41e96794c9cc5b697e576540b095c3e434199013115192f9f817728
size 4997743184

3
model-00012-of-00013.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3027e9cc70e40603135b60b591fd225fe2a55bd36520f1c38dcbe0c61e119491
size 4997743184

3
model-00013-of-00013.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b55e3b3a456d8ef16344d90c8a62af269c2f5e798a19d6c1e765a545a186503e
size 1094220288

18875
model.safetensors.index.json Normal file
View File

File diff suppressed because it is too large Load Diff

31
special_tokens_map.json Normal file
View File

@@ -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
}
}

3
tokenizer.json Normal file
View File

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

239
tokenizer_config.json Normal file
View File

@@ -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,
"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
}

1
vocab.json Normal file
View File

File diff suppressed because one or more lines are too long