Hugging Face's logo

t-tech
/
T-pro-it-2.0-FP8

Safetensors
Russian
qwen3
fp8
Model card Files
xet
Community
German Abramov commited on
Commit
17d6e7b
·
1 Parent(s): 794fbb2

added ckpt

Browse files
Files changed (18) hide show
  1. README.md +119 -3
  2. added_tokens.json +27 -0
  3. chat_template.jinja +89 -0
  4. config.json +105 -0
  5. generation_config.json +8 -0
  6. merges.txt +0 -0
  7. model-00001-of-00007.safetensors +3 -0
  8. model-00002-of-00007.safetensors +3 -0
  9. model-00003-of-00007.safetensors +3 -0
  10. model-00004-of-00007.safetensors +3 -0
  11. model-00005-of-00007.safetensors +3 -0
  12. model-00006-of-00007.safetensors +3 -0
  13. model-00007-of-00007.safetensors +3 -0
  14. model.safetensors.index.json +0 -0
  15. special_tokens_map.json +31 -0
  16. tokenizer.json +3 -0
  17. tokenizer_config.json +239 -0
  18. vocab.json +0 -0
README.md CHANGED
@@ -1,3 +1,119 @@
1
- ---
2
- license: apache-2.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - ru
4
+ license: apache-2.0
5
+ base_model:
6
+ - Qwen/Qwen3-32B
7
+ ---
8
+ # T-pro-it-2.0-FP8
9
+
10
+ > **Main BF16 model:** [t-tech/T-pro-it-2.0](https://huggingface.co/t-tech/T-pro-it-2.0)
11
+
12
+ **🚨 Users are advised to exercise caution and are responsible for any additional training and oversight required to ensure the model's responses meet acceptable ethical and safety standards. The responsibility for incorporating this model into industrial or commercial solutions lies entirely with those who choose to deploy it.**
13
+
14
+ T‑pro‑it‑2.0‑FP8 is a fine‑grained FP8‑quantised version of **T‑pro‑it‑2.0** (built on the Qwen‑3 family). It delivers identical capabilities with roughly half the memory footprint and higher inference speed.
15
+ ## Description
16
+
17
+ T-pro-it-2.0 is a model built upon the Qwen 3 model family and incorporates both continual pre-training and alignment techniques.
18
+
19
+ ### 📚 Dataset
20
+
21
+ Instruction Pre-Training:
22
+ 40B tokens of instruction data, with one-third focused on reasoning tasks.
23
+
24
+ Supervised Fine-Tuning (SFT):
25
+ ~500K high-quality and diverse instructions with balanced complexity. Reasoning tasks make up about 20% of the dataset.
26
+
27
+ Preference Tuning:
28
+ ~100K carefully selected instructions, filtered by length and type for general tasks and with domain-balanced selection for reasoning tasks.
29
+
30
+ ## 📊 Benchmarks
31
+
32
+ TBD
33
+
34
+ ## Note on FP8
35
+
36
+ For convenience and performance, we have provided `fp8`-quantized model checkpoint for T-pro-it-2.0, whose name ends with `-FP8`. The quantization method is fine-grained `fp8` quantization with block size of 128. You can find more details in the `quantization_config` field in `config.json`.
37
+
38
+ You can use the T-pro-it-2.0-FP8 model with serveral inference frameworks, including `transformers`, `sglang`, and `vllm`, as the original bfloat16 model.
39
+ However, please pay attention to the following known issues:
40
+ - `transformers`:
41
+ - there are currently issues with the "fine-grained fp8" method in `transformers` for distributed inference. You may need to set the environment variable `CUDA_LAUNCH_BLOCKING=1` if multiple devices are used in inference.
42
+
43
+
44
+ ## Switching Between Thinking and Non‑Thinking Modes
45
+
46
+ To enable or disable reasoning mode in HuggingFace, set the `enable_thinking` flag in `tokenizer.apply_chat_template`.
47
+ For more details, see:
48
+ - [SGLang Thinking/Non‑Thinking Modes](https://qwen.readthedocs.io/en/latest/deployment/sglang.html#thinking-non-thinking-modes)
49
+ - [vLLM Thinking/Non‑Thinking Modes](https://qwen.readthedocs.io/en/latest/deployment/vllm.html#thinking-non-thinking-modes)
50
+
51
+ ---
52
+
53
+ ## Recommended Generation Parameters
54
+
55
+ | Mode | Temperature | presence_penalty |
56
+ |-----------------------------------|-------------|------------------|
57
+ | No‑think (general requests) | ≤ 0.3 | 1.0 |
58
+ | Think mode (standard requests) | ≈ 0.6 | 1.0 |
59
+ | Complex reasoning requests | ≥ 0.8 | 1.0 |
60
+
61
+
62
+ ## 👨‍💻 Examples of usage
63
+
64
+ ### HF Usage
65
+
66
+ ```python
67
+ from transformers import AutoTokenizer, AutoModelForCausalLM
68
+ import torch
69
+ torch.manual_seed(42)
70
+
71
+ model_name = "t-tech/T-pro-it-2.0-FP8"
72
+ tokenizer = AutoTokenizer.from_pretrained(model_name)
73
+ model = AutoModelForCausalLM.from_pretrained(
74
+ model_name,
75
+ torch_dtype="auto",
76
+ device_map="auto",
77
+ )
78
+
79
+ prompt = (
80
+ "Пожалуйста, вычисли определённый интеграл ∫_0^1 x² eˣ dx, "
81
+ "пошагово объясни решение и укажи окончательный результат."
82
+ )
83
+ messages = [
84
+ {"role": "system", "content": "Ты T-pro, виртуальный ассистент в Т-Технологии. Твоя задача - быть полезным диалоговым ассистентом."},
85
+ {"role": "user", "content": prompt}
86
+ ]
87
+ text = tokenizer.apply_chat_template(
88
+ messages,
89
+ tokenize=False,
90
+ add_generation_prompt=True,
91
+ enable_thinking=True # Switches between thinking and non-thinking modes. Default is True.
92
+ )
93
+ model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
94
+
95
+ generated_ids = model.generate(
96
+ **model_inputs,
97
+ max_new_tokens=512
98
+ )
99
+ generated_ids = [
100
+ output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
101
+ ]
102
+
103
+ response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
104
+
105
+ print(response)
106
+
107
+ ```
108
+
109
+ ### Deployment
110
+
111
+ For deployment, you can use `sglang>=0.4.6.post1` or `vllm>=0.8.5` or to create an OpenAI-compatible API endpoint:
112
+ - SGLang:
113
+ ```shell
114
+ python -m sglang.launch_server --model-path t-tech/T‑pro‑it‑2.0‑FP8 --reasoning-parser qwen3
115
+ ```
116
+ - vLLM:
117
+ ```shell
118
+ vllm serve t-tech/T‑pro‑it‑2.0‑FP8 --enable-reasoning --reasoning-parser deepseek_r1
119
+ ```
added_tokens.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151667,
3
+ "</tool_call>": 151657,
4
+ "</tool_response>": 151665,
5
+ "<think>": 151666,
6
+ "<tool_call>": 151656,
7
+ "<tool_response>": 151664,
8
+ "<|box_end|>": 151648,
9
+ "<|box_start|>": 151647,
10
+ "<|file_sep|>": 151663,
11
+ "<|fim_middle|>": 151659,
12
+ "<|fim_pad|>": 151661,
13
+ "<|fim_prefix|>": 151658,
14
+ "<|fim_suffix|>": 151660,
15
+ "<|im_end|>": 151644,
16
+ "<|im_start|>": 151643,
17
+ "<|image_pad|>": 151654,
18
+ "<|object_ref_end|>": 151646,
19
+ "<|object_ref_start|>": 151645,
20
+ "<|quad_end|>": 151650,
21
+ "<|quad_start|>": 151649,
22
+ "<|repo_name|>": 151662,
23
+ "<|video_pad|>": 151655,
24
+ "<|vision_end|>": 151652,
25
+ "<|vision_pad|>": 151653,
26
+ "<|vision_start|>": 151651
27
+ }
chat_template.jinja ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0].role == 'system' %}
4
+ {{- messages[0].content + '\n\n' }}
5
+ {%- endif %}
6
+ {{- "# 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>" }}
7
+ {%- for tool in tools %}
8
+ {{- "\n" }}
9
+ {{- tool | tojson }}
10
+ {%- endfor %}
11
+ {{- "\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" }}
12
+ {%- else %}
13
+ {%- if messages[0].role == 'system' %}
14
+ {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
+ {%- endif %}
16
+ {%- endif %}
17
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
18
+ {%- for message in messages[::-1] %}
19
+ {%- set index = (messages|length - 1) - loop.index0 %}
20
+ {%- 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>')) %}
21
+ {%- set ns.multi_step_tool = false %}
22
+ {%- set ns.last_query_index = index %}
23
+ {%- endif %}
24
+ {%- endfor %}
25
+ {%- for message in messages %}
26
+ {%- if message.content is string %}
27
+ {%- set content = message.content %}
28
+ {%- else %}
29
+ {%- set content = '' %}
30
+ {%- endif %}
31
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
32
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
33
+ {%- elif message.role == "assistant" %}
34
+ {%- set reasoning_content = '' %}
35
+ {%- if message.reasoning_content is string %}
36
+ {%- set reasoning_content = message.reasoning_content %}
37
+ {%- else %}
38
+ {%- if '</think>' in content %}
39
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
40
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
41
+ {%- endif %}
42
+ {%- endif %}
43
+ {%- if loop.index0 > ns.last_query_index %}
44
+ {%- if loop.last or (not loop.last and reasoning_content) %}
45
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
46
+ {%- else %}
47
+ {{- '<|im_start|>' + message.role + '\n' + content }}
48
+ {%- endif %}
49
+ {%- else %}
50
+ {{- '<|im_start|>' + message.role + '\n' + content }}
51
+ {%- endif %}
52
+ {%- if message.tool_calls %}
53
+ {%- for tool_call in message.tool_calls %}
54
+ {%- if (loop.first and content) or (not loop.first) %}
55
+ {{- '\n' }}
56
+ {%- endif %}
57
+ {%- if tool_call.function %}
58
+ {%- set tool_call = tool_call.function %}
59
+ {%- endif %}
60
+ {{- '<tool_call>\n{"name": "' }}
61
+ {{- tool_call.name }}
62
+ {{- '", "arguments": ' }}
63
+ {%- if tool_call.arguments is string %}
64
+ {{- tool_call.arguments }}
65
+ {%- else %}
66
+ {{- tool_call.arguments | tojson }}
67
+ {%- endif %}
68
+ {{- '}\n</tool_call>' }}
69
+ {%- endfor %}
70
+ {%- endif %}
71
+ {{- '<|im_end|>\n' }}
72
+ {%- elif message.role == "tool" %}
73
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
74
+ {{- '<|im_start|>user' }}
75
+ {%- endif %}
76
+ {{- '\n<tool_response>\n' }}
77
+ {{- content }}
78
+ {{- '\n</tool_response>' }}
79
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
80
+ {{- '<|im_end|>\n' }}
81
+ {%- endif %}
82
+ {%- endif %}
83
+ {%- endfor %}
84
+ {%- if add_generation_prompt %}
85
+ {{- '<|im_start|>assistant\n' }}
86
+ {%- if enable_thinking is defined and enable_thinking is false %}
87
+ {{- '<think>\n\n</think>\n\n' }}
88
+ {%- endif %}
89
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,105 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "eos_token_id": 8956,
8
+ "head_dim": 128,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 5120,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 25600,
13
+ "layer_types": [
14
+ "full_attention",
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention",
51
+ "full_attention",
52
+ "full_attention",
53
+ "full_attention",
54
+ "full_attention",
55
+ "full_attention",
56
+ "full_attention",
57
+ "full_attention",
58
+ "full_attention",
59
+ "full_attention",
60
+ "full_attention",
61
+ "full_attention",
62
+ "full_attention",
63
+ "full_attention",
64
+ "full_attention",
65
+ "full_attention",
66
+ "full_attention",
67
+ "full_attention",
68
+ "full_attention",
69
+ "full_attention",
70
+ "full_attention",
71
+ "full_attention",
72
+ "full_attention",
73
+ "full_attention",
74
+ "full_attention",
75
+ "full_attention",
76
+ "full_attention",
77
+ "full_attention"
78
+ ],
79
+ "max_position_embeddings": 40960,
80
+ "max_window_layers": 64,
81
+ "model_type": "qwen3",
82
+ "num_attention_heads": 64,
83
+ "num_hidden_layers": 64,
84
+ "num_key_value_heads": 8,
85
+ "pad_token_id": 151654,
86
+ "quantization_config": {
87
+ "activation_scheme": "dynamic",
88
+ "modules_to_not_convert": null,
89
+ "quant_method": "fp8",
90
+ "weight_block_size": [
91
+ 128,
92
+ 128
93
+ ]
94
+ },
95
+ "rms_norm_eps": 1e-06,
96
+ "rope_scaling": null,
97
+ "rope_theta": 1000000,
98
+ "sliding_window": null,
99
+ "tie_word_embeddings": false,
100
+ "torch_dtype": "bfloat16",
101
+ "transformers_version": "4.53.2",
102
+ "use_cache": false,
103
+ "use_sliding_window": false,
104
+ "vocab_size": 151668
105
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": 151644,
4
+ "pad_token_id": 8956,
5
+ "temperature": 0.6,
6
+ "presence_penalty": 1.0,
7
+ "transformers_version": "4.51.3"
8
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a30d0811cfd5b55143ec9190cdfa0e4612ac69b5bfcf95b2a530ee098ef8f0e0
3
+ size 4966773880
model-00002-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07e4b713f4b0594a6e3e59c8348e1caea4273ba5a72d8f0edfcc53d7ee41ae90
3
+ size 4971089136
model-00003-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c60657e5732163c0ba9181fcd7987d71dcf9918223b959bd9762c354e5291c85
3
+ size 4876704184
model-00004-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a641b67b04fd638a12ab546859ec17beb34623a2a63c5c131053790f01087b11
3
+ size 4876704184
model-00005-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a33bcfea390914a8f00655c65fb121069663b8964a2733d1095410ceac98c3bb
3
+ size 4876704184
model-00006-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3700ef07c2d4f6d022758bc704003096713958df944b529d0fd615fbd03079c3
3
+ size 4876704184
model-00007-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce2812116dd459ff64b11e1de2c2d376f7518bf5fdbd1ed7c130ede079aeda82
3
+ size 4872399248
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|image_pad|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f021b3d276c7b8f00a2a2412bc360a9079b2572eb159d7bcee3810acb4507a4e
3
+ size 13040411
tokenizer_config.json ADDED
@@ -0,0 +1,239 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "8956": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151643": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151644": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151645": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151646": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151647": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151648": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151649": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151650": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151651": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151652": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151653": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151654": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151655": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151656": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151657": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151658": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151659": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151660": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151661": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151662": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151663": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151664": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151665": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151666": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151667": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "clean_up_tokenization_spaces": false,
231
+ "eos_token": "<|im_end|>",
232
+ "errors": "replace",
233
+ "extra_special_tokens": {},
234
+ "model_max_length": 131072,
235
+ "pad_token": "<|endoftext|>",
236
+ "split_special_tokens": false,
237
+ "tokenizer_class": "Qwen2Tokenizer",
238
+ "unk_token": null
239
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff