Hugging Face's logo

iamPi
/
mnl

Safetensors
deepseek_v3
Model card Files
xet
 Community
iamPi commited on
Commit
8307655
·
0 Parent(s):

Duplicate from iamPi/Moonlight-Instruct

Browse files
Files changed (35) hide show
  1. .gitattributes +36 -0
  2. chat_template.jinja +112 -0
  3. config.json +54 -0
  4. generation_config.json +7 -0
  5. model-1-of-27.safetensors +3 -0
  6. model-10-of-27.safetensors +3 -0
  7. model-11-of-27.safetensors +3 -0
  8. model-12-of-27.safetensors +3 -0
  9. model-13-of-27.safetensors +3 -0
  10. model-14-of-27.safetensors +3 -0
  11. model-15-of-27.safetensors +3 -0
  12. model-16-of-27.safetensors +3 -0
  13. model-17-of-27.safetensors +3 -0
  14. model-18-of-27.safetensors +3 -0
  15. model-19-of-27.safetensors +3 -0
  16. model-2-of-27.safetensors +3 -0
  17. model-20-of-27.safetensors +3 -0
  18. model-21-of-27.safetensors +3 -0
  19. model-22-of-27.safetensors +3 -0
  20. model-23-of-27.safetensors +3 -0
  21. model-24-of-27.safetensors +3 -0
  22. model-25-of-27.safetensors +3 -0
  23. model-26-of-27.safetensors +3 -0
  24. model-27-of-27.safetensors +3 -0
  25. model-3-of-27.safetensors +3 -0
  26. model-4-of-27.safetensors +3 -0
  27. model-5-of-27.safetensors +3 -0
  28. model-6-of-27.safetensors +3 -0
  29. model-7-of-27.safetensors +3 -0
  30. model-8-of-27.safetensors +3 -0
  31. model-9-of-27.safetensors +3 -0
  32. model.safetensors.index.json +0 -0
  33. preprocessor_config.json +30 -0
  34. special_tokens_map.json +41 -0
  35. tokenizer_config.json +29 -0
.gitattributes ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
chat_template.jinja ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- macro render_content(msg) -%}
2
+ {%- set c = msg.get('content') -%}
3
+ {%- if c is string -%}
4
+ {{ c }}
5
+ {%- elif c is not none -%}
6
+ {% for content in c -%}
7
+ {% if content['type'] == 'image' or content['type'] == 'image_url' -%}
8
+ <|media_begin|>image<|media_content|><|media_pad|><|media_end|>
9
+ {% elif content['type'] == 'video' or content['type']== 'video_url'-%}
10
+ <|kimi_k25_video_placeholder|>
11
+ {% else -%}
12
+ {{ content['text'] }}
13
+ {%- endif -%}
14
+ {%- endfor -%}
15
+ {%- endif -%}
16
+ {%- endmacro -%}
17
+
18
+ {% macro set_roles(message) -%}
19
+ {%- set role_name = message.get('name') or message['role'] -%}
20
+ {%- if message['role'] == 'user' -%}
21
+ <|im_user|>{{role_name}}<|im_middle|>
22
+ {%- elif message['role'] == 'assistant' -%}
23
+ <|im_assistant|>{{role_name}}<|im_middle|>
24
+ {%- else -%}
25
+ <|im_system|>{{role_name}}<|im_middle|>
26
+ {%- endif -%}
27
+ {%- endmacro -%}
28
+
29
+
30
+ {%- macro render_toolcalls(message) -%}
31
+ <|tool_calls_section_begin|>
32
+ {%- for tool_call in message['tool_calls'] -%}
33
+ {%- set formatted_id = tool_call['id'] -%}
34
+ <|tool_call_begin|>{{ formatted_id }}<|tool_call_argument_begin|>{% if tool_call['function']['arguments'] is string %}{{ tool_call['function']['arguments'] }}{% else %}{{ tool_call['function']['arguments'] | tojson }}{% endif %}<|tool_call_end|>
35
+ {%- endfor -%}
36
+ <|tool_calls_section_end|>
37
+ {%- endmacro -%}
38
+
39
+
40
+ {%- set preserve_thinking = preserve_thinking | default(false) -%}
41
+ {# Find last non-tool-call assistant message. If preserve_thinking, keep -1 so hist is empty and all msgs use suffix (retain reasoning). #}
42
+ {%- set ns = namespace(last_non_tool_call_assistant_msg=-1) -%}
43
+ {%- if not preserve_thinking -%}
44
+ {%- for idx in range(messages|length-1, -1, -1) -%}
45
+ {%- if messages[idx]['role'] == 'assistant' and not messages[idx].get('tool_calls') -%}
46
+ {%- set ns.last_non_tool_call_assistant_msg = idx -%}
47
+ {%- break -%}
48
+ {%- endif -%}
49
+ {%- endfor -%}
50
+ {%- endif -%}
51
+
52
+ {# split all messages into history & suffix, reasoning_content in suffix should be reserved.#}
53
+ {%- set hist_msgs = messages[:ns.last_non_tool_call_assistant_msg+1] -%}
54
+ {%- set suffix_msgs = messages[ns.last_non_tool_call_assistant_msg+1:] -%}
55
+
56
+ {%- if tools -%}
57
+ {%- if tools_ts_str -%}
58
+ <|im_system|>tool_declare<|im_middle|>{{ tools_ts_str }}<|im_end|>
59
+ {%- else -%}
60
+ <|im_system|>tool_declare<|im_middle|>{{ tools | tojson(separators=(',', ':')) }}<|im_end|>
61
+ {%- endif -%}
62
+ {%- endif -%}
63
+
64
+
65
+ {%- for message in hist_msgs -%}
66
+ {{set_roles(message)}}
67
+ {%- if message['role'] == 'assistant' -%}
68
+ <think></think>{{render_content(message)}}
69
+ {%- if message.get('tool_calls') -%}
70
+ {{render_toolcalls(message)}}
71
+ {%- endif -%}
72
+ {%- elif message['role'] == 'tool' -%}
73
+ {%- set tool_call_id = message.tool_call_id -%}
74
+ ## Return of {{ tool_call_id }}
75
+ {{render_content(message)}}
76
+ {%- elif message['content'] is not none -%}
77
+ {{render_content(message)}}
78
+ {%- endif -%}
79
+ <|im_end|>
80
+ {%- endfor -%}
81
+
82
+ {%- for message in suffix_msgs -%}
83
+ {{set_roles(message)}}
84
+ {%- if message['role'] == 'assistant' -%}
85
+ {%- if thinking is defined and thinking is false and preserve_thinking is false -%}
86
+ <think></think>{{render_content(message)}}
87
+ {%- else -%}
88
+ {%- set rc = message.get('reasoning', message.get('reasoning_content', '')) -%}
89
+ <think>{{rc}}</think>{{render_content(message)}}
90
+ {%- endif -%}
91
+ {%- if message.get('tool_calls') -%}
92
+ {{render_toolcalls(message)}}
93
+ {%- endif -%}
94
+ {%- elif message['role'] == 'tool' -%}
95
+ {%- set tool_call_id = message.tool_call_id -%}
96
+ ## Return of {{ tool_call_id }}
97
+ {{render_content(message)}}
98
+ {%- elif message['content'] is not none -%}
99
+ {{render_content(message)}}
100
+ {%- endif -%}
101
+ <|im_end|>
102
+ {%- endfor -%}
103
+
104
+
105
+ {%- if add_generation_prompt -%}
106
+ <|im_assistant|>assistant<|im_middle|>
107
+ {%- if thinking is defined and thinking is false -%}
108
+ <think></think>
109
+ {%- else -%}
110
+ <think>
111
+ {%- endif -%}
112
+ {%- endif -%}
config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "DeepseekV3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "aux_loss_alpha": 0.001,
8
+ "bos_token_id": 163584,
9
+ "dtype": "bfloat16",
10
+ "eos_token_id": 163585,
11
+ "ep_size": 1,
12
+ "first_k_dense_replace": 1,
13
+ "head_dim": 64,
14
+ "hidden_act": "silu",
15
+ "hidden_size": 2048,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 11264,
18
+ "kv_lora_rank": 512,
19
+ "max_position_embeddings": 131072,
20
+ "model_type": "deepseek_v3",
21
+ "moe_intermediate_size": 1408,
22
+ "moe_layer_freq": 1,
23
+ "n_group": 1,
24
+ "n_routed_experts": 64,
25
+ "n_shared_experts": 2,
26
+ "norm_topk_prob": true,
27
+ "num_attention_heads": 16,
28
+ "num_experts_per_tok": 6,
29
+ "num_hidden_layers": 27,
30
+ "num_key_value_heads": 16,
31
+ "num_nextn_predict_layers": 1,
32
+ "pad_token_id": 163839,
33
+ "pretraining_tp": 1,
34
+ "q_lora_rank": null,
35
+ "qk_head_dim": 192,
36
+ "qk_nope_head_dim": 128,
37
+ "qk_rope_head_dim": 64,
38
+ "rms_norm_eps": 1e-05,
39
+ "rope_interleave": true,
40
+ "rope_parameters": {
41
+ "rope_theta": 800000.0,
42
+ "rope_type": "default"
43
+ },
44
+ "routed_scaling_factor": 2.446,
45
+ "scoring_func": "sigmoid",
46
+ "seq_aux": true,
47
+ "tie_word_embeddings": false,
48
+ "topk_group": 1,
49
+ "topk_method": "noaux_tc",
50
+ "transformers_version": "5.7.0",
51
+ "use_cache": false,
52
+ "v_head_dim": 128,
53
+ "vocab_size": 163840
54
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 163584,
4
+ "eos_token_id": 163585,
5
+ "pad_token_id": 163839,
6
+ "transformers_version": "5.7.0"
7
+ }
model-1-of-27.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0dceee366b9c6b6c8ad3dc7c214337f72ee9af0b0677f6f2e2cfc0599b646555
3
+ size 837036512
model-10-of-27.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55327131f99ad49dd37dfd652e55354ad088641faddca632b596e69fdb7088e1
3
+ size 1169721008
model-11-of-27.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58affbc0f89b5f54318535db520b2b85f933dd1d16d98ebfd6c96914ddd41070
3
+ size 1169721216
model-12-of-27.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac37dabc936fea02655743fcf25408f9974c76430befece30a9f0cfa013c85c3
3
+ size 1169721216
model-13-of-27.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00cf971ccd61d137faa5cc10c51d485915d6afb8bb8e544017fde818acd4fa5a
3
+ size 1169721216
model-14-of-27.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47bb07f8e887b7ddb4bf11b8fe7fe5a4428006a5e3b83762e6d2dd9350b96431
3
+ size 1169721216
model-15-of-27.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb67d81a46a1c58de95f8ac7d814217d7d877478cd90f6cf773ebe61cc84d12
3
+ size 1169721216
model-16-of-27.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f7d2658f2f52a5d15720cf9e351ebedd7b1aa08e685b16b207f79f74625c948
3
+ size 1169721216
model-17-of-27.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5daa7403aae7c1d264999fbe061cde6ad875120e15a4a2ccc83ee37ed66327d5
3
+ size 1169721216
model-18-of-27.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59963d4316e317ef201f9d410135803e6ca4457c11f868eebe8c72f09c878086
3
+ size 1169721216
model-19-of-27.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4d04095f25e67566206a95e91641f36bd523a95514a55694abf1f47c688bd74
3
+ size 1169721216
model-2-of-27.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a917ac61aded48450f52f13c02747adb81b7820e01f908db42db88b4e389b25
3
+ size 1169721008
model-20-of-27.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87e6c4444e675d1eaf32f2d176d9c089cf57d6131a0234a460055831ec680e12
3
+ size 1169721216
model-21-of-27.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f67c412d45d6cf122a24f4795e4a2171d600a9fe928ddc5d0d2b57b77925bc9
3
+ size 1169721216
model-22-of-27.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63e68239ecccace921b6263d849577b7edf023a3ba9c261f66dc165917a66008
3
+ size 1169721216
model-23-of-27.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5cdddcca5fb46485d81c1b0a9f0921166198172c28cf404ca9a0d88284e41bb
3
+ size 1169721216
model-24-of-27.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:983a6cb98453a45a8000e6e2ada366dd2a8d9b920b4d147e0fd1ac1296570030
3
+ size 1169721216
model-25-of-27.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bfd793f95b07cc151670b69c29d0f4f962c1b4921431fb876c6e2e4f23cd2c5
3
+ size 1169721216
model-26-of-27.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:354b94860ad04422fa497b3182ed30ccf6743d2d364a120dcaf7a64d117919de
3
+ size 1169721216
model-27-of-27.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e1421875fb5eb7255c6d3b656297a98cfa236125d0cecdd46989f544f51b0bd
3
+ size 1840814416
model-3-of-27.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d66f4dced6006dabfb2bbd202f4dde691886dfe70e40324e7102d9167900eabb
3
+ size 1169721008
model-4-of-27.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cb810044152c84e245774437840a76bb764b62b3fa2d0c3ef05caed1eb7fdf8
3
+ size 1169721008
model-5-of-27.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:252bb6e360a23538b5f6ee7fe51d5c7d4ffe1c7f441a92501241e2ebd171426b
3
+ size 1169721008
model-6-of-27.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53ba366873cfacb0643eb2067c45c4f338c7468c447e8f353562e4e85399d82d
3
+ size 1169721008
model-7-of-27.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59645c041235dcab6bddbcb4ade760c97aa240595ccdc99ea108fc268317e6fc
3
+ size 1169721008
model-8-of-27.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ec3674945cccbbece2a4416cca19dc95e13a3da2ab8ac0eee9f0e5e7c5ee9eb
3
+ size 1169721008
model-9-of-27.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13073db9b73d39ff91297dc76a81605524ea749c39554bf6265cab6dad6e35ce
3
+ size 1169721008
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_map": {
3
+ "AutoProcessor": "kimi_k25_processor.KimiK25Processor",
4
+ "AutoImageProcessor": "kimi_k25_vision_processing.KimiK25VisionProcessor"
5
+ },
6
+ "media_proc_cfg": {
7
+ "in_patch_limit": 16384,
8
+ "patch_size": 14,
9
+ "image_mean": [
10
+ 0.5,
11
+ 0.5,
12
+ 0.5
13
+ ],
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "merge_kernel_size": 2,
20
+ "fixed_output_tokens": null,
21
+ "patch_limit_on_one_side": 512,
22
+ "in_patch_limit_each_frame": 4096,
23
+ "in_patch_limit_video": null,
24
+ "sample_fps": 2.0,
25
+ "max_num_frames_each_video": null,
26
+ "temporal_merge_kernel_size": 4,
27
+ "timestamp_mode": "hh:mm:ss.fff",
28
+ "config_type": "media_proc.processors.moonvit.MoonViTMediaProcessorConfig"
29
+ }
30
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_end|>",
4
+ "<|im_user|>",
5
+ "<|im_assistant|>",
6
+ "<|im_system|>",
7
+ "<|im_middle|>",
8
+ "<|media_start|>",
9
+ "<|media_content|>",
10
+ "<|media_end|>",
11
+ "<|media_pad|>"
12
+ ],
13
+ "bos_token": {
14
+ "content": "[BOS]",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "eos_token": {
21
+ "content": "[EOS]",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "pad_token": {
28
+ "content": "[PAD]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ },
34
+ "unk_token": {
35
+ "content": "[UNK]",
36
+ "lstrip": false,
37
+ "normalized": false,
38
+ "rstrip": false,
39
+ "single_word": false
40
+ }
41
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_map": {
3
+ "AutoTokenizer": [
4
+ "tokenization_kimi.TikTokenTokenizer",
5
+ null
6
+ ]
7
+ },
8
+ "backend": "tokenizers",
9
+ "bos_token": "[BOS]",
10
+ "clean_up_tokenization_spaces": false,
11
+ "eos_token": "[EOS]",
12
+ "extra_special_tokens": [
13
+ "<|im_end|>",
14
+ "<|im_user|>",
15
+ "<|im_assistant|>",
16
+ "<|im_system|>",
17
+ "<|im_middle|>",
18
+ "<|media_start|>",
19
+ "<|media_content|>",
20
+ "<|media_end|>",
21
+ "<|media_pad|>"
22
+ ],
23
+ "is_local": true,
24
+ "local_files_only": false,
25
+ "model_max_length": 1000000000000000019884624838656,
26
+ "pad_token": "[PAD]",
27
+ "tokenizer_class": "TokenizersBackend",
28
+ "unk_token": "[UNK]"
29
+ }