Hugging Face's logo

netto87
/
dcubelanguage

Text Generation
Safetensors
GGUF
qwen2
language-identification
knowledge-distillation
dcube
conversational
Model card Files
xet
 Community
netto87 commited on
Commit
eeadd13
·
verified ·
1 Parent(s): 0d8ed43

Upload 13 files

Browse files
Files changed (14) hide show
  1. .gitattributes +1 -0
  2. DCUBE_LANGUAGE_IDENTIFIER.gguf +3 -0
  3. README.md +59 -0
  4. added_tokens.json +24 -0
  5. chat_template.jinja +64 -0
  6. config.json +54 -0
  7. generation_config.json +14 -0
  8. languages.json +25 -0
  9. merges.txt +0 -0
  10. model.safetensors +3 -0
  11. special_tokens_map.json +31 -0
  12. tokenizer.json +3 -0
  13. tokenizer_config.json +211 -0
  14. vocab.json +0 -0
.gitattributes CHANGED
@@ -34,3 +34,4 @@ saved_model/**/* 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
  DCUBE_LANGUAGE_IDENTIFIER.gguf 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
  DCUBE_LANGUAGE_IDENTIFIER.gguf filter=lfs diff=lfs merge=lfs -text
37
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
DCUBE_LANGUAGE_IDENTIFIER.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c99fc2f6e7d53362ec5a4a4b2be55c0ae7fe06bf592261ce7e53b83220d3adf8
3
+ size 531068768
README.md ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: Qwen/Qwen2.5-0.5B-Instruct
4
+ tags:
5
+ - language-identification
6
+ - knowledge-distillation
7
+ - dcube
8
+ - qwen2
9
+ pipeline_tag: text-generation
10
+ ---
11
+
12
+ # DCUBE Language Identifier
13
+
14
+ Fine-tuned **Qwen2.5-0.5B-Instruct** for multilingual language identification via knowledge distillation.
15
+
16
+ ## Usage
17
+
18
+ **Paste any text** — the embedded chat template automatically:
19
+ 1. Applies the DCUBE system prompt
20
+ 2. Wraps your input with `Identify the language:`
21
+
22
+ ### LM Studio
23
+ 1. Download the **GGUF** file (or convert from this repo)
24
+ 2. Load the model — **no manual system prompt needed** if the GGUF includes the chat template
25
+ 3. Paste text directly, e.g. `Обичам да слушам музика вечер`
26
+ 4. Set **Temperature = 0**
27
+
28
+ ### Python (llama-cpp)
29
+ ```bash
30
+ py run_gguf.py "Your text here"
31
+ ```
32
+
33
+ ### Hugging Face Transformers
34
+ ```python
35
+ from transformers import AutoModelForCausalLM, AutoTokenizer
36
+
37
+ tokenizer = AutoTokenizer.from_pretrained("YOUR_REPO_ID", trust_remote_code=True)
38
+ model = AutoModelForCausalLM.from_pretrained("YOUR_REPO_ID", trust_remote_code=True)
39
+
40
+ messages = [{"role": "user", "content": "Le temps est magnifique."}]
41
+ prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
42
+ # Template auto-adds system prompt + "Identify the language:" prefix
43
+ ```
44
+
45
+ ## Supported languages
46
+
47
+ Arabic, Bulgarian, German, Greek, English, Spanish, French, Hindi, Italian, Japanese, Dutch, Polish, Portuguese, Russian, Swahili, Thai, Turkish, Urdu, Vietnamese, Chinese, Malayalam
48
+
49
+ ## System prompt (embedded in chat template)
50
+
51
+ ```
52
+ You are DCUBE Language Identifier, a language identification assistant created by DCUBE Ai (www.dcubeai.com). Given a text, respond with ONLY the language name. Do not include any explanation.
53
+ ```
54
+
55
+ ## Training
56
+
57
+ - Teacher: Qwen3-14B (knowledge distillation)
58
+ - Method: LoRA SFT on papluca/language-identification + Malayalam samples
59
+ - DCUBE Ai · www.dcubeai.com
added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
chat_template.jinja ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {# DCUBE Language Identifier — auto system prompt + "Identify the language:" wrapper #}
2
+ {%- set dcube_system = "You are DCUBE Language Identifier, a language identification assistant created by DCUBE Ai (www.dcubeai.com). Given a text, respond with ONLY the language name. Do not include any explanation." -%}
3
+ {%- if tools %}
4
+ {{- '<|im_start|>system\n' }}
5
+ {%- if messages[0]['role'] == 'system' %}
6
+ {{- messages[0]['content'] }}
7
+ {%- else %}
8
+ {{- dcube_system }}
9
+ {%- endif %}
10
+ {{- "\n\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>" }}
11
+ {%- for tool in tools %}
12
+ {{- "\n" }}
13
+ {{- tool | tojson }}
14
+ {%- endfor %}
15
+ {{- "\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" }}
16
+ {%- else %}
17
+ {%- if messages[0]['role'] == 'system' %}
18
+ {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
19
+ {%- else %}
20
+ {{- '<|im_start|>system\n' + dcube_system + '<|im_end|>\n' }}
21
+ {%- endif %}
22
+ {%- endif %}
23
+ {%- for message in messages %}
24
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
25
+ {%- if message.role == "user" %}
26
+ {%- set user_content = message.content %}
27
+ {%- if not user_content.startswith("Identify the language:") %}
28
+ {%- set user_content = "Identify the language:\n" + user_content %}
29
+ {%- endif %}
30
+ {{- '<|im_start|>user\n' + user_content + '<|im_end|>' + '\n' }}
31
+ {%- else %}
32
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
33
+ {%- endif %}
34
+ {%- elif message.role == "assistant" %}
35
+ {{- '<|im_start|>' + message.role }}
36
+ {%- if message.content %}
37
+ {{- '\n' + message.content }}
38
+ {%- endif %}
39
+ {%- for tool_call in message.tool_calls %}
40
+ {%- if tool_call.function is defined %}
41
+ {%- set tool_call = tool_call.function %}
42
+ {%- endif %}
43
+ {{- '\n<tool_call>\n{"name": "' }}
44
+ {{- tool_call.name }}
45
+ {{- '", "arguments": ' }}
46
+ {{- tool_call.arguments | tojson }}
47
+ {{- '}\n</tool_call>' }}
48
+ {%- endfor %}
49
+ {{- '<|im_end|>\n' }}
50
+ {%- elif message.role == "tool" %}
51
+ {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
52
+ {{- '<|im_start|>user' }}
53
+ {%- endif %}
54
+ {{- '\n<tool_response>\n' }}
55
+ {{- message.content }}
56
+ {{- '\n</tool_response>' }}
57
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
58
+ {{- '<|im_end|>\n' }}
59
+ {%- endif %}
60
+ {%- endif %}
61
+ {%- endfor %}
62
+ {%- if add_generation_prompt %}
63
+ {{- '<|im_start|>assistant\n' }}
64
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "dtype": "float16",
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 896,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 4864,
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
+ ],
39
+ "max_position_embeddings": 32768,
40
+ "max_window_layers": 21,
41
+ "model_type": "qwen2",
42
+ "num_attention_heads": 14,
43
+ "num_hidden_layers": 24,
44
+ "num_key_value_heads": 2,
45
+ "rms_norm_eps": 1e-06,
46
+ "rope_scaling": null,
47
+ "rope_theta": 1000000.0,
48
+ "sliding_window": null,
49
+ "tie_word_embeddings": true,
50
+ "transformers_version": "4.57.1",
51
+ "use_cache": true,
52
+ "use_sliding_window": false,
53
+ "vocab_size": 151936
54
+ }
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.1,
10
+ "temperature": 0.7,
11
+ "top_k": 20,
12
+ "top_p": 0.8,
13
+ "transformers_version": "4.57.1"
14
+ }
languages.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "languages": [
3
+ "Arabic",
4
+ "Bulgarian",
5
+ "German",
6
+ "Greek",
7
+ "English",
8
+ "Spanish",
9
+ "French",
10
+ "Hindi",
11
+ "Italian",
12
+ "Japanese",
13
+ "Dutch",
14
+ "Polish",
15
+ "Portuguese",
16
+ "Russian",
17
+ "Swahili",
18
+ "Thai",
19
+ "Turkish",
20
+ "Urdu",
21
+ "Vietnamese",
22
+ "Chinese",
23
+ "Malayalam"
24
+ ]
25
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d2fca4532f17f2710efd4c43cbc6d0f194a6d68441d6a07b25f9b9bda250d16
3
+ size 988097536
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": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
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:e1bb43ac6226b35aa5fb20bf7f7eeb9c8c63289288dc1ce1ea4c7c69d8079a1d
3
+ size 11421994
tokenizer_config.json ADDED
@@ -0,0 +1,211 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "clean_up_tokenization_spaces": false,
199
+ "eos_token": "<|im_end|>",
200
+ "errors": "replace",
201
+ "extra_special_tokens": {},
202
+ "max_length": 256,
203
+ "model_max_length": 131072,
204
+ "pad_token": "<|endoftext|>",
205
+ "split_special_tokens": false,
206
+ "stride": 0,
207
+ "tokenizer_class": "Qwen2Tokenizer",
208
+ "truncation_side": "right",
209
+ "truncation_strategy": "longest_first",
210
+ "unk_token": null
211
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff