Hugging Face's logo

hozifa1
/
Faqih-R1-14B-Islamic-AI

Text Generation
Transformers
Safetensors
English
qwen2
text-generation-inference
unsloth
conversational
Model card Files
xet
 Community
hozifa1 commited on
Commit
ffd3fee
·
verified ·
1 Parent(s): 7660629

(Trained with Unsloth)

Browse files
Files changed (3) hide show
  1. config.json +81 -80
  2. generation_config.json +3 -1
  3. tokenizer_config.json +4 -3
config.json CHANGED
@@ -1,81 +1,82 @@
1
  {
2
- "architectures": [
3
- "Qwen2ForCausalLM"
4
- ],
5
- "attention_dropout": 0.0,
6
- "bos_token_id": 151643,
7
- "dtype": "bfloat16",
8
- "eos_token_id": 151643,
9
- "hidden_act": "silu",
10
- "hidden_size": 5120,
11
- "initializer_range": 0.02,
12
- "intermediate_size": 13824,
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
- ],
63
- "max_position_embeddings": 131072,
64
- "max_window_layers": 48,
65
- "model_type": "qwen2",
66
- "num_attention_heads": 40,
67
- "num_hidden_layers": 48,
68
- "num_key_value_heads": 8,
69
- "pad_token_id": null,
70
- "rms_norm_eps": 1e-05,
71
- "rope_parameters": {
72
- "rope_theta": 1000000.0,
73
- "rope_type": "default"
74
- },
75
- "sliding_window": null,
76
- "tie_word_embeddings": false,
77
- "transformers_version": "5.12.1",
78
- "use_cache": true,
79
- "use_sliding_window": false,
80
- "vocab_size": 152064
81
- }
 
 
1
  {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151646,
7
+ "torch_dtype": "float16",
8
+ "eos_token_id": 151643,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 5120,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 13824,
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
+ ],
63
+ "max_position_embeddings": 131072,
64
+ "max_window_layers": 48,
65
+ "model_type": "qwen2",
66
+ "num_attention_heads": 40,
67
+ "num_hidden_layers": 48,
68
+ "num_key_value_heads": 8,
69
+ "pad_token_id": 151654,
70
+ "rms_norm_eps": 1e-05,
71
+ "rope_parameters": {
72
+ "rope_theta": 1000000.0,
73
+ "rope_type": "default"
74
+ },
75
+ "sliding_window": null,
76
+ "tie_word_embeddings": false,
77
+ "unsloth_fixed": true,
78
+ "unsloth_version": "2026.8.19",
79
+ "use_cache": true,
80
+ "use_sliding_window": false,
81
+ "vocab_size": 152064
82
+ }
generation_config.json CHANGED
@@ -3,7 +3,9 @@
3
  "bos_token_id": 151646,
4
  "do_sample": true,
5
  "eos_token_id": 151643,
 
 
6
  "temperature": 0.6,
7
  "top_p": 0.95,
8
- "transformers_version": "5.12.1"
9
  }
 
3
  "bos_token_id": 151646,
4
  "do_sample": true,
5
  "eos_token_id": 151643,
6
+ "max_length": 131072,
7
+ "pad_token_id": 151654,
8
  "temperature": 0.6,
9
  "top_p": 0.95,
10
+ "transformers_version": "5.5.0"
11
  }
tokenizer_config.json CHANGED
@@ -9,7 +9,7 @@
9
  "legacy": false,
10
  "model_max_length": 131072,
11
  "pad_token": "<|vision_pad|>",
12
- "padding_side": "right",
13
  "sp_model_kwargs": {},
14
  "tokenizer_class": "TokenizersBackend",
15
  "unk_token": null,
@@ -191,5 +191,6 @@
191
  "normalized": false,
192
  "special": false
193
  }
194
- }
195
- }
 
 
9
  "legacy": false,
10
  "model_max_length": 131072,
11
  "pad_token": "<|vision_pad|>",
12
+ "padding_side": "left",
13
  "sp_model_kwargs": {},
14
  "tokenizer_class": "TokenizersBackend",
15
  "unk_token": null,
 
191
  "normalized": false,
192
  "special": false
193
  }
194
+ },
195
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\\n'}}{% endif %}"
196
+ }