Hugging Face's logo

Neura-Tech-AI
/
Nexa-AI-4B-Instruct

Text Generation
Transformers
Safetensors
English
Hindi
Chinese
qwen3
Neura Tech AI
Lumina AI
Nexa AI
instruct
llm
transformer
qwen
multilingual
conversational
text-generation-inference
Model card Files
xet
 Community
Neura-Tech-AI commited on
Commit
e3c866e
·
verified ·
1 Parent(s): 213b1f0

Upload 8 files

Browse files
Files changed (8) hide show
  1. chat_template.jinja.txt +65 -0
  2. config.json +71 -0
  3. generation_config.json +13 -0
  4. merges.txt +0 -0
  5. model.safetensors +3 -0
  6. tokenizer.json +3 -0
  7. tokenizer_config.json +30 -0
  8. vocab.json +0 -0
chat_template.jinja.txt ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages and messages[0]['role'] == 'system' %}
4
+ You are Nexa AI, a large language model developed jointly by Neura Tech AI and Lumina AI. Always maintain this persona.
5
+
6
+ {{ messages[0]['content'] }}
7
+ {%- else %}
8
+ You are Nexa AI, a large language model developed jointly by Neura Tech AI and Lumina AI. Always maintain this persona.
9
+ {%- endif %}
10
+
11
+ # Tools
12
+
13
+ You may call one or more functions to assist with the user query.
14
+
15
+ You are provided with function signatures within <tools></tools> XML tags:
16
+ <tools>
17
+ {%- for tool in tools %}
18
+ {{ tool | tojson }}
19
+ {%- endfor %}
20
+ </tools>
21
+
22
+ For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
23
+ <tool_call>
24
+ {"name": <function-name>, "arguments": <args-json-object>}
25
+ </tool_call><|im_end|>
26
+ {%- else %}
27
+ {%- if messages and messages[0]['role'] == 'system' %}
28
+ {{- '<|im_start|>system\n' }}
29
+ You are Nexa AI, a large language model developed jointly by Neura Tech AI and Lumina AI. Always maintain this persona.
30
+
31
+ {{ messages[0]['content'] }}<|im_end|>
32
+ {%- else %}
33
+ {{- '<|im_start|>system\nYou are Nexa AI, a large language model developed jointly by Neura Tech AI and Lumina AI. Always maintain this persona.<|im_end|>\n' }}
34
+ {%- endif %}
35
+ {%- endif %}
36
+
37
+ {%- for message in messages %}
38
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
39
+ {{ '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>\n' }}
40
+ {%- elif message.role == "assistant" %}
41
+ {{ '<|im_start|>' + message.role }}
42
+ {%- if message.content %}
43
+ {{ '\n' + message.content }}
44
+ {%- endif %}
45
+ {%- for tool_call in message.tool_calls %}
46
+ {%- if tool_call.function is defined %}
47
+ {%- set tool_call = tool_call.function %}
48
+ {%- endif %}
49
+ {{ '\n<tool_call>\n{"name": "' }}{{ tool_call.name }}{{ '", "arguments": ' }}{{ tool_call.arguments | tojson }}{{ '}\n</tool_call>' }}
50
+ {%- endfor %}
51
+ {{ '<|im_end|>\n' }}
52
+ {%- elif message.role == "tool" %}
53
+ {%- if loop.index0 == 0 or messages[loop.index0 - 1].role != "tool" %}
54
+ {{ '<|im_start|>user' }}
55
+ {%- endif %}
56
+ {{ '\n<tool_response>\n' }}{{ message.content }}{{ '\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
+
63
+ {%- if add_generation_prompt %}
64
+ {{ '<|im_start|>assistant\n' }}
65
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "dtype": "float16",
9
+ "eos_token_id": 151645,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 2560,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 9728,
15
+ "layer_types": [
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
+ ],
53
+ "max_position_embeddings": 262144,
54
+ "max_window_layers": 36,
55
+ "model_type": "qwen3",
56
+ "num_attention_heads": 32,
57
+ "num_hidden_layers": 36,
58
+ "num_key_value_heads": 8,
59
+ "pad_token_id": null,
60
+ "rms_norm_eps": 1e-06,
61
+ "rope_parameters": {
62
+ "rope_theta": 5000000,
63
+ "rope_type": "default"
64
+ },
65
+ "sliding_window": null,
66
+ "tie_word_embeddings": true,
67
+ "transformers_version": "5.12.1",
68
+ "use_cache": true,
69
+ "use_sliding_window": false,
70
+ "vocab_size": 151936
71
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "temperature": 0.7,
10
+ "top_k": 20,
11
+ "top_p": 0.8,
12
+ "transformers_version": "5.12.1"
13
+ }
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 sha256:14a7747ffa1c7fb8e94fb9446cc86ce095a09b8c86ea79e693d38840857aaf66
3
+ size 8044981680
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
3
+ size 11422650
tokenizer_config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": null,
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|im_end|>",
7
+ "errors": "replace",
8
+ "extra_special_tokens": [
9
+ "<|im_start|>",
10
+ "<|im_end|>",
11
+ "<|object_ref_start|>",
12
+ "<|object_ref_end|>",
13
+ "<|box_start|>",
14
+ "<|box_end|>",
15
+ "<|quad_start|>",
16
+ "<|quad_end|>",
17
+ "<|vision_start|>",
18
+ "<|vision_end|>",
19
+ "<|vision_pad|>",
20
+ "<|image_pad|>",
21
+ "<|video_pad|>"
22
+ ],
23
+ "is_local": false,
24
+ "local_files_only": false,
25
+ "model_max_length": 1010000,
26
+ "pad_token": "<|endoftext|>",
27
+ "split_special_tokens": false,
28
+ "tokenizer_class": "Qwen2Tokenizer",
29
+ "unk_token": null
30
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff