Hugging Face's logo

waynelm
/
120500

Safetensors
qwen3
Model card Files
xet
 Community
waynelm commited on
Commit
5546dca
·
verified ·
1 Parent(s): abfa31c

Upload 6 files

Browse files
Files changed (6) hide show
  1. chat_template.jinja +4 -0
  2. config.json +65 -0
  3. generation_config.json +9 -0
  4. model.safetensors +3 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +33 -0
chat_template.jinja ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {% for message in messages %}{{'<|im_start|>' + message['role'] + '
2
+ ' + message['content'] + '<|im_end|>' + '
3
+ '}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
4
+ ' }}{% endif %}
config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": null,
8
+ "dtype": "float32",
9
+ "eos_token_id": 5,
10
+ "head_dim": 64,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 576,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 1536,
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
+ ],
47
+ "max_position_embeddings": 4096,
48
+ "max_window_layers": 30,
49
+ "model_type": "qwen3",
50
+ "num_attention_heads": 9,
51
+ "num_hidden_layers": 30,
52
+ "num_key_value_heads": 3,
53
+ "pad_token_id": 64002,
54
+ "rms_norm_eps": 1e-06,
55
+ "rope_parameters": {
56
+ "rope_theta": 100000,
57
+ "rope_type": "default"
58
+ },
59
+ "sliding_window": null,
60
+ "tie_word_embeddings": true,
61
+ "transformers_version": "5.6.0",
62
+ "use_cache": false,
63
+ "use_sliding_window": false,
64
+ "vocab_size": 64000
65
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": [
4
+ 5
5
+ ],
6
+ "pad_token_id": 64002,
7
+ "transformers_version": "5.6.0",
8
+ "use_cache": true
9
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e73ee564ceb43e422dd166b2354d62e197d8b4578774cc3ef4402297f44045ef
3
+ size 572322016
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
24
+ "local_files_only": false,
25
+ "model_max_length": 256000,
26
+ "pad_token": "<endoftext/>",
27
+ "padding_side": "right",
28
+ "sp_model_kwargs": {},
29
+ "split_special_tokens": false,
30
+ "tokenizer_class": "LlamaTokenizer",
31
+ "unk_token": "<unk>",
32
+ "use_default_system_prompt": false
33
+ }