LH-Tech-AI commited on
Commit
84d47eb
·
verified ·
1 Parent(s): 3dc94a9

Upload model files

Browse files
chat_template.jinja ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {% for m in messages %}<|im_start|>{{ m['role'] }}
2
+ {{ m['content'] }}<|im_end|>
3
+ {% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
4
+ {% endif %}
config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "dtype": "float32",
9
+ "eos_token_id": 0,
10
+ "head_dim": 64,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 640,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 1600,
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
+ ],
29
+ "max_position_embeddings": 512,
30
+ "max_window_layers": 28,
31
+ "model_type": "qwen3",
32
+ "num_attention_heads": 10,
33
+ "num_hidden_layers": 12,
34
+ "num_key_value_heads": 10,
35
+ "pad_token_id": 0,
36
+ "rms_norm_eps": 1e-06,
37
+ "rope_parameters": {
38
+ "rope_theta": 10000.0,
39
+ "rope_type": "default"
40
+ },
41
+ "sliding_window": null,
42
+ "tie_word_embeddings": true,
43
+ "transformers_version": "5.22.1",
44
+ "use_cache": true,
45
+ "use_sliding_window": false,
46
+ "vocab_size": 16384
47
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "output_attentions": false,
6
+ "output_hidden_states": false,
7
+ "pad_token_id": 0,
8
+ "transformers_version": "5.22.1",
9
+ "use_cache": false
10
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ec50901e41aaee94e308e92968fb06b49ccc2db9834f3e8f968003b7e5e0463
3
+ size 268127112
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "clean_up_tokenization_spaces": false,
4
+ "eos_token": "<|endoftext|>",
5
+ "extra_special_tokens": [
6
+ "<|im_start|>",
7
+ "<|im_end|>",
8
+ "<|vision_start|>",
9
+ "<|vision_end|>",
10
+ "<|image_pad|>",
11
+ "<|fim_prefix|>",
12
+ "<|fim_middle|>",
13
+ "<|fim_suffix|>",
14
+ "<|fim_pad|>",
15
+ "<|repo_name|>",
16
+ "<|file_sep|>",
17
+ "<|reserved_0|>",
18
+ "<|reserved_1|>",
19
+ "<|reserved_2|>",
20
+ "<|reserved_3|>"
21
+ ],
22
+ "is_local": true,
23
+ "local_files_only": false,
24
+ "model_max_length": 512,
25
+ "pad_token": "<|endoftext|>",
26
+ "tokenizer_class": "TokenizersBackend"
27
+ }