Hugging Face's logo

zuhri025
/
lm_weights_scratch

TensorBoard
Safetensors
qwen3
Model card Files
xet
 Metrics Community
1
zuhri025 commited on
Commit
46f2fbc
·
verified ·
1 Parent(s): 7beee94

ckpt step 10500

Browse files
Files changed (7) hide show
  1. checkpoint-10500/config.json +52 -0
  2. checkpoint-10500/generation_config.json +10 -0
  3. checkpoint-10500/meta.pt +3 -0
  4. checkpoint-10500/model.safetensors +3 -0
  5. checkpoint-10500/optimizer.pt +3 -0
  6. checkpoint-10500/tokenizer.json +0 -0
  7. checkpoint-10500/tokenizer_config.json +100 -0
checkpoint-10500/config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 2,
8
+ "dtype": "float32",
9
+ "eos_token_id": 3,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 512,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 2304,
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
+ ],
34
+ "max_position_embeddings": 2048,
35
+ "max_window_layers": 28,
36
+ "model_type": "qwen3",
37
+ "num_attention_heads": 4,
38
+ "num_hidden_layers": 17,
39
+ "num_key_value_heads": 1,
40
+ "pad_token_id": 0,
41
+ "rms_norm_eps": 1e-06,
42
+ "rope_parameters": {
43
+ "rope_theta": 20000,
44
+ "rope_type": "default"
45
+ },
46
+ "sliding_window": null,
47
+ "tie_word_embeddings": true,
48
+ "transformers_version": "5.0.0",
49
+ "use_cache": true,
50
+ "use_sliding_window": false,
51
+ "vocab_size": 50000
52
+ }
checkpoint-10500/generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "eos_token_id": 3,
5
+ "output_attentions": false,
6
+ "output_hidden_states": false,
7
+ "pad_token_id": 0,
8
+ "transformers_version": "5.0.0",
9
+ "use_cache": true
10
+ }
checkpoint-10500/meta.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7f763ddb0f76c5237c0781e7eb2ec5668bf49cf2bf95373e7fc3764484f6a3d
3
+ size 1243
checkpoint-10500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29d5a3a00f4235d45b03fb7923e3c071abef0546f37d4266a227ae3164009cab
3
+ size 387722712
checkpoint-10500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abb8b85ab74e89b1496baf324eb58fce1d9642b41493572cad5bbaeca241345e
3
+ size 775565131
checkpoint-10500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-10500/tokenizer_config.json ADDED
@@ -0,0 +1,100 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<|bos|>",
4
+ "eos_token": "<|eos|>",
5
+ "extra_special_tokens": [
6
+ "<|im_start|>",
7
+ "<|im_end|>",
8
+ "<|system|>",
9
+ "<|user|>",
10
+ "<|assistant|>",
11
+ "<|speech|>",
12
+ "<|frame_start|>",
13
+ "<|frame_end|>",
14
+ "<|reserved_1|>",
15
+ "<|reserved_2|>",
16
+ "<|reserved_3|>",
17
+ "<|reserved_4|>",
18
+ "<|reserved_5|>",
19
+ "<|reserved_6|>",
20
+ "<|reserved_7|>",
21
+ "<|reserved_8|>",
22
+ "<|reserved_9|>",
23
+ "<|reserved_10|>",
24
+ "<|reserved_11|>",
25
+ "<|reserved_12|>",
26
+ "<|reserved_13|>",
27
+ "<|reserved_14|>",
28
+ "<|reserved_15|>",
29
+ "<|reserved_16|>",
30
+ "<|reserved_17|>",
31
+ "<|reserved_18|>",
32
+ "<|reserved_19|>",
33
+ "<|reserved_20|>",
34
+ "<|reserved_21|>",
35
+ "<|reserved_22|>",
36
+ "<|reserved_23|>",
37
+ "<|reserved_24|>",
38
+ "<|reserved_25|>",
39
+ "<|reserved_26|>",
40
+ "<|reserved_27|>",
41
+ "<|reserved_28|>",
42
+ "<|reserved_29|>",
43
+ "<|reserved_30|>",
44
+ "<|reserved_31|>",
45
+ "<|reserved_32|>",
46
+ "<|reserved_33|>",
47
+ "<|reserved_34|>",
48
+ "<|reserved_35|>",
49
+ "<|reserved_36|>",
50
+ "<|reserved_37|>",
51
+ "<|reserved_38|>",
52
+ "<|reserved_39|>",
53
+ "<|reserved_40|>",
54
+ "<|reserved_41|>",
55
+ "<|reserved_42|>",
56
+ "<|reserved_43|>",
57
+ "<|reserved_44|>",
58
+ "<|reserved_45|>",
59
+ "<|reserved_46|>",
60
+ "<|reserved_47|>",
61
+ "<|reserved_48|>",
62
+ "<|reserved_49|>",
63
+ "<|reserved_50|>",
64
+ "<|reserved_51|>",
65
+ "<|reserved_52|>",
66
+ "<|reserved_53|>",
67
+ "<|reserved_54|>",
68
+ "<|reserved_55|>",
69
+ "<|reserved_56|>",
70
+ "<|reserved_57|>",
71
+ "<|reserved_58|>",
72
+ "<|reserved_59|>",
73
+ "<|reserved_60|>",
74
+ "<|reserved_61|>",
75
+ "<|reserved_62|>",
76
+ "<|reserved_63|>",
77
+ "<|reserved_64|>",
78
+ "<|reserved_65|>",
79
+ "<|reserved_66|>",
80
+ "<|reserved_67|>",
81
+ "<|reserved_68|>",
82
+ "<|reserved_69|>",
83
+ "<|reserved_70|>",
84
+ "<|reserved_71|>",
85
+ "<|reserved_72|>",
86
+ "<|reserved_73|>",
87
+ "<|reserved_74|>",
88
+ "<|reserved_75|>",
89
+ "<|reserved_76|>",
90
+ "<|reserved_77|>",
91
+ "<|reserved_78|>",
92
+ "<|reserved_79|>",
93
+ "<|reserved_80|>"
94
+ ],
95
+ "is_local": true,
96
+ "model_max_length": 1000000000000000019884624838656,
97
+ "pad_token": "<|pad|>",
98
+ "tokenizer_class": "TokenizersBackend",
99
+ "unk_token": "<|unk|>"
100
+ }