Hugging Face's logo

Ba2han
/
checkpoint-10398

Safetensors
qwen3
Model card Files
xet
 Community
Ba2han commited on
Commit
a710030
·
verified ·
1 Parent(s): e2431d6

Upload folder using huggingface_hub

Browse files
Files changed (10) hide show
  1. config.json +77 -0
  2. generation_config.json +13 -0
  3. model.safetensors +3 -0
  4. optimizer.pt +3 -0
  5. rng_state.pth +3 -0
  6. scheduler.pt +3 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +16 -0
  9. trainer_state.json +0 -0
  10. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 50030,
8
+ "dtype": "bfloat16",
9
+ "eos_token_id": 50031,
10
+ "head_dim": 96,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 1152,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 2880,
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
+ "full_attention",
53
+ "full_attention",
54
+ "full_attention",
55
+ "full_attention"
56
+ ],
57
+ "max_position_embeddings": 8192,
58
+ "max_window_layers": 40,
59
+ "model_name": "test_checkpoint",
60
+ "model_type": "qwen3",
61
+ "num_attention_heads": 8,
62
+ "num_hidden_layers": 40,
63
+ "num_key_value_heads": 8,
64
+ "pad_token_id": 50034,
65
+ "rms_norm_eps": 1e-06,
66
+ "rope_parameters": {
67
+ "rope_theta": 1000000,
68
+ "rope_type": "default"
69
+ },
70
+ "sliding_window": null,
71
+ "tie_word_embeddings": false,
72
+ "transformers_version": "5.3.0",
73
+ "unsloth_version": "2026.3.4",
74
+ "use_cache": false,
75
+ "use_sliding_window": false,
76
+ "vocab_size": 50048
77
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50030,
4
+ "eos_token_id": [
5
+ 50031
6
+ ],
7
+ "max_length": 8192,
8
+ "output_attentions": false,
9
+ "output_hidden_states": false,
10
+ "pad_token_id": 50034,
11
+ "transformers_version": "5.3.0",
12
+ "use_cache": true
13
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cfc17e1663ce2315ea8630d7913fd32447ae530b0dd0f8d2c3977e9b93974e5
3
+ size 1310251320
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1894818bc431480572328a7076ae1d3dd471bc88a2ed15baffe45128d50794f1
3
+ size 1541205579
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:062cad456526df4fc3a7b9dce8f88703df4f14e009508e93261d8306129e78c8
3
+ size 14645
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:650d8359da0db9d4842c3654bcb4b6ef5521dd6094d8286fb2c66bf8f85e678a
3
+ size 1465
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<|begin_of_text|>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "eos_token": "<|end_of_text|>",
6
+ "is_local": true,
7
+ "model_input_names": [
8
+ "input_ids",
9
+ "attention_mask"
10
+ ],
11
+ "model_max_length": 8192,
12
+ "pad_token": "<|finetune_right_pad_id|>",
13
+ "padding_side": "right",
14
+ "tokenizer_class": "PreTrainedTokenizerFast",
15
+ "unk_token": null
16
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3320d4bf190ba439db17aa3ff7484f49828c6d05e4d0b3604815e175cd53a36
3
+ size 5713