DecoderImmortal commited on
Commit
50d850e
·
verified ·
1 Parent(s): d0895fc

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ checkpoint-4928/trainer_state.json filter=lfs diff=lfs merge=lfs -text
37
+ training_logs.jsonl filter=lfs diff=lfs merge=lfs -text
checkpoint-4928/config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "dtype": "bfloat16",
9
+ "eos_token_id": 151645,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 4096,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 12288,
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": 40960,
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
+ "rms_norm_eps": 1e-06,
60
+ "rope_scaling": null,
61
+ "rope_theta": 1000000,
62
+ "sliding_window": null,
63
+ "tie_word_embeddings": false,
64
+ "transformers_version": "4.57.0",
65
+ "use_cache": false,
66
+ "use_sliding_window": false,
67
+ "vocab_size": 151936
68
+ }
checkpoint-4928/mar.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55446cc00dd04bd03ed27ad88dab2c56ed4f7e1da60233fecec2d15259264cbb
3
+ size 1101301456
checkpoint-4928/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f36facedf877d3ac918eb8a4d2a2963b7a6e9701d2ca13d386cea62a654507f5
3
+ size 1513171851
checkpoint-4928/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30e15a4fdb02ed1b686cbc96214f76d89cf9fe0f3c5cb2aa94c7c7e2969b6de7
3
+ size 16389
checkpoint-4928/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa7344a225678a9d0e5eee0d53b85ae9436960d1854bc4a69c6f34dc152cc3e1
3
+ size 16389
checkpoint-4928/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6af1412df6a4e5329ad5b8d4d0789180caac4593aa5d7b7449cd84f5bfbefa3b
3
+ size 16389
checkpoint-4928/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69a282d30a0553943e0e9d84f382af59b4c2bf77a11656ad43fb9acd6d5f4039
3
+ size 16389
checkpoint-4928/rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b8b3445137fb7855f3b36c2d2c3d142cab0d64f9c4c8df6a7f430807458166e
3
+ size 16389
checkpoint-4928/rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ec18859fc2d5c79a1a35780890aacdc06758de62c5d6b9041ee5a206961139e
3
+ size 16389
checkpoint-4928/rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b56e05f8f06d30175658631c4b9591e182834c51d939484ca246627597a462f9
3
+ size 16389
checkpoint-4928/rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:273f4447177519084bdf2cb30264b53cebe05a97d2df85a815f948324716b6a0
3
+ size 16389
checkpoint-4928/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50ed9ad99e4cdb423b845be87a84231837ad251f8a0554f22d1f7026df6dc9f0
3
+ size 1465
checkpoint-4928/trainer_state.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df0c05ca5053ca129fc05589404a52698be952aea9da3e5dbfcdc1a68ae48af6
3
+ size 17233267
config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_model_name_or_path": "/root/paddlejob/workspace/output/attn_medusa/pt_model",
3
+ "conv_kernel_size": 1,
4
+ "extract_layers": [
5
+ -1
6
+ ],
7
+ "medusa_num_heads": 4,
8
+ "medusa_num_layers": 1,
9
+ "small_model_name_or_path": "/root/paddlejob/workspace/output/MAR/tiny_model",
10
+ "transformers_version": "4.57.0"
11
+ }
training_logs.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9636e5df47398ca0695d1cdd3d2ac5f8840f9b23bc83db9f3187f114d67f9dd6
3
+ size 116481173