Hugging Face's logo

promotion
/
nbpo-checkpoints

Safetensors
Model card Files
xet
 Community
promotion commited on
Commit
ef5aa68
·
verified ·
1 Parent(s): f4a0e7e

hs2gemma/gnb/nbs round 1

Browse files
Files changed (25) hide show
  1. .gitattributes +19 -0
  2. hs2gemma/gnb/nbs/config.json +82 -0
  3. hs2gemma/gnb/nbs/config.yaml +38 -0
  4. hs2gemma/gnb/nbs/generation_config.json +10 -0
  5. hs2gemma/gnb/nbs/model-00001-of-00018.safetensors +3 -0
  6. hs2gemma/gnb/nbs/model-00002-of-00018.safetensors +3 -0
  7. hs2gemma/gnb/nbs/model-00003-of-00018.safetensors +3 -0
  8. hs2gemma/gnb/nbs/model-00004-of-00018.safetensors +3 -0
  9. hs2gemma/gnb/nbs/model-00005-of-00018.safetensors +3 -0
  10. hs2gemma/gnb/nbs/model-00006-of-00018.safetensors +3 -0
  11. hs2gemma/gnb/nbs/model-00007-of-00018.safetensors +3 -0
  12. hs2gemma/gnb/nbs/model-00008-of-00018.safetensors +3 -0
  13. hs2gemma/gnb/nbs/model-00009-of-00018.safetensors +3 -0
  14. hs2gemma/gnb/nbs/model-00010-of-00018.safetensors +3 -0
  15. hs2gemma/gnb/nbs/model-00011-of-00018.safetensors +3 -0
  16. hs2gemma/gnb/nbs/model-00012-of-00018.safetensors +3 -0
  17. hs2gemma/gnb/nbs/model-00013-of-00018.safetensors +3 -0
  18. hs2gemma/gnb/nbs/model-00014-of-00018.safetensors +3 -0
  19. hs2gemma/gnb/nbs/model-00015-of-00018.safetensors +3 -0
  20. hs2gemma/gnb/nbs/model-00016-of-00018.safetensors +3 -0
  21. hs2gemma/gnb/nbs/model-00017-of-00018.safetensors +3 -0
  22. hs2gemma/gnb/nbs/model-00018-of-00018.safetensors +3 -0
  23. hs2gemma/gnb/nbs/model.safetensors.index.json +472 -0
  24. hs2gemma/gnb/nbs/tokenizer.json +3 -0
  25. hs2gemma/gnb/nbs/tokenizer_config.json +20 -0
.gitattributes CHANGED
@@ -17,3 +17,22 @@ hs2gemma/gks/ks/model-00016-of-00018.safetensors filter=lfs diff=lfs merge=lfs -
17
  hs2gemma/gks/ks/model-00017-of-00018.safetensors filter=lfs diff=lfs merge=lfs -text
18
  hs2gemma/gks/ks/model-00018-of-00018.safetensors filter=lfs diff=lfs merge=lfs -text
19
  hs2gemma/gks/ks/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
17
  hs2gemma/gks/ks/model-00017-of-00018.safetensors filter=lfs diff=lfs merge=lfs -text
18
  hs2gemma/gks/ks/model-00018-of-00018.safetensors filter=lfs diff=lfs merge=lfs -text
19
  hs2gemma/gks/ks/tokenizer.json filter=lfs diff=lfs merge=lfs -text
20
+ hs2gemma/gnb/nbs/model-00001-of-00018.safetensors filter=lfs diff=lfs merge=lfs -text
21
+ hs2gemma/gnb/nbs/model-00002-of-00018.safetensors filter=lfs diff=lfs merge=lfs -text
22
+ hs2gemma/gnb/nbs/model-00003-of-00018.safetensors filter=lfs diff=lfs merge=lfs -text
23
+ hs2gemma/gnb/nbs/model-00004-of-00018.safetensors filter=lfs diff=lfs merge=lfs -text
24
+ hs2gemma/gnb/nbs/model-00005-of-00018.safetensors filter=lfs diff=lfs merge=lfs -text
25
+ hs2gemma/gnb/nbs/model-00006-of-00018.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ hs2gemma/gnb/nbs/model-00007-of-00018.safetensors filter=lfs diff=lfs merge=lfs -text
27
+ hs2gemma/gnb/nbs/model-00008-of-00018.safetensors filter=lfs diff=lfs merge=lfs -text
28
+ hs2gemma/gnb/nbs/model-00009-of-00018.safetensors filter=lfs diff=lfs merge=lfs -text
29
+ hs2gemma/gnb/nbs/model-00010-of-00018.safetensors filter=lfs diff=lfs merge=lfs -text
30
+ hs2gemma/gnb/nbs/model-00011-of-00018.safetensors filter=lfs diff=lfs merge=lfs -text
31
+ hs2gemma/gnb/nbs/model-00012-of-00018.safetensors filter=lfs diff=lfs merge=lfs -text
32
+ hs2gemma/gnb/nbs/model-00013-of-00018.safetensors filter=lfs diff=lfs merge=lfs -text
33
+ hs2gemma/gnb/nbs/model-00014-of-00018.safetensors filter=lfs diff=lfs merge=lfs -text
34
+ hs2gemma/gnb/nbs/model-00015-of-00018.safetensors filter=lfs diff=lfs merge=lfs -text
35
+ hs2gemma/gnb/nbs/model-00016-of-00018.safetensors filter=lfs diff=lfs merge=lfs -text
36
+ hs2gemma/gnb/nbs/model-00017-of-00018.safetensors filter=lfs diff=lfs merge=lfs -text
37
+ hs2gemma/gnb/nbs/model-00018-of-00018.safetensors filter=lfs diff=lfs merge=lfs -text
38
+ hs2gemma/gnb/nbs/tokenizer.json filter=lfs diff=lfs merge=lfs -text
hs2gemma/gnb/nbs/config.json ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Gemma2ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "attn_logit_softcapping": 50.0,
8
+ "bos_token_id": 2,
9
+ "cache_implementation": "hybrid",
10
+ "dtype": "bfloat16",
11
+ "eos_token_id": 1,
12
+ "final_logit_softcapping": 30.0,
13
+ "head_dim": 256,
14
+ "hidden_act": "gelu_pytorch_tanh",
15
+ "hidden_activation": "gelu_pytorch_tanh",
16
+ "hidden_size": 3584,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 14336,
19
+ "layer_types": [
20
+ "sliding_attention",
21
+ "full_attention",
22
+ "sliding_attention",
23
+ "full_attention",
24
+ "sliding_attention",
25
+ "full_attention",
26
+ "sliding_attention",
27
+ "full_attention",
28
+ "sliding_attention",
29
+ "full_attention",
30
+ "sliding_attention",
31
+ "full_attention",
32
+ "sliding_attention",
33
+ "full_attention",
34
+ "sliding_attention",
35
+ "full_attention",
36
+ "sliding_attention",
37
+ "full_attention",
38
+ "sliding_attention",
39
+ "full_attention",
40
+ "sliding_attention",
41
+ "full_attention",
42
+ "sliding_attention",
43
+ "full_attention",
44
+ "sliding_attention",
45
+ "full_attention",
46
+ "sliding_attention",
47
+ "full_attention",
48
+ "sliding_attention",
49
+ "full_attention",
50
+ "sliding_attention",
51
+ "full_attention",
52
+ "sliding_attention",
53
+ "full_attention",
54
+ "sliding_attention",
55
+ "full_attention",
56
+ "sliding_attention",
57
+ "full_attention",
58
+ "sliding_attention",
59
+ "full_attention",
60
+ "sliding_attention",
61
+ "full_attention"
62
+ ],
63
+ "max_position_embeddings": 8192,
64
+ "model_type": "gemma2",
65
+ "num_attention_heads": 16,
66
+ "num_hidden_layers": 42,
67
+ "num_key_value_heads": 8,
68
+ "pad_token_id": 0,
69
+ "query_pre_attn_scalar": 256,
70
+ "rms_norm_eps": 1e-06,
71
+ "rope_parameters": {
72
+ "rope_theta": 10000.0,
73
+ "rope_type": "default"
74
+ },
75
+ "sliding_window": 4096,
76
+ "sliding_window_size": 4096,
77
+ "tie_word_embeddings": true,
78
+ "transformers_version": "5.13.0",
79
+ "use_bidirectional_attention": null,
80
+ "use_cache": true,
81
+ "vocab_size": 256000
82
+ }
hs2gemma/gnb/nbs/config.yaml ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ model_name_or_path: /NHNHOME/AIPR/sjkim/policy_bases/models--google--gemma-2-9b-it/snapshots/11c9b309abf73637e4b6f9a3fa1e92e615547819/
2
+ attn_implementation: sdpa
3
+ dataset_mixer:
4
+ /NHNHOME/AIPR/sjkim/gtpref/hs2gemma/exp/rmpool_mbgnb1/pre: 1.0
5
+ dataset_splits:
6
+ - train
7
+ - test
8
+ bf16: true
9
+ loss_type: ronpo
10
+ ronpo_alpha: 1.0
11
+ ronpo_tau: 0.05
12
+ ronpo_target_column: bpo_target_nbs
13
+ max_history_t: 1
14
+ history_weights: [1.0]
15
+ beta: 10.0
16
+ learning_rate: 5.0e-7
17
+ lr_scheduler_type: cosine
18
+ warmup_ratio: 0.1
19
+ optim: adamw_torch
20
+ seed: 42
21
+ gradient_accumulation_steps: 8
22
+ gradient_checkpointing: true
23
+ gradient_checkpointing_kwargs:
24
+ use_reentrant: false
25
+ num_train_epochs: 1
26
+ max_steps: 900
27
+ per_device_train_batch_size: 2
28
+ per_device_eval_batch_size: 2
29
+ max_length: 2048
30
+ max_prompt_length: 1024
31
+ do_eval: false
32
+ save_strategy: 'no'
33
+ save_only_model: true
34
+ save_safetensors: true
35
+ report_to:
36
+ - wandb
37
+ output_dir: /NHNHOME/AIPR/sjkim/gtpref/hs2gemma/exp/rmpool_mbgnb1/train/nbs
38
+ run_name: gt-hs2gemma-exp/rmpool_mbgnb1-nbs
hs2gemma/gnb/nbs/generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "cache_implementation": "hybrid",
5
+ "eos_token_id": [
6
+ 1
7
+ ],
8
+ "pad_token_id": 0,
9
+ "transformers_version": "5.13.0"
10
+ }
hs2gemma/gnb/nbs/model-00001-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a5890136d79e2c59ad9c91181fd86fd9a0b6f44382635b7e1636a2ea87ea0e1
3
+ size 1835008144
hs2gemma/gnb/nbs/model-00002-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e3320d4281e356a1d29d15a312afba5d3aaaae8c3dc4845389818e802bf3b07
3
+ size 998311752
hs2gemma/gnb/nbs/model-00003-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8766c56d13b63362198e24bc4657942f92948b1e0a70eb1758abcd2d625f8198
3
+ size 983653904
hs2gemma/gnb/nbs/model-00004-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1b328f59c21f81bd109c107c8d81e49f685104822c5c6b3e75b0dab7f50ed03
3
+ size 998304480
hs2gemma/gnb/nbs/model-00005-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4720a108b452f5b6a2ca525d4458a1ca78e5af5817d505ef2775fc41796e4c2
3
+ size 983653896
hs2gemma/gnb/nbs/model-00006-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bda937ce4f1e3bf946d0c8840f44f4f5c15a5fd6c5569205deb61542aa1866c
3
+ size 998304504
hs2gemma/gnb/nbs/model-00007-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a58eee9f926b6613d7975f853c3842f434e50a70caba14c4a304b74e1e6e4841
3
+ size 983653936
hs2gemma/gnb/nbs/model-00008-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf552817d5861120878d2c7d5a16128bc8d37e02cab420d01fb5b882325fc02d
3
+ size 998304504
hs2gemma/gnb/nbs/model-00009-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8666dbaa587057f84cbd18c483b34cf316d2ef1663fdb2f4d3cb984270c4202
3
+ size 983653936
hs2gemma/gnb/nbs/model-00010-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18dbbb9d810e253e102a6ca4d1dbf6eb3a32e3ea56848928bcd0f5c9a9ee590e
3
+ size 998304504
hs2gemma/gnb/nbs/model-00011-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0d3cbabb886865f14aa0055beb68b45c239c49ebffcccf27d563c3b74656446
3
+ size 983653936
hs2gemma/gnb/nbs/model-00012-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:292cbfa89854b27359f5c9e1d22f466e006a4136567167f5935b2ae10d02e12f
3
+ size 998304504
hs2gemma/gnb/nbs/model-00013-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51addfb9601020b4f62deeae6b107bdf306fcdea99b585ac7b54d6571febb5bd
3
+ size 983653936
hs2gemma/gnb/nbs/model-00014-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0683f0411af58ac81e6c556f79600c4fa5ae053c1b1c0af839d7af275acb5023
3
+ size 998304504
hs2gemma/gnb/nbs/model-00015-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24809d46e8697f015caff90219d5bab9ff59892ccaf35d7ba78498d02c2fadbf
3
+ size 983653936
hs2gemma/gnb/nbs/model-00016-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af151295c6372691fa6e78a08c639c08a3d950abd012722d2a1338c292be9899
3
+ size 998304504
hs2gemma/gnb/nbs/model-00017-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2c34f0a49ee910733b535466ae6704d5928bdd58783ab47d9ef5c81ebbd5d58
3
+ size 983653936
hs2gemma/gnb/nbs/model-00018-of-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d257cc4673bcd73e6322e4822feb65f33f9174bc9afe627e4f866b37e5f0250a
3
+ size 792783360
hs2gemma/gnb/nbs/model.safetensors.index.json ADDED
@@ -0,0 +1,472 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 9241705984,
4
+ "total_size": 18483411968
5
+ },
6
+ "weight_map": {
7
+ "model.embed_tokens.weight": "model-00001-of-00018.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00002-of-00018.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00002-of-00018.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00018.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00002-of-00018.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00018.safetensors",
13
+ "model.layers.0.post_feedforward_layernorm.weight": "model-00002-of-00018.safetensors",
14
+ "model.layers.0.pre_feedforward_layernorm.weight": "model-00002-of-00018.safetensors",
15
+ "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00018.safetensors",
16
+ "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00018.safetensors",
17
+ "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00018.safetensors",
18
+ "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00018.safetensors",
19
+ "model.layers.1.input_layernorm.weight": "model-00002-of-00018.safetensors",
20
+ "model.layers.1.mlp.down_proj.weight": "model-00002-of-00018.safetensors",
21
+ "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00018.safetensors",
22
+ "model.layers.1.mlp.up_proj.weight": "model-00002-of-00018.safetensors",
23
+ "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00018.safetensors",
24
+ "model.layers.1.post_feedforward_layernorm.weight": "model-00002-of-00018.safetensors",
25
+ "model.layers.1.pre_feedforward_layernorm.weight": "model-00002-of-00018.safetensors",
26
+ "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00018.safetensors",
27
+ "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00018.safetensors",
28
+ "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00018.safetensors",
29
+ "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00018.safetensors",
30
+ "model.layers.10.input_layernorm.weight": "model-00005-of-00018.safetensors",
31
+ "model.layers.10.mlp.down_proj.weight": "model-00006-of-00018.safetensors",
32
+ "model.layers.10.mlp.gate_proj.weight": "model-00006-of-00018.safetensors",
33
+ "model.layers.10.mlp.up_proj.weight": "model-00006-of-00018.safetensors",
34
+ "model.layers.10.post_attention_layernorm.weight": "model-00006-of-00018.safetensors",
35
+ "model.layers.10.post_feedforward_layernorm.weight": "model-00006-of-00018.safetensors",
36
+ "model.layers.10.pre_feedforward_layernorm.weight": "model-00006-of-00018.safetensors",
37
+ "model.layers.10.self_attn.k_proj.weight": "model-00006-of-00018.safetensors",
38
+ "model.layers.10.self_attn.o_proj.weight": "model-00006-of-00018.safetensors",
39
+ "model.layers.10.self_attn.q_proj.weight": "model-00006-of-00018.safetensors",
40
+ "model.layers.10.self_attn.v_proj.weight": "model-00006-of-00018.safetensors",
41
+ "model.layers.11.input_layernorm.weight": "model-00006-of-00018.safetensors",
42
+ "model.layers.11.mlp.down_proj.weight": "model-00006-of-00018.safetensors",
43
+ "model.layers.11.mlp.gate_proj.weight": "model-00006-of-00018.safetensors",
44
+ "model.layers.11.mlp.up_proj.weight": "model-00006-of-00018.safetensors",
45
+ "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00018.safetensors",
46
+ "model.layers.11.post_feedforward_layernorm.weight": "model-00006-of-00018.safetensors",
47
+ "model.layers.11.pre_feedforward_layernorm.weight": "model-00006-of-00018.safetensors",
48
+ "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00018.safetensors",
49
+ "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00018.safetensors",
50
+ "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00018.safetensors",
51
+ "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00018.safetensors",
52
+ "model.layers.12.input_layernorm.weight": "model-00006-of-00018.safetensors",
53
+ "model.layers.12.mlp.down_proj.weight": "model-00006-of-00018.safetensors",
54
+ "model.layers.12.mlp.gate_proj.weight": "model-00006-of-00018.safetensors",
55
+ "model.layers.12.mlp.up_proj.weight": "model-00007-of-00018.safetensors",
56
+ "model.layers.12.post_attention_layernorm.weight": "model-00007-of-00018.safetensors",
57
+ "model.layers.12.post_feedforward_layernorm.weight": "model-00007-of-00018.safetensors",
58
+ "model.layers.12.pre_feedforward_layernorm.weight": "model-00007-of-00018.safetensors",
59
+ "model.layers.12.self_attn.k_proj.weight": "model-00007-of-00018.safetensors",
60
+ "model.layers.12.self_attn.o_proj.weight": "model-00007-of-00018.safetensors",
61
+ "model.layers.12.self_attn.q_proj.weight": "model-00007-of-00018.safetensors",
62
+ "model.layers.12.self_attn.v_proj.weight": "model-00007-of-00018.safetensors",
63
+ "model.layers.13.input_layernorm.weight": "model-00007-of-00018.safetensors",
64
+ "model.layers.13.mlp.down_proj.weight": "model-00007-of-00018.safetensors",
65
+ "model.layers.13.mlp.gate_proj.weight": "model-00007-of-00018.safetensors",
66
+ "model.layers.13.mlp.up_proj.weight": "model-00007-of-00018.safetensors",
67
+ "model.layers.13.post_attention_layernorm.weight": "model-00007-of-00018.safetensors",
68
+ "model.layers.13.post_feedforward_layernorm.weight": "model-00007-of-00018.safetensors",
69
+ "model.layers.13.pre_feedforward_layernorm.weight": "model-00007-of-00018.safetensors",
70
+ "model.layers.13.self_attn.k_proj.weight": "model-00007-of-00018.safetensors",
71
+ "model.layers.13.self_attn.o_proj.weight": "model-00007-of-00018.safetensors",
72
+ "model.layers.13.self_attn.q_proj.weight": "model-00007-of-00018.safetensors",
73
+ "model.layers.13.self_attn.v_proj.weight": "model-00007-of-00018.safetensors",
74
+ "model.layers.14.input_layernorm.weight": "model-00007-of-00018.safetensors",
75
+ "model.layers.14.mlp.down_proj.weight": "model-00007-of-00018.safetensors",
76
+ "model.layers.14.mlp.gate_proj.weight": "model-00007-of-00018.safetensors",
77
+ "model.layers.14.mlp.up_proj.weight": "model-00007-of-00018.safetensors",
78
+ "model.layers.14.post_attention_layernorm.weight": "model-00007-of-00018.safetensors",
79
+ "model.layers.14.post_feedforward_layernorm.weight": "model-00007-of-00018.safetensors",
80
+ "model.layers.14.pre_feedforward_layernorm.weight": "model-00007-of-00018.safetensors",
81
+ "model.layers.14.self_attn.k_proj.weight": "model-00007-of-00018.safetensors",
82
+ "model.layers.14.self_attn.o_proj.weight": "model-00007-of-00018.safetensors",
83
+ "model.layers.14.self_attn.q_proj.weight": "model-00007-of-00018.safetensors",
84
+ "model.layers.14.self_attn.v_proj.weight": "model-00007-of-00018.safetensors",
85
+ "model.layers.15.input_layernorm.weight": "model-00007-of-00018.safetensors",
86
+ "model.layers.15.mlp.down_proj.weight": "model-00008-of-00018.safetensors",
87
+ "model.layers.15.mlp.gate_proj.weight": "model-00008-of-00018.safetensors",
88
+ "model.layers.15.mlp.up_proj.weight": "model-00008-of-00018.safetensors",
89
+ "model.layers.15.post_attention_layernorm.weight": "model-00008-of-00018.safetensors",
90
+ "model.layers.15.post_feedforward_layernorm.weight": "model-00008-of-00018.safetensors",
91
+ "model.layers.15.pre_feedforward_layernorm.weight": "model-00008-of-00018.safetensors",
92
+ "model.layers.15.self_attn.k_proj.weight": "model-00008-of-00018.safetensors",
93
+ "model.layers.15.self_attn.o_proj.weight": "model-00008-of-00018.safetensors",
94
+ "model.layers.15.self_attn.q_proj.weight": "model-00008-of-00018.safetensors",
95
+ "model.layers.15.self_attn.v_proj.weight": "model-00008-of-00018.safetensors",
96
+ "model.layers.16.input_layernorm.weight": "model-00008-of-00018.safetensors",
97
+ "model.layers.16.mlp.down_proj.weight": "model-00008-of-00018.safetensors",
98
+ "model.layers.16.mlp.gate_proj.weight": "model-00008-of-00018.safetensors",
99
+ "model.layers.16.mlp.up_proj.weight": "model-00008-of-00018.safetensors",
100
+ "model.layers.16.post_attention_layernorm.weight": "model-00008-of-00018.safetensors",
101
+ "model.layers.16.post_feedforward_layernorm.weight": "model-00008-of-00018.safetensors",
102
+ "model.layers.16.pre_feedforward_layernorm.weight": "model-00008-of-00018.safetensors",
103
+ "model.layers.16.self_attn.k_proj.weight": "model-00008-of-00018.safetensors",
104
+ "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00018.safetensors",
105
+ "model.layers.16.self_attn.q_proj.weight": "model-00008-of-00018.safetensors",
106
+ "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00018.safetensors",
107
+ "model.layers.17.input_layernorm.weight": "model-00008-of-00018.safetensors",
108
+ "model.layers.17.mlp.down_proj.weight": "model-00008-of-00018.safetensors",
109
+ "model.layers.17.mlp.gate_proj.weight": "model-00008-of-00018.safetensors",
110
+ "model.layers.17.mlp.up_proj.weight": "model-00009-of-00018.safetensors",
111
+ "model.layers.17.post_attention_layernorm.weight": "model-00009-of-00018.safetensors",
112
+ "model.layers.17.post_feedforward_layernorm.weight": "model-00009-of-00018.safetensors",
113
+ "model.layers.17.pre_feedforward_layernorm.weight": "model-00009-of-00018.safetensors",
114
+ "model.layers.17.self_attn.k_proj.weight": "model-00009-of-00018.safetensors",
115
+ "model.layers.17.self_attn.o_proj.weight": "model-00009-of-00018.safetensors",
116
+ "model.layers.17.self_attn.q_proj.weight": "model-00009-of-00018.safetensors",
117
+ "model.layers.17.self_attn.v_proj.weight": "model-00009-of-00018.safetensors",
118
+ "model.layers.18.input_layernorm.weight": "model-00009-of-00018.safetensors",
119
+ "model.layers.18.mlp.down_proj.weight": "model-00009-of-00018.safetensors",
120
+ "model.layers.18.mlp.gate_proj.weight": "model-00009-of-00018.safetensors",
121
+ "model.layers.18.mlp.up_proj.weight": "model-00009-of-00018.safetensors",
122
+ "model.layers.18.post_attention_layernorm.weight": "model-00009-of-00018.safetensors",
123
+ "model.layers.18.post_feedforward_layernorm.weight": "model-00009-of-00018.safetensors",
124
+ "model.layers.18.pre_feedforward_layernorm.weight": "model-00009-of-00018.safetensors",
125
+ "model.layers.18.self_attn.k_proj.weight": "model-00009-of-00018.safetensors",
126
+ "model.layers.18.self_attn.o_proj.weight": "model-00009-of-00018.safetensors",
127
+ "model.layers.18.self_attn.q_proj.weight": "model-00009-of-00018.safetensors",
128
+ "model.layers.18.self_attn.v_proj.weight": "model-00009-of-00018.safetensors",
129
+ "model.layers.19.input_layernorm.weight": "model-00009-of-00018.safetensors",
130
+ "model.layers.19.mlp.down_proj.weight": "model-00009-of-00018.safetensors",
131
+ "model.layers.19.mlp.gate_proj.weight": "model-00009-of-00018.safetensors",
132
+ "model.layers.19.mlp.up_proj.weight": "model-00009-of-00018.safetensors",
133
+ "model.layers.19.post_attention_layernorm.weight": "model-00009-of-00018.safetensors",
134
+ "model.layers.19.post_feedforward_layernorm.weight": "model-00009-of-00018.safetensors",
135
+ "model.layers.19.pre_feedforward_layernorm.weight": "model-00009-of-00018.safetensors",
136
+ "model.layers.19.self_attn.k_proj.weight": "model-00009-of-00018.safetensors",
137
+ "model.layers.19.self_attn.o_proj.weight": "model-00009-of-00018.safetensors",
138
+ "model.layers.19.self_attn.q_proj.weight": "model-00009-of-00018.safetensors",
139
+ "model.layers.19.self_attn.v_proj.weight": "model-00009-of-00018.safetensors",
140
+ "model.layers.2.input_layernorm.weight": "model-00002-of-00018.safetensors",
141
+ "model.layers.2.mlp.down_proj.weight": "model-00002-of-00018.safetensors",
142
+ "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00018.safetensors",
143
+ "model.layers.2.mlp.up_proj.weight": "model-00003-of-00018.safetensors",
144
+ "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00018.safetensors",
145
+ "model.layers.2.post_feedforward_layernorm.weight": "model-00003-of-00018.safetensors",
146
+ "model.layers.2.pre_feedforward_layernorm.weight": "model-00003-of-00018.safetensors",
147
+ "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00018.safetensors",
148
+ "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00018.safetensors",
149
+ "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00018.safetensors",
150
+ "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00018.safetensors",
151
+ "model.layers.20.input_layernorm.weight": "model-00009-of-00018.safetensors",
152
+ "model.layers.20.mlp.down_proj.weight": "model-00010-of-00018.safetensors",
153
+ "model.layers.20.mlp.gate_proj.weight": "model-00010-of-00018.safetensors",
154
+ "model.layers.20.mlp.up_proj.weight": "model-00010-of-00018.safetensors",
155
+ "model.layers.20.post_attention_layernorm.weight": "model-00010-of-00018.safetensors",
156
+ "model.layers.20.post_feedforward_layernorm.weight": "model-00010-of-00018.safetensors",
157
+ "model.layers.20.pre_feedforward_layernorm.weight": "model-00010-of-00018.safetensors",
158
+ "model.layers.20.self_attn.k_proj.weight": "model-00010-of-00018.safetensors",
159
+ "model.layers.20.self_attn.o_proj.weight": "model-00010-of-00018.safetensors",
160
+ "model.layers.20.self_attn.q_proj.weight": "model-00010-of-00018.safetensors",
161
+ "model.layers.20.self_attn.v_proj.weight": "model-00010-of-00018.safetensors",
162
+ "model.layers.21.input_layernorm.weight": "model-00010-of-00018.safetensors",
163
+ "model.layers.21.mlp.down_proj.weight": "model-00010-of-00018.safetensors",
164
+ "model.layers.21.mlp.gate_proj.weight": "model-00010-of-00018.safetensors",
165
+ "model.layers.21.mlp.up_proj.weight": "model-00010-of-00018.safetensors",
166
+ "model.layers.21.post_attention_layernorm.weight": "model-00010-of-00018.safetensors",
167
+ "model.layers.21.post_feedforward_layernorm.weight": "model-00010-of-00018.safetensors",
168
+ "model.layers.21.pre_feedforward_layernorm.weight": "model-00010-of-00018.safetensors",
169
+ "model.layers.21.self_attn.k_proj.weight": "model-00010-of-00018.safetensors",
170
+ "model.layers.21.self_attn.o_proj.weight": "model-00010-of-00018.safetensors",
171
+ "model.layers.21.self_attn.q_proj.weight": "model-00010-of-00018.safetensors",
172
+ "model.layers.21.self_attn.v_proj.weight": "model-00010-of-00018.safetensors",
173
+ "model.layers.22.input_layernorm.weight": "model-00010-of-00018.safetensors",
174
+ "model.layers.22.mlp.down_proj.weight": "model-00010-of-00018.safetensors",
175
+ "model.layers.22.mlp.gate_proj.weight": "model-00010-of-00018.safetensors",
176
+ "model.layers.22.mlp.up_proj.weight": "model-00011-of-00018.safetensors",
177
+ "model.layers.22.post_attention_layernorm.weight": "model-00011-of-00018.safetensors",
178
+ "model.layers.22.post_feedforward_layernorm.weight": "model-00011-of-00018.safetensors",
179
+ "model.layers.22.pre_feedforward_layernorm.weight": "model-00011-of-00018.safetensors",
180
+ "model.layers.22.self_attn.k_proj.weight": "model-00011-of-00018.safetensors",
181
+ "model.layers.22.self_attn.o_proj.weight": "model-00011-of-00018.safetensors",
182
+ "model.layers.22.self_attn.q_proj.weight": "model-00011-of-00018.safetensors",
183
+ "model.layers.22.self_attn.v_proj.weight": "model-00011-of-00018.safetensors",
184
+ "model.layers.23.input_layernorm.weight": "model-00011-of-00018.safetensors",
185
+ "model.layers.23.mlp.down_proj.weight": "model-00011-of-00018.safetensors",
186
+ "model.layers.23.mlp.gate_proj.weight": "model-00011-of-00018.safetensors",
187
+ "model.layers.23.mlp.up_proj.weight": "model-00011-of-00018.safetensors",
188
+ "model.layers.23.post_attention_layernorm.weight": "model-00011-of-00018.safetensors",
189
+ "model.layers.23.post_feedforward_layernorm.weight": "model-00011-of-00018.safetensors",
190
+ "model.layers.23.pre_feedforward_layernorm.weight": "model-00011-of-00018.safetensors",
191
+ "model.layers.23.self_attn.k_proj.weight": "model-00011-of-00018.safetensors",
192
+ "model.layers.23.self_attn.o_proj.weight": "model-00011-of-00018.safetensors",
193
+ "model.layers.23.self_attn.q_proj.weight": "model-00011-of-00018.safetensors",
194
+ "model.layers.23.self_attn.v_proj.weight": "model-00011-of-00018.safetensors",
195
+ "model.layers.24.input_layernorm.weight": "model-00011-of-00018.safetensors",
196
+ "model.layers.24.mlp.down_proj.weight": "model-00011-of-00018.safetensors",
197
+ "model.layers.24.mlp.gate_proj.weight": "model-00011-of-00018.safetensors",
198
+ "model.layers.24.mlp.up_proj.weight": "model-00011-of-00018.safetensors",
199
+ "model.layers.24.post_attention_layernorm.weight": "model-00011-of-00018.safetensors",
200
+ "model.layers.24.post_feedforward_layernorm.weight": "model-00011-of-00018.safetensors",
201
+ "model.layers.24.pre_feedforward_layernorm.weight": "model-00011-of-00018.safetensors",
202
+ "model.layers.24.self_attn.k_proj.weight": "model-00011-of-00018.safetensors",
203
+ "model.layers.24.self_attn.o_proj.weight": "model-00011-of-00018.safetensors",
204
+ "model.layers.24.self_attn.q_proj.weight": "model-00011-of-00018.safetensors",
205
+ "model.layers.24.self_attn.v_proj.weight": "model-00011-of-00018.safetensors",
206
+ "model.layers.25.input_layernorm.weight": "model-00011-of-00018.safetensors",
207
+ "model.layers.25.mlp.down_proj.weight": "model-00012-of-00018.safetensors",
208
+ "model.layers.25.mlp.gate_proj.weight": "model-00012-of-00018.safetensors",
209
+ "model.layers.25.mlp.up_proj.weight": "model-00012-of-00018.safetensors",
210
+ "model.layers.25.post_attention_layernorm.weight": "model-00012-of-00018.safetensors",
211
+ "model.layers.25.post_feedforward_layernorm.weight": "model-00012-of-00018.safetensors",
212
+ "model.layers.25.pre_feedforward_layernorm.weight": "model-00012-of-00018.safetensors",
213
+ "model.layers.25.self_attn.k_proj.weight": "model-00012-of-00018.safetensors",
214
+ "model.layers.25.self_attn.o_proj.weight": "model-00012-of-00018.safetensors",
215
+ "model.layers.25.self_attn.q_proj.weight": "model-00012-of-00018.safetensors",
216
+ "model.layers.25.self_attn.v_proj.weight": "model-00012-of-00018.safetensors",
217
+ "model.layers.26.input_layernorm.weight": "model-00012-of-00018.safetensors",
218
+ "model.layers.26.mlp.down_proj.weight": "model-00012-of-00018.safetensors",
219
+ "model.layers.26.mlp.gate_proj.weight": "model-00012-of-00018.safetensors",
220
+ "model.layers.26.mlp.up_proj.weight": "model-00012-of-00018.safetensors",
221
+ "model.layers.26.post_attention_layernorm.weight": "model-00012-of-00018.safetensors",
222
+ "model.layers.26.post_feedforward_layernorm.weight": "model-00012-of-00018.safetensors",
223
+ "model.layers.26.pre_feedforward_layernorm.weight": "model-00012-of-00018.safetensors",
224
+ "model.layers.26.self_attn.k_proj.weight": "model-00012-of-00018.safetensors",
225
+ "model.layers.26.self_attn.o_proj.weight": "model-00012-of-00018.safetensors",
226
+ "model.layers.26.self_attn.q_proj.weight": "model-00012-of-00018.safetensors",
227
+ "model.layers.26.self_attn.v_proj.weight": "model-00012-of-00018.safetensors",
228
+ "model.layers.27.input_layernorm.weight": "model-00012-of-00018.safetensors",
229
+ "model.layers.27.mlp.down_proj.weight": "model-00012-of-00018.safetensors",
230
+ "model.layers.27.mlp.gate_proj.weight": "model-00012-of-00018.safetensors",
231
+ "model.layers.27.mlp.up_proj.weight": "model-00013-of-00018.safetensors",
232
+ "model.layers.27.post_attention_layernorm.weight": "model-00013-of-00018.safetensors",
233
+ "model.layers.27.post_feedforward_layernorm.weight": "model-00013-of-00018.safetensors",
234
+ "model.layers.27.pre_feedforward_layernorm.weight": "model-00013-of-00018.safetensors",
235
+ "model.layers.27.self_attn.k_proj.weight": "model-00013-of-00018.safetensors",
236
+ "model.layers.27.self_attn.o_proj.weight": "model-00013-of-00018.safetensors",
237
+ "model.layers.27.self_attn.q_proj.weight": "model-00013-of-00018.safetensors",
238
+ "model.layers.27.self_attn.v_proj.weight": "model-00013-of-00018.safetensors",
239
+ "model.layers.28.input_layernorm.weight": "model-00013-of-00018.safetensors",
240
+ "model.layers.28.mlp.down_proj.weight": "model-00013-of-00018.safetensors",
241
+ "model.layers.28.mlp.gate_proj.weight": "model-00013-of-00018.safetensors",
242
+ "model.layers.28.mlp.up_proj.weight": "model-00013-of-00018.safetensors",
243
+ "model.layers.28.post_attention_layernorm.weight": "model-00013-of-00018.safetensors",
244
+ "model.layers.28.post_feedforward_layernorm.weight": "model-00013-of-00018.safetensors",
245
+ "model.layers.28.pre_feedforward_layernorm.weight": "model-00013-of-00018.safetensors",
246
+ "model.layers.28.self_attn.k_proj.weight": "model-00013-of-00018.safetensors",
247
+ "model.layers.28.self_attn.o_proj.weight": "model-00013-of-00018.safetensors",
248
+ "model.layers.28.self_attn.q_proj.weight": "model-00013-of-00018.safetensors",
249
+ "model.layers.28.self_attn.v_proj.weight": "model-00013-of-00018.safetensors",
250
+ "model.layers.29.input_layernorm.weight": "model-00013-of-00018.safetensors",
251
+ "model.layers.29.mlp.down_proj.weight": "model-00013-of-00018.safetensors",
252
+ "model.layers.29.mlp.gate_proj.weight": "model-00013-of-00018.safetensors",
253
+ "model.layers.29.mlp.up_proj.weight": "model-00013-of-00018.safetensors",
254
+ "model.layers.29.post_attention_layernorm.weight": "model-00013-of-00018.safetensors",
255
+ "model.layers.29.post_feedforward_layernorm.weight": "model-00013-of-00018.safetensors",
256
+ "model.layers.29.pre_feedforward_layernorm.weight": "model-00013-of-00018.safetensors",
257
+ "model.layers.29.self_attn.k_proj.weight": "model-00013-of-00018.safetensors",
258
+ "model.layers.29.self_attn.o_proj.weight": "model-00013-of-00018.safetensors",
259
+ "model.layers.29.self_attn.q_proj.weight": "model-00013-of-00018.safetensors",
260
+ "model.layers.29.self_attn.v_proj.weight": "model-00013-of-00018.safetensors",
261
+ "model.layers.3.input_layernorm.weight": "model-00003-of-00018.safetensors",
262
+ "model.layers.3.mlp.down_proj.weight": "model-00003-of-00018.safetensors",
263
+ "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00018.safetensors",
264
+ "model.layers.3.mlp.up_proj.weight": "model-00003-of-00018.safetensors",
265
+ "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00018.safetensors",
266
+ "model.layers.3.post_feedforward_layernorm.weight": "model-00003-of-00018.safetensors",
267
+ "model.layers.3.pre_feedforward_layernorm.weight": "model-00003-of-00018.safetensors",
268
+ "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00018.safetensors",
269
+ "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00018.safetensors",
270
+ "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00018.safetensors",
271
+ "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00018.safetensors",
272
+ "model.layers.30.input_layernorm.weight": "model-00013-of-00018.safetensors",
273
+ "model.layers.30.mlp.down_proj.weight": "model-00014-of-00018.safetensors",
274
+ "model.layers.30.mlp.gate_proj.weight": "model-00014-of-00018.safetensors",
275
+ "model.layers.30.mlp.up_proj.weight": "model-00014-of-00018.safetensors",
276
+ "model.layers.30.post_attention_layernorm.weight": "model-00014-of-00018.safetensors",
277
+ "model.layers.30.post_feedforward_layernorm.weight": "model-00014-of-00018.safetensors",
278
+ "model.layers.30.pre_feedforward_layernorm.weight": "model-00014-of-00018.safetensors",
279
+ "model.layers.30.self_attn.k_proj.weight": "model-00014-of-00018.safetensors",
280
+ "model.layers.30.self_attn.o_proj.weight": "model-00014-of-00018.safetensors",
281
+ "model.layers.30.self_attn.q_proj.weight": "model-00014-of-00018.safetensors",
282
+ "model.layers.30.self_attn.v_proj.weight": "model-00014-of-00018.safetensors",
283
+ "model.layers.31.input_layernorm.weight": "model-00014-of-00018.safetensors",
284
+ "model.layers.31.mlp.down_proj.weight": "model-00014-of-00018.safetensors",
285
+ "model.layers.31.mlp.gate_proj.weight": "model-00014-of-00018.safetensors",
286
+ "model.layers.31.mlp.up_proj.weight": "model-00014-of-00018.safetensors",
287
+ "model.layers.31.post_attention_layernorm.weight": "model-00014-of-00018.safetensors",
288
+ "model.layers.31.post_feedforward_layernorm.weight": "model-00014-of-00018.safetensors",
289
+ "model.layers.31.pre_feedforward_layernorm.weight": "model-00014-of-00018.safetensors",
290
+ "model.layers.31.self_attn.k_proj.weight": "model-00014-of-00018.safetensors",
291
+ "model.layers.31.self_attn.o_proj.weight": "model-00014-of-00018.safetensors",
292
+ "model.layers.31.self_attn.q_proj.weight": "model-00014-of-00018.safetensors",
293
+ "model.layers.31.self_attn.v_proj.weight": "model-00014-of-00018.safetensors",
294
+ "model.layers.32.input_layernorm.weight": "model-00014-of-00018.safetensors",
295
+ "model.layers.32.mlp.down_proj.weight": "model-00014-of-00018.safetensors",
296
+ "model.layers.32.mlp.gate_proj.weight": "model-00014-of-00018.safetensors",
297
+ "model.layers.32.mlp.up_proj.weight": "model-00015-of-00018.safetensors",
298
+ "model.layers.32.post_attention_layernorm.weight": "model-00015-of-00018.safetensors",
299
+ "model.layers.32.post_feedforward_layernorm.weight": "model-00015-of-00018.safetensors",
300
+ "model.layers.32.pre_feedforward_layernorm.weight": "model-00015-of-00018.safetensors",
301
+ "model.layers.32.self_attn.k_proj.weight": "model-00015-of-00018.safetensors",
302
+ "model.layers.32.self_attn.o_proj.weight": "model-00015-of-00018.safetensors",
303
+ "model.layers.32.self_attn.q_proj.weight": "model-00015-of-00018.safetensors",
304
+ "model.layers.32.self_attn.v_proj.weight": "model-00015-of-00018.safetensors",
305
+ "model.layers.33.input_layernorm.weight": "model-00015-of-00018.safetensors",
306
+ "model.layers.33.mlp.down_proj.weight": "model-00015-of-00018.safetensors",
307
+ "model.layers.33.mlp.gate_proj.weight": "model-00015-of-00018.safetensors",
308
+ "model.layers.33.mlp.up_proj.weight": "model-00015-of-00018.safetensors",
309
+ "model.layers.33.post_attention_layernorm.weight": "model-00015-of-00018.safetensors",
310
+ "model.layers.33.post_feedforward_layernorm.weight": "model-00015-of-00018.safetensors",
311
+ "model.layers.33.pre_feedforward_layernorm.weight": "model-00015-of-00018.safetensors",
312
+ "model.layers.33.self_attn.k_proj.weight": "model-00015-of-00018.safetensors",
313
+ "model.layers.33.self_attn.o_proj.weight": "model-00015-of-00018.safetensors",
314
+ "model.layers.33.self_attn.q_proj.weight": "model-00015-of-00018.safetensors",
315
+ "model.layers.33.self_attn.v_proj.weight": "model-00015-of-00018.safetensors",
316
+ "model.layers.34.input_layernorm.weight": "model-00015-of-00018.safetensors",
317
+ "model.layers.34.mlp.down_proj.weight": "model-00015-of-00018.safetensors",
318
+ "model.layers.34.mlp.gate_proj.weight": "model-00015-of-00018.safetensors",
319
+ "model.layers.34.mlp.up_proj.weight": "model-00015-of-00018.safetensors",
320
+ "model.layers.34.post_attention_layernorm.weight": "model-00015-of-00018.safetensors",
321
+ "model.layers.34.post_feedforward_layernorm.weight": "model-00015-of-00018.safetensors",
322
+ "model.layers.34.pre_feedforward_layernorm.weight": "model-00015-of-00018.safetensors",
323
+ "model.layers.34.self_attn.k_proj.weight": "model-00015-of-00018.safetensors",
324
+ "model.layers.34.self_attn.o_proj.weight": "model-00015-of-00018.safetensors",
325
+ "model.layers.34.self_attn.q_proj.weight": "model-00015-of-00018.safetensors",
326
+ "model.layers.34.self_attn.v_proj.weight": "model-00015-of-00018.safetensors",
327
+ "model.layers.35.input_layernorm.weight": "model-00015-of-00018.safetensors",
328
+ "model.layers.35.mlp.down_proj.weight": "model-00016-of-00018.safetensors",
329
+ "model.layers.35.mlp.gate_proj.weight": "model-00016-of-00018.safetensors",
330
+ "model.layers.35.mlp.up_proj.weight": "model-00016-of-00018.safetensors",
331
+ "model.layers.35.post_attention_layernorm.weight": "model-00016-of-00018.safetensors",
332
+ "model.layers.35.post_feedforward_layernorm.weight": "model-00016-of-00018.safetensors",
333
+ "model.layers.35.pre_feedforward_layernorm.weight": "model-00016-of-00018.safetensors",
334
+ "model.layers.35.self_attn.k_proj.weight": "model-00016-of-00018.safetensors",
335
+ "model.layers.35.self_attn.o_proj.weight": "model-00016-of-00018.safetensors",
336
+ "model.layers.35.self_attn.q_proj.weight": "model-00016-of-00018.safetensors",
337
+ "model.layers.35.self_attn.v_proj.weight": "model-00016-of-00018.safetensors",
338
+ "model.layers.36.input_layernorm.weight": "model-00016-of-00018.safetensors",
339
+ "model.layers.36.mlp.down_proj.weight": "model-00016-of-00018.safetensors",
340
+ "model.layers.36.mlp.gate_proj.weight": "model-00016-of-00018.safetensors",
341
+ "model.layers.36.mlp.up_proj.weight": "model-00016-of-00018.safetensors",
342
+ "model.layers.36.post_attention_layernorm.weight": "model-00016-of-00018.safetensors",
343
+ "model.layers.36.post_feedforward_layernorm.weight": "model-00016-of-00018.safetensors",
344
+ "model.layers.36.pre_feedforward_layernorm.weight": "model-00016-of-00018.safetensors",
345
+ "model.layers.36.self_attn.k_proj.weight": "model-00016-of-00018.safetensors",
346
+ "model.layers.36.self_attn.o_proj.weight": "model-00016-of-00018.safetensors",
347
+ "model.layers.36.self_attn.q_proj.weight": "model-00016-of-00018.safetensors",
348
+ "model.layers.36.self_attn.v_proj.weight": "model-00016-of-00018.safetensors",
349
+ "model.layers.37.input_layernorm.weight": "model-00016-of-00018.safetensors",
350
+ "model.layers.37.mlp.down_proj.weight": "model-00016-of-00018.safetensors",
351
+ "model.layers.37.mlp.gate_proj.weight": "model-00016-of-00018.safetensors",
352
+ "model.layers.37.mlp.up_proj.weight": "model-00017-of-00018.safetensors",
353
+ "model.layers.37.post_attention_layernorm.weight": "model-00017-of-00018.safetensors",
354
+ "model.layers.37.post_feedforward_layernorm.weight": "model-00017-of-00018.safetensors",
355
+ "model.layers.37.pre_feedforward_layernorm.weight": "model-00017-of-00018.safetensors",
356
+ "model.layers.37.self_attn.k_proj.weight": "model-00017-of-00018.safetensors",
357
+ "model.layers.37.self_attn.o_proj.weight": "model-00017-of-00018.safetensors",
358
+ "model.layers.37.self_attn.q_proj.weight": "model-00017-of-00018.safetensors",
359
+ "model.layers.37.self_attn.v_proj.weight": "model-00017-of-00018.safetensors",
360
+ "model.layers.38.input_layernorm.weight": "model-00017-of-00018.safetensors",
361
+ "model.layers.38.mlp.down_proj.weight": "model-00017-of-00018.safetensors",
362
+ "model.layers.38.mlp.gate_proj.weight": "model-00017-of-00018.safetensors",
363
+ "model.layers.38.mlp.up_proj.weight": "model-00017-of-00018.safetensors",
364
+ "model.layers.38.post_attention_layernorm.weight": "model-00017-of-00018.safetensors",
365
+ "model.layers.38.post_feedforward_layernorm.weight": "model-00017-of-00018.safetensors",
366
+ "model.layers.38.pre_feedforward_layernorm.weight": "model-00017-of-00018.safetensors",
367
+ "model.layers.38.self_attn.k_proj.weight": "model-00017-of-00018.safetensors",
368
+ "model.layers.38.self_attn.o_proj.weight": "model-00017-of-00018.safetensors",
369
+ "model.layers.38.self_attn.q_proj.weight": "model-00017-of-00018.safetensors",
370
+ "model.layers.38.self_attn.v_proj.weight": "model-00017-of-00018.safetensors",
371
+ "model.layers.39.input_layernorm.weight": "model-00017-of-00018.safetensors",
372
+ "model.layers.39.mlp.down_proj.weight": "model-00017-of-00018.safetensors",
373
+ "model.layers.39.mlp.gate_proj.weight": "model-00017-of-00018.safetensors",
374
+ "model.layers.39.mlp.up_proj.weight": "model-00017-of-00018.safetensors",
375
+ "model.layers.39.post_attention_layernorm.weight": "model-00017-of-00018.safetensors",
376
+ "model.layers.39.post_feedforward_layernorm.weight": "model-00017-of-00018.safetensors",
377
+ "model.layers.39.pre_feedforward_layernorm.weight": "model-00017-of-00018.safetensors",
378
+ "model.layers.39.self_attn.k_proj.weight": "model-00017-of-00018.safetensors",
379
+ "model.layers.39.self_attn.o_proj.weight": "model-00017-of-00018.safetensors",
380
+ "model.layers.39.self_attn.q_proj.weight": "model-00017-of-00018.safetensors",
381
+ "model.layers.39.self_attn.v_proj.weight": "model-00017-of-00018.safetensors",
382
+ "model.layers.4.input_layernorm.weight": "model-00003-of-00018.safetensors",
383
+ "model.layers.4.mlp.down_proj.weight": "model-00003-of-00018.safetensors",
384
+ "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00018.safetensors",
385
+ "model.layers.4.mlp.up_proj.weight": "model-00003-of-00018.safetensors",
386
+ "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00018.safetensors",
387
+ "model.layers.4.post_feedforward_layernorm.weight": "model-00003-of-00018.safetensors",
388
+ "model.layers.4.pre_feedforward_layernorm.weight": "model-00003-of-00018.safetensors",
389
+ "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00018.safetensors",
390
+ "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00018.safetensors",
391
+ "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00018.safetensors",
392
+ "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00018.safetensors",
393
+ "model.layers.40.input_layernorm.weight": "model-00017-of-00018.safetensors",
394
+ "model.layers.40.mlp.down_proj.weight": "model-00018-of-00018.safetensors",
395
+ "model.layers.40.mlp.gate_proj.weight": "model-00018-of-00018.safetensors",
396
+ "model.layers.40.mlp.up_proj.weight": "model-00018-of-00018.safetensors",
397
+ "model.layers.40.post_attention_layernorm.weight": "model-00018-of-00018.safetensors",
398
+ "model.layers.40.post_feedforward_layernorm.weight": "model-00018-of-00018.safetensors",
399
+ "model.layers.40.pre_feedforward_layernorm.weight": "model-00018-of-00018.safetensors",
400
+ "model.layers.40.self_attn.k_proj.weight": "model-00018-of-00018.safetensors",
401
+ "model.layers.40.self_attn.o_proj.weight": "model-00018-of-00018.safetensors",
402
+ "model.layers.40.self_attn.q_proj.weight": "model-00018-of-00018.safetensors",
403
+ "model.layers.40.self_attn.v_proj.weight": "model-00018-of-00018.safetensors",
404
+ "model.layers.41.input_layernorm.weight": "model-00018-of-00018.safetensors",
405
+ "model.layers.41.mlp.down_proj.weight": "model-00018-of-00018.safetensors",
406
+ "model.layers.41.mlp.gate_proj.weight": "model-00018-of-00018.safetensors",
407
+ "model.layers.41.mlp.up_proj.weight": "model-00018-of-00018.safetensors",
408
+ "model.layers.41.post_attention_layernorm.weight": "model-00018-of-00018.safetensors",
409
+ "model.layers.41.post_feedforward_layernorm.weight": "model-00018-of-00018.safetensors",
410
+ "model.layers.41.pre_feedforward_layernorm.weight": "model-00018-of-00018.safetensors",
411
+ "model.layers.41.self_attn.k_proj.weight": "model-00018-of-00018.safetensors",
412
+ "model.layers.41.self_attn.o_proj.weight": "model-00018-of-00018.safetensors",
413
+ "model.layers.41.self_attn.q_proj.weight": "model-00018-of-00018.safetensors",
414
+ "model.layers.41.self_attn.v_proj.weight": "model-00018-of-00018.safetensors",
415
+ "model.layers.5.input_layernorm.weight": "model-00003-of-00018.safetensors",
416
+ "model.layers.5.mlp.down_proj.weight": "model-00004-of-00018.safetensors",
417
+ "model.layers.5.mlp.gate_proj.weight": "model-00004-of-00018.safetensors",
418
+ "model.layers.5.mlp.up_proj.weight": "model-00004-of-00018.safetensors",
419
+ "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00018.safetensors",
420
+ "model.layers.5.post_feedforward_layernorm.weight": "model-00004-of-00018.safetensors",
421
+ "model.layers.5.pre_feedforward_layernorm.weight": "model-00004-of-00018.safetensors",
422
+ "model.layers.5.self_attn.k_proj.weight": "model-00004-of-00018.safetensors",
423
+ "model.layers.5.self_attn.o_proj.weight": "model-00004-of-00018.safetensors",
424
+ "model.layers.5.self_attn.q_proj.weight": "model-00004-of-00018.safetensors",
425
+ "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00018.safetensors",
426
+ "model.layers.6.input_layernorm.weight": "model-00004-of-00018.safetensors",
427
+ "model.layers.6.mlp.down_proj.weight": "model-00004-of-00018.safetensors",
428
+ "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00018.safetensors",
429
+ "model.layers.6.mlp.up_proj.weight": "model-00004-of-00018.safetensors",
430
+ "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00018.safetensors",
431
+ "model.layers.6.post_feedforward_layernorm.weight": "model-00004-of-00018.safetensors",
432
+ "model.layers.6.pre_feedforward_layernorm.weight": "model-00004-of-00018.safetensors",
433
+ "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00018.safetensors",
434
+ "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00018.safetensors",
435
+ "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00018.safetensors",
436
+ "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00018.safetensors",
437
+ "model.layers.7.input_layernorm.weight": "model-00004-of-00018.safetensors",
438
+ "model.layers.7.mlp.down_proj.weight": "model-00004-of-00018.safetensors",
439
+ "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00018.safetensors",
440
+ "model.layers.7.mlp.up_proj.weight": "model-00005-of-00018.safetensors",
441
+ "model.layers.7.post_attention_layernorm.weight": "model-00005-of-00018.safetensors",
442
+ "model.layers.7.post_feedforward_layernorm.weight": "model-00005-of-00018.safetensors",
443
+ "model.layers.7.pre_feedforward_layernorm.weight": "model-00005-of-00018.safetensors",
444
+ "model.layers.7.self_attn.k_proj.weight": "model-00005-of-00018.safetensors",
445
+ "model.layers.7.self_attn.o_proj.weight": "model-00005-of-00018.safetensors",
446
+ "model.layers.7.self_attn.q_proj.weight": "model-00005-of-00018.safetensors",
447
+ "model.layers.7.self_attn.v_proj.weight": "model-00005-of-00018.safetensors",
448
+ "model.layers.8.input_layernorm.weight": "model-00005-of-00018.safetensors",
449
+ "model.layers.8.mlp.down_proj.weight": "model-00005-of-00018.safetensors",
450
+ "model.layers.8.mlp.gate_proj.weight": "model-00005-of-00018.safetensors",
451
+ "model.layers.8.mlp.up_proj.weight": "model-00005-of-00018.safetensors",
452
+ "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00018.safetensors",
453
+ "model.layers.8.post_feedforward_layernorm.weight": "model-00005-of-00018.safetensors",
454
+ "model.layers.8.pre_feedforward_layernorm.weight": "model-00005-of-00018.safetensors",
455
+ "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00018.safetensors",
456
+ "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00018.safetensors",
457
+ "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00018.safetensors",
458
+ "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00018.safetensors",
459
+ "model.layers.9.input_layernorm.weight": "model-00005-of-00018.safetensors",
460
+ "model.layers.9.mlp.down_proj.weight": "model-00005-of-00018.safetensors",
461
+ "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00018.safetensors",
462
+ "model.layers.9.mlp.up_proj.weight": "model-00005-of-00018.safetensors",
463
+ "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00018.safetensors",
464
+ "model.layers.9.post_feedforward_layernorm.weight": "model-00005-of-00018.safetensors",
465
+ "model.layers.9.pre_feedforward_layernorm.weight": "model-00005-of-00018.safetensors",
466
+ "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00018.safetensors",
467
+ "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00018.safetensors",
468
+ "model.layers.9.self_attn.q_proj.weight": "model-00005-of-00018.safetensors",
469
+ "model.layers.9.self_attn.v_proj.weight": "model-00005-of-00018.safetensors",
470
+ "model.norm.weight": "model-00018-of-00018.safetensors"
471
+ }
472
+ }
hs2gemma/gnb/nbs/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:487cee8724215dcd2dde8888539e8b1bf844ceb5dbbe27f7845abda69eeb060f
3
+ size 34362872
hs2gemma/gnb/nbs/tokenizer_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<bos>",
4
+ "clean_up_tokenization_spaces": false,
5
+ "eos_token": "<eos>",
6
+ "extra_special_tokens": [
7
+ "<start_of_turn>",
8
+ "<end_of_turn>"
9
+ ],
10
+ "is_local": true,
11
+ "local_files_only": true,
12
+ "mask_token": "<mask>",
13
+ "model_max_length": 2048,
14
+ "pad_token": "<pad>",
15
+ "sp_model_kwargs": {},
16
+ "spaces_between_special_tokens": false,
17
+ "tokenizer_class": "GemmaTokenizer",
18
+ "unk_token": "<unk>",
19
+ "use_default_system_prompt": false
20
+ }