lilwilsond2 commited on
Commit
80c1224
1 Parent(s): 022b444
README.md ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ model-index:
5
+ - name: completed-model
6
+ results: []
7
+ ---
8
+
9
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
10
+ should probably proofread and complete it, then remove this comment. -->
11
+
12
+ [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
13
+ # completed-model
14
+
15
+ This model was trained from scratch on the None dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 0.3186
18
+ - Rewards/chosen: -0.6296
19
+ - Rewards/rejected: -2.5591
20
+ - Rewards/accuracies: 0.8571
21
+ - Rewards/margins: 1.9295
22
+ - Logps/rejected: -296.3221
23
+ - Logps/chosen: -425.5087
24
+ - Logits/rejected: -2.2481
25
+ - Logits/chosen: -1.7413
26
+
27
+ ## Model description
28
+
29
+ More information needed
30
+
31
+ ## Intended uses & limitations
32
+
33
+ More information needed
34
+
35
+ ## Training and evaluation data
36
+
37
+ More information needed
38
+
39
+ ## Training procedure
40
+
41
+ ### Training hyperparameters
42
+
43
+ The following hyperparameters were used during training:
44
+ - learning_rate: 5e-07
45
+ - train_batch_size: 3
46
+ - eval_batch_size: 3
47
+ - seed: 42
48
+ - distributed_type: multi-GPU
49
+ - num_devices: 40
50
+ - total_train_batch_size: 120
51
+ - total_eval_batch_size: 120
52
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
53
+ - lr_scheduler_type: linear
54
+ - lr_scheduler_warmup_steps: 18
55
+ - num_epochs: 1
56
+
57
+ ### Training results
58
+
59
+ | Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
60
+ |:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
61
+ | 0.4772 | 0.1 | 61 | 0.4037 | -0.3256 | -1.2099 | 0.8095 | 0.8843 | -282.8301 | -422.4691 | -2.1649 | -1.6678 |
62
+ | 0.3859 | 0.2 | 122 | 0.3681 | -0.3816 | -1.7445 | 0.7143 | 1.3629 | -288.1762 | -423.0287 | -2.2536 | -1.7385 |
63
+ | 0.3061 | 0.3 | 183 | 0.3546 | -0.4969 | -2.1025 | 0.8095 | 1.6056 | -291.7559 | -424.1818 | -2.1989 | -1.7108 |
64
+ | 0.3765 | 0.4 | 244 | 0.3374 | -0.5153 | -2.1301 | 0.7619 | 1.6148 | -292.0326 | -424.3660 | -2.2182 | -1.7222 |
65
+ | 0.2819 | 0.5 | 305 | 0.3303 | -0.4402 | -2.1809 | 0.8095 | 1.7407 | -292.5404 | -423.6147 | -2.1835 | -1.6998 |
66
+ | 0.3009 | 0.6 | 366 | 0.3314 | -0.8026 | -2.7756 | 0.8571 | 1.9730 | -298.4871 | -427.2388 | -2.2430 | -1.7529 |
67
+ | 0.3015 | 0.7 | 427 | 0.3228 | -0.6439 | -2.5710 | 0.9048 | 1.9271 | -296.4410 | -425.6519 | -2.2258 | -1.7303 |
68
+ | 0.3407 | 0.8 | 488 | 0.3185 | -0.7270 | -2.7118 | 0.8571 | 1.9847 | -297.8488 | -426.4829 | -2.2530 | -1.7496 |
69
+ | 0.3149 | 0.9 | 549 | 0.3186 | -0.6296 | -2.5591 | 0.8571 | 1.9295 | -296.3221 | -425.5087 | -2.2481 | -1.7413 |
70
+
71
+
72
+ ### Framework versions
73
+
74
+ - Transformers 4.35.1
75
+ - Pytorch 2.0.1+cu118
76
+ - Datasets 2.14.7
77
+ - Tokenizers 0.14.1
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<pad>": 32000
3
+ }
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/tmp/model",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 8192,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 28672,
14
+ "max_position_embeddings": 4096,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 64,
17
+ "num_hidden_layers": 80,
18
+ "num_key_value_heads": 8,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_scaling": null,
22
+ "rope_theta": 10000.0,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.35.1",
26
+ "use_cache": false,
27
+ "vocab_size": 32001
28
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "do_sample": true,
4
+ "eos_token_id": 2,
5
+ "max_length": 4096,
6
+ "pad_token_id": 0,
7
+ "temperature": 0.6,
8
+ "top_p": 0.9,
9
+ "transformers_version": "4.35.1"
10
+ }
model-00001-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9b65882814319ea0d9da14aeb1fd79b014fcb1aafcd85f0a7952972f218813f
3
+ size 4718676720
model-00002-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d2a997ecb5ff710dccc0b2d817f7381cde00b1c91fb4279b80f912144bab4d6
3
+ size 4664167376
model-00003-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31e57d9019e4c2708586ca668d8619d17200a8034b1a9a6b266f3028a0a67db5
3
+ size 4999711704
model-00004-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55944d7987280771480e4d18031ae491f26f302907c5914dde00d6505316ba35
3
+ size 4966157048
model-00005-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9360e9d9018fa8723cac0ecd9b496814dade6ea6dbf4f795cb901dcb140bd2de
3
+ size 4664134408
model-00006-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4dfcbdf8717cfb29c9df563a9a1052a78a839d917e8f853dd728b22777aa9cd0
3
+ size 4664167408
model-00007-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1259163f5bbe0caf9c38b1a7bd3106f87899bd04df3dfde336efdd50277d088a
3
+ size 4664167408
model-00008-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58fa4d3c798973df319b407d9be2f43e24261e8880d0d9ac68fa3d413d6b2d6b
3
+ size 4999711728
model-00009-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:740b8b715a1d5428a475c364b8064736caac1e57f605ec68d7d920afc3dec9ac
3
+ size 4966157056
model-00010-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:031fcb6c0a6aad972b9633f0c16f897ce8247c773f5b8d6cb0ba958d1ab91327
3
+ size 4664134408
model-00011-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2c2c46934bc70f3d70b44ffbee9856ff2efa82124f3ca2d455dbd15f697f0fd
3
+ size 4664167408
model-00012-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35c7102f31f0c81d69f57b7b7001ab1d6dfb8811a19fa7154565f291553f386c
3
+ size 4664167408
model-00013-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eeb4777fbca2407783a13b8e2d1f70b83435a5748c3ccaa8952ac0748524e5ab
3
+ size 4999711728
model-00014-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13a7b0efd006095bda6c6c148e42ca78553e8fb55ccda9f365916d91ff9877a3
3
+ size 4966157056
model-00015-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5e851a846e1532ca85e52b4839362fee9947f42671830fcbc41c7c4bb397f77
3
+ size 4664134408
model-00016-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d634856a3416fdb2a30aced3a18d5910708823cfab7a611a0e649ca74711b18e
3
+ size 4664167408
model-00017-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4d1b3855c270fd6109aec7aa58f4088f0a0a769222086fb3f7385feff94f81e
3
+ size 4664167408
model-00018-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc42ee82a73d56f3ced20d21cb9bff780bd7f8f477cfba742ade991b561106e9
3
+ size 4999711728
model-00019-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf57a6da2f6195b8b927ed26a8807865ca1d2813ecd6b6ce201a170a77ddcdb1
3
+ size 4966157056
model-00020-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24cdebc904dfbc8f9538a5a52081e83c0779b92ba1ad9da1b79896e320ddd757
3
+ size 4664134408
model-00021-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4414244446917ef6b675d3dfd7a0ac5d9f8de54d1e286678213e9226a7813ddf
3
+ size 4664167408
model-00022-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c571053175a7c0993009e0ed5bc82e52689f3921d9b8c70688e718f01e2e0d0
3
+ size 4664167408
model-00023-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8d9b9f4e8a5b687685c6296f979b54607119f7cde5c524d4b399e6ba40d8a63
3
+ size 4999711728
model-00024-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8feb9a828da0fe3bcd29996af214e408524382158a0548000ef934f1fda9fd37
3
+ size 4966157056
model-00025-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40f85f4d9e94ce7b2d8f4c3ea2dff3c6eda8bf59881ae2a8c451e35d4fd8557c
3
+ size 4664134408
model-00026-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8fa298f27004b196115e86ea736e964b84ebb6e15bba72df12984fafdc314e0
3
+ size 4664167408
model-00027-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42f279dd139f154ace5b70549432e052ae956ffe6510dc29f23179955f3a2a2d
3
+ size 4664167408
model-00028-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8a5187ce16d3d370f19e42499a7002f04c7242c37d21e58e0dcf77aaad7359c
3
+ size 4999711728
model-00029-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e52a6f70489ebf871f5481917ad948a34c7f4c39e8bb83d2093023449eca915
3
+ size 3779168168
model.safetensors.index.json ADDED
@@ -0,0 +1,730 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 137953329152
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00029-of-00029.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00029.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00029.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00029.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00029.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00029.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00029.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00029.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00029.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00029.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00029.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00029.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00029.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00029.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00029.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00029.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00029.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00029.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00029.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00029.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00004-of-00029.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00004-of-00029.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00029.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00004-of-00029.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00029.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00029.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00029.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00029.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00029.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00005-of-00029.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00005-of-00029.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00029.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00005-of-00029.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00029.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00029.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00029.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00029.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00029.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00005-of-00029.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00005-of-00029.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00029.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00005-of-00029.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00029.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00029.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00029.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00029.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00029.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00006-of-00029.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00006-of-00029.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00029.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00005-of-00029.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00029.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00029.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00029.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00029.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00029.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00006-of-00029.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00006-of-00029.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00029.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00006-of-00029.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00029.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00029.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00029.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00029.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00029.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00006-of-00029.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00006-of-00029.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00006-of-00029.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00006-of-00029.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00029.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00029.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00029.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00029.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00029.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00007-of-00029.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00007-of-00029.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00006-of-00029.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00007-of-00029.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00029.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00029.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00006-of-00029.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00029.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00029.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00007-of-00029.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00007-of-00029.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00007-of-00029.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00007-of-00029.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00007-of-00029.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00007-of-00029.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00007-of-00029.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00007-of-00029.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00007-of-00029.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00007-of-00029.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00007-of-00029.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00007-of-00029.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00007-of-00029.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00007-of-00029.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00029.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00029.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00029.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00029.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00008-of-00029.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00008-of-00029.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00008-of-00029.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00008-of-00029.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00008-of-00029.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00007-of-00029.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00007-of-00029.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00029.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00007-of-00029.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00002-of-00029.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00002-of-00029.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00029.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00002-of-00029.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00029.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00029.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00029.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00029.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00029.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00008-of-00029.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00008-of-00029.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00008-of-00029.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00008-of-00029.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00008-of-00029.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00008-of-00029.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00008-of-00029.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00008-of-00029.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00008-of-00029.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00008-of-00029.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00008-of-00029.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00008-of-00029.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00008-of-00029.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00008-of-00029.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00029.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00008-of-00029.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00029.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00029.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00009-of-00029.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00009-of-00029.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00009-of-00029.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00009-of-00029.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00009-of-00029.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00029.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00009-of-00029.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00029.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00029.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00009-of-00029.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00009-of-00029.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00009-of-00029.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00009-of-00029.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00009-of-00029.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00009-of-00029.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00009-of-00029.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00009-of-00029.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00009-of-00029.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00009-of-00029.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00009-of-00029.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00009-of-00029.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00009-of-00029.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00009-of-00029.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00009-of-00029.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00009-of-00029.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00009-of-00029.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00009-of-00029.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00010-of-00029.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00010-of-00029.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00010-of-00029.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00010-of-00029.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00010-of-00029.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00010-of-00029.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00010-of-00029.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00010-of-00029.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00010-of-00029.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00010-of-00029.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00010-of-00029.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00010-of-00029.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00010-of-00029.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00010-of-00029.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00010-of-00029.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00010-of-00029.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00010-of-00029.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00010-of-00029.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00011-of-00029.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00011-of-00029.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00010-of-00029.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00010-of-00029.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00011-of-00029.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00010-of-00029.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00010-of-00029.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00010-of-00029.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00010-of-00029.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00011-of-00029.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00011-of-00029.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00011-of-00029.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00011-of-00029.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00011-of-00029.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00011-of-00029.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00011-of-00029.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00011-of-00029.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00011-of-00029.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00011-of-00029.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00011-of-00029.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00011-of-00029.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00011-of-00029.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00011-of-00029.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00011-of-00029.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00011-of-00029.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00011-of-00029.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00011-of-00029.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00002-of-00029.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00002-of-00029.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00029.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00002-of-00029.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00029.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00029.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00029.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00029.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00029.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00012-of-00029.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00012-of-00029.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00011-of-00029.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00012-of-00029.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00012-of-00029.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00011-of-00029.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00011-of-00029.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00011-of-00029.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00011-of-00029.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00012-of-00029.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00012-of-00029.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00012-of-00029.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00012-of-00029.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00012-of-00029.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00012-of-00029.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00012-of-00029.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00012-of-00029.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00012-of-00029.safetensors",
242
+ "model.layers.32.input_layernorm.weight": "model-00012-of-00029.safetensors",
243
+ "model.layers.32.mlp.down_proj.weight": "model-00012-of-00029.safetensors",
244
+ "model.layers.32.mlp.gate_proj.weight": "model-00012-of-00029.safetensors",
245
+ "model.layers.32.mlp.up_proj.weight": "model-00012-of-00029.safetensors",
246
+ "model.layers.32.post_attention_layernorm.weight": "model-00012-of-00029.safetensors",
247
+ "model.layers.32.self_attn.k_proj.weight": "model-00012-of-00029.safetensors",
248
+ "model.layers.32.self_attn.o_proj.weight": "model-00012-of-00029.safetensors",
249
+ "model.layers.32.self_attn.q_proj.weight": "model-00012-of-00029.safetensors",
250
+ "model.layers.32.self_attn.v_proj.weight": "model-00012-of-00029.safetensors",
251
+ "model.layers.33.input_layernorm.weight": "model-00013-of-00029.safetensors",
252
+ "model.layers.33.mlp.down_proj.weight": "model-00013-of-00029.safetensors",
253
+ "model.layers.33.mlp.gate_proj.weight": "model-00013-of-00029.safetensors",
254
+ "model.layers.33.mlp.up_proj.weight": "model-00013-of-00029.safetensors",
255
+ "model.layers.33.post_attention_layernorm.weight": "model-00013-of-00029.safetensors",
256
+ "model.layers.33.self_attn.k_proj.weight": "model-00012-of-00029.safetensors",
257
+ "model.layers.33.self_attn.o_proj.weight": "model-00012-of-00029.safetensors",
258
+ "model.layers.33.self_attn.q_proj.weight": "model-00012-of-00029.safetensors",
259
+ "model.layers.33.self_attn.v_proj.weight": "model-00012-of-00029.safetensors",
260
+ "model.layers.34.input_layernorm.weight": "model-00013-of-00029.safetensors",
261
+ "model.layers.34.mlp.down_proj.weight": "model-00013-of-00029.safetensors",
262
+ "model.layers.34.mlp.gate_proj.weight": "model-00013-of-00029.safetensors",
263
+ "model.layers.34.mlp.up_proj.weight": "model-00013-of-00029.safetensors",
264
+ "model.layers.34.post_attention_layernorm.weight": "model-00013-of-00029.safetensors",
265
+ "model.layers.34.self_attn.k_proj.weight": "model-00013-of-00029.safetensors",
266
+ "model.layers.34.self_attn.o_proj.weight": "model-00013-of-00029.safetensors",
267
+ "model.layers.34.self_attn.q_proj.weight": "model-00013-of-00029.safetensors",
268
+ "model.layers.34.self_attn.v_proj.weight": "model-00013-of-00029.safetensors",
269
+ "model.layers.35.input_layernorm.weight": "model-00013-of-00029.safetensors",
270
+ "model.layers.35.mlp.down_proj.weight": "model-00013-of-00029.safetensors",
271
+ "model.layers.35.mlp.gate_proj.weight": "model-00013-of-00029.safetensors",
272
+ "model.layers.35.mlp.up_proj.weight": "model-00013-of-00029.safetensors",
273
+ "model.layers.35.post_attention_layernorm.weight": "model-00013-of-00029.safetensors",
274
+ "model.layers.35.self_attn.k_proj.weight": "model-00013-of-00029.safetensors",
275
+ "model.layers.35.self_attn.o_proj.weight": "model-00013-of-00029.safetensors",
276
+ "model.layers.35.self_attn.q_proj.weight": "model-00013-of-00029.safetensors",
277
+ "model.layers.35.self_attn.v_proj.weight": "model-00013-of-00029.safetensors",
278
+ "model.layers.36.input_layernorm.weight": "model-00014-of-00029.safetensors",
279
+ "model.layers.36.mlp.down_proj.weight": "model-00014-of-00029.safetensors",
280
+ "model.layers.36.mlp.gate_proj.weight": "model-00014-of-00029.safetensors",
281
+ "model.layers.36.mlp.up_proj.weight": "model-00014-of-00029.safetensors",
282
+ "model.layers.36.post_attention_layernorm.weight": "model-00014-of-00029.safetensors",
283
+ "model.layers.36.self_attn.k_proj.weight": "model-00013-of-00029.safetensors",
284
+ "model.layers.36.self_attn.o_proj.weight": "model-00014-of-00029.safetensors",
285
+ "model.layers.36.self_attn.q_proj.weight": "model-00013-of-00029.safetensors",
286
+ "model.layers.36.self_attn.v_proj.weight": "model-00013-of-00029.safetensors",
287
+ "model.layers.37.input_layernorm.weight": "model-00014-of-00029.safetensors",
288
+ "model.layers.37.mlp.down_proj.weight": "model-00014-of-00029.safetensors",
289
+ "model.layers.37.mlp.gate_proj.weight": "model-00014-of-00029.safetensors",
290
+ "model.layers.37.mlp.up_proj.weight": "model-00014-of-00029.safetensors",
291
+ "model.layers.37.post_attention_layernorm.weight": "model-00014-of-00029.safetensors",
292
+ "model.layers.37.self_attn.k_proj.weight": "model-00014-of-00029.safetensors",
293
+ "model.layers.37.self_attn.o_proj.weight": "model-00014-of-00029.safetensors",
294
+ "model.layers.37.self_attn.q_proj.weight": "model-00014-of-00029.safetensors",
295
+ "model.layers.37.self_attn.v_proj.weight": "model-00014-of-00029.safetensors",
296
+ "model.layers.38.input_layernorm.weight": "model-00014-of-00029.safetensors",
297
+ "model.layers.38.mlp.down_proj.weight": "model-00014-of-00029.safetensors",
298
+ "model.layers.38.mlp.gate_proj.weight": "model-00014-of-00029.safetensors",
299
+ "model.layers.38.mlp.up_proj.weight": "model-00014-of-00029.safetensors",
300
+ "model.layers.38.post_attention_layernorm.weight": "model-00014-of-00029.safetensors",
301
+ "model.layers.38.self_attn.k_proj.weight": "model-00014-of-00029.safetensors",
302
+ "model.layers.38.self_attn.o_proj.weight": "model-00014-of-00029.safetensors",
303
+ "model.layers.38.self_attn.q_proj.weight": "model-00014-of-00029.safetensors",
304
+ "model.layers.38.self_attn.v_proj.weight": "model-00014-of-00029.safetensors",
305
+ "model.layers.39.input_layernorm.weight": "model-00015-of-00029.safetensors",
306
+ "model.layers.39.mlp.down_proj.weight": "model-00015-of-00029.safetensors",
307
+ "model.layers.39.mlp.gate_proj.weight": "model-00015-of-00029.safetensors",
308
+ "model.layers.39.mlp.up_proj.weight": "model-00015-of-00029.safetensors",
309
+ "model.layers.39.post_attention_layernorm.weight": "model-00015-of-00029.safetensors",
310
+ "model.layers.39.self_attn.k_proj.weight": "model-00015-of-00029.safetensors",
311
+ "model.layers.39.self_attn.o_proj.weight": "model-00015-of-00029.safetensors",
312
+ "model.layers.39.self_attn.q_proj.weight": "model-00015-of-00029.safetensors",
313
+ "model.layers.39.self_attn.v_proj.weight": "model-00015-of-00029.safetensors",
314
+ "model.layers.4.input_layernorm.weight": "model-00002-of-00029.safetensors",
315
+ "model.layers.4.mlp.down_proj.weight": "model-00002-of-00029.safetensors",
316
+ "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00029.safetensors",
317
+ "model.layers.4.mlp.up_proj.weight": "model-00002-of-00029.safetensors",
318
+ "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00029.safetensors",
319
+ "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00029.safetensors",
320
+ "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00029.safetensors",
321
+ "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00029.safetensors",
322
+ "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00029.safetensors",
323
+ "model.layers.40.input_layernorm.weight": "model-00015-of-00029.safetensors",
324
+ "model.layers.40.mlp.down_proj.weight": "model-00015-of-00029.safetensors",
325
+ "model.layers.40.mlp.gate_proj.weight": "model-00015-of-00029.safetensors",
326
+ "model.layers.40.mlp.up_proj.weight": "model-00015-of-00029.safetensors",
327
+ "model.layers.40.post_attention_layernorm.weight": "model-00015-of-00029.safetensors",
328
+ "model.layers.40.self_attn.k_proj.weight": "model-00015-of-00029.safetensors",
329
+ "model.layers.40.self_attn.o_proj.weight": "model-00015-of-00029.safetensors",
330
+ "model.layers.40.self_attn.q_proj.weight": "model-00015-of-00029.safetensors",
331
+ "model.layers.40.self_attn.v_proj.weight": "model-00015-of-00029.safetensors",
332
+ "model.layers.41.input_layernorm.weight": "model-00016-of-00029.safetensors",
333
+ "model.layers.41.mlp.down_proj.weight": "model-00016-of-00029.safetensors",
334
+ "model.layers.41.mlp.gate_proj.weight": "model-00015-of-00029.safetensors",
335
+ "model.layers.41.mlp.up_proj.weight": "model-00015-of-00029.safetensors",
336
+ "model.layers.41.post_attention_layernorm.weight": "model-00016-of-00029.safetensors",
337
+ "model.layers.41.self_attn.k_proj.weight": "model-00015-of-00029.safetensors",
338
+ "model.layers.41.self_attn.o_proj.weight": "model-00015-of-00029.safetensors",
339
+ "model.layers.41.self_attn.q_proj.weight": "model-00015-of-00029.safetensors",
340
+ "model.layers.41.self_attn.v_proj.weight": "model-00015-of-00029.safetensors",
341
+ "model.layers.42.input_layernorm.weight": "model-00016-of-00029.safetensors",
342
+ "model.layers.42.mlp.down_proj.weight": "model-00016-of-00029.safetensors",
343
+ "model.layers.42.mlp.gate_proj.weight": "model-00016-of-00029.safetensors",
344
+ "model.layers.42.mlp.up_proj.weight": "model-00016-of-00029.safetensors",
345
+ "model.layers.42.post_attention_layernorm.weight": "model-00016-of-00029.safetensors",
346
+ "model.layers.42.self_attn.k_proj.weight": "model-00016-of-00029.safetensors",
347
+ "model.layers.42.self_attn.o_proj.weight": "model-00016-of-00029.safetensors",
348
+ "model.layers.42.self_attn.q_proj.weight": "model-00016-of-00029.safetensors",
349
+ "model.layers.42.self_attn.v_proj.weight": "model-00016-of-00029.safetensors",
350
+ "model.layers.43.input_layernorm.weight": "model-00016-of-00029.safetensors",
351
+ "model.layers.43.mlp.down_proj.weight": "model-00016-of-00029.safetensors",
352
+ "model.layers.43.mlp.gate_proj.weight": "model-00016-of-00029.safetensors",
353
+ "model.layers.43.mlp.up_proj.weight": "model-00016-of-00029.safetensors",
354
+ "model.layers.43.post_attention_layernorm.weight": "model-00016-of-00029.safetensors",
355
+ "model.layers.43.self_attn.k_proj.weight": "model-00016-of-00029.safetensors",
356
+ "model.layers.43.self_attn.o_proj.weight": "model-00016-of-00029.safetensors",
357
+ "model.layers.43.self_attn.q_proj.weight": "model-00016-of-00029.safetensors",
358
+ "model.layers.43.self_attn.v_proj.weight": "model-00016-of-00029.safetensors",
359
+ "model.layers.44.input_layernorm.weight": "model-00017-of-00029.safetensors",
360
+ "model.layers.44.mlp.down_proj.weight": "model-00017-of-00029.safetensors",
361
+ "model.layers.44.mlp.gate_proj.weight": "model-00016-of-00029.safetensors",
362
+ "model.layers.44.mlp.up_proj.weight": "model-00017-of-00029.safetensors",
363
+ "model.layers.44.post_attention_layernorm.weight": "model-00017-of-00029.safetensors",
364
+ "model.layers.44.self_attn.k_proj.weight": "model-00016-of-00029.safetensors",
365
+ "model.layers.44.self_attn.o_proj.weight": "model-00016-of-00029.safetensors",
366
+ "model.layers.44.self_attn.q_proj.weight": "model-00016-of-00029.safetensors",
367
+ "model.layers.44.self_attn.v_proj.weight": "model-00016-of-00029.safetensors",
368
+ "model.layers.45.input_layernorm.weight": "model-00017-of-00029.safetensors",
369
+ "model.layers.45.mlp.down_proj.weight": "model-00017-of-00029.safetensors",
370
+ "model.layers.45.mlp.gate_proj.weight": "model-00017-of-00029.safetensors",
371
+ "model.layers.45.mlp.up_proj.weight": "model-00017-of-00029.safetensors",
372
+ "model.layers.45.post_attention_layernorm.weight": "model-00017-of-00029.safetensors",
373
+ "model.layers.45.self_attn.k_proj.weight": "model-00017-of-00029.safetensors",
374
+ "model.layers.45.self_attn.o_proj.weight": "model-00017-of-00029.safetensors",
375
+ "model.layers.45.self_attn.q_proj.weight": "model-00017-of-00029.safetensors",
376
+ "model.layers.45.self_attn.v_proj.weight": "model-00017-of-00029.safetensors",
377
+ "model.layers.46.input_layernorm.weight": "model-00017-of-00029.safetensors",
378
+ "model.layers.46.mlp.down_proj.weight": "model-00017-of-00029.safetensors",
379
+ "model.layers.46.mlp.gate_proj.weight": "model-00017-of-00029.safetensors",
380
+ "model.layers.46.mlp.up_proj.weight": "model-00017-of-00029.safetensors",
381
+ "model.layers.46.post_attention_layernorm.weight": "model-00017-of-00029.safetensors",
382
+ "model.layers.46.self_attn.k_proj.weight": "model-00017-of-00029.safetensors",
383
+ "model.layers.46.self_attn.o_proj.weight": "model-00017-of-00029.safetensors",
384
+ "model.layers.46.self_attn.q_proj.weight": "model-00017-of-00029.safetensors",
385
+ "model.layers.46.self_attn.v_proj.weight": "model-00017-of-00029.safetensors",
386
+ "model.layers.47.input_layernorm.weight": "model-00018-of-00029.safetensors",
387
+ "model.layers.47.mlp.down_proj.weight": "model-00018-of-00029.safetensors",
388
+ "model.layers.47.mlp.gate_proj.weight": "model-00018-of-00029.safetensors",
389
+ "model.layers.47.mlp.up_proj.weight": "model-00018-of-00029.safetensors",
390
+ "model.layers.47.post_attention_layernorm.weight": "model-00018-of-00029.safetensors",
391
+ "model.layers.47.self_attn.k_proj.weight": "model-00017-of-00029.safetensors",
392
+ "model.layers.47.self_attn.o_proj.weight": "model-00017-of-00029.safetensors",
393
+ "model.layers.47.self_attn.q_proj.weight": "model-00017-of-00029.safetensors",
394
+ "model.layers.47.self_attn.v_proj.weight": "model-00017-of-00029.safetensors",
395
+ "model.layers.48.input_layernorm.weight": "model-00018-of-00029.safetensors",
396
+ "model.layers.48.mlp.down_proj.weight": "model-00018-of-00029.safetensors",
397
+ "model.layers.48.mlp.gate_proj.weight": "model-00018-of-00029.safetensors",
398
+ "model.layers.48.mlp.up_proj.weight": "model-00018-of-00029.safetensors",
399
+ "model.layers.48.post_attention_layernorm.weight": "model-00018-of-00029.safetensors",
400
+ "model.layers.48.self_attn.k_proj.weight": "model-00018-of-00029.safetensors",
401
+ "model.layers.48.self_attn.o_proj.weight": "model-00018-of-00029.safetensors",
402
+ "model.layers.48.self_attn.q_proj.weight": "model-00018-of-00029.safetensors",
403
+ "model.layers.48.self_attn.v_proj.weight": "model-00018-of-00029.safetensors",
404
+ "model.layers.49.input_layernorm.weight": "model-00018-of-00029.safetensors",
405
+ "model.layers.49.mlp.down_proj.weight": "model-00018-of-00029.safetensors",
406
+ "model.layers.49.mlp.gate_proj.weight": "model-00018-of-00029.safetensors",
407
+ "model.layers.49.mlp.up_proj.weight": "model-00018-of-00029.safetensors",
408
+ "model.layers.49.post_attention_layernorm.weight": "model-00018-of-00029.safetensors",
409
+ "model.layers.49.self_attn.k_proj.weight": "model-00018-of-00029.safetensors",
410
+ "model.layers.49.self_attn.o_proj.weight": "model-00018-of-00029.safetensors",
411
+ "model.layers.49.self_attn.q_proj.weight": "model-00018-of-00029.safetensors",
412
+ "model.layers.49.self_attn.v_proj.weight": "model-00018-of-00029.safetensors",
413
+ "model.layers.5.input_layernorm.weight": "model-00003-of-00029.safetensors",
414
+ "model.layers.5.mlp.down_proj.weight": "model-00003-of-00029.safetensors",
415
+ "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00029.safetensors",
416
+ "model.layers.5.mlp.up_proj.weight": "model-00003-of-00029.safetensors",
417
+ "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00029.safetensors",
418
+ "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00029.safetensors",
419
+ "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00029.safetensors",
420
+ "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00029.safetensors",
421
+ "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00029.safetensors",
422
+ "model.layers.50.input_layernorm.weight": "model-00019-of-00029.safetensors",
423
+ "model.layers.50.mlp.down_proj.weight": "model-00019-of-00029.safetensors",
424
+ "model.layers.50.mlp.gate_proj.weight": "model-00019-of-00029.safetensors",
425
+ "model.layers.50.mlp.up_proj.weight": "model-00019-of-00029.safetensors",
426
+ "model.layers.50.post_attention_layernorm.weight": "model-00019-of-00029.safetensors",
427
+ "model.layers.50.self_attn.k_proj.weight": "model-00018-of-00029.safetensors",
428
+ "model.layers.50.self_attn.o_proj.weight": "model-00019-of-00029.safetensors",
429
+ "model.layers.50.self_attn.q_proj.weight": "model-00018-of-00029.safetensors",
430
+ "model.layers.50.self_attn.v_proj.weight": "model-00018-of-00029.safetensors",
431
+ "model.layers.51.input_layernorm.weight": "model-00019-of-00029.safetensors",
432
+ "model.layers.51.mlp.down_proj.weight": "model-00019-of-00029.safetensors",
433
+ "model.layers.51.mlp.gate_proj.weight": "model-00019-of-00029.safetensors",
434
+ "model.layers.51.mlp.up_proj.weight": "model-00019-of-00029.safetensors",
435
+ "model.layers.51.post_attention_layernorm.weight": "model-00019-of-00029.safetensors",
436
+ "model.layers.51.self_attn.k_proj.weight": "model-00019-of-00029.safetensors",
437
+ "model.layers.51.self_attn.o_proj.weight": "model-00019-of-00029.safetensors",
438
+ "model.layers.51.self_attn.q_proj.weight": "model-00019-of-00029.safetensors",
439
+ "model.layers.51.self_attn.v_proj.weight": "model-00019-of-00029.safetensors",
440
+ "model.layers.52.input_layernorm.weight": "model-00019-of-00029.safetensors",
441
+ "model.layers.52.mlp.down_proj.weight": "model-00019-of-00029.safetensors",
442
+ "model.layers.52.mlp.gate_proj.weight": "model-00019-of-00029.safetensors",
443
+ "model.layers.52.mlp.up_proj.weight": "model-00019-of-00029.safetensors",
444
+ "model.layers.52.post_attention_layernorm.weight": "model-00019-of-00029.safetensors",
445
+ "model.layers.52.self_attn.k_proj.weight": "model-00019-of-00029.safetensors",
446
+ "model.layers.52.self_attn.o_proj.weight": "model-00019-of-00029.safetensors",
447
+ "model.layers.52.self_attn.q_proj.weight": "model-00019-of-00029.safetensors",
448
+ "model.layers.52.self_attn.v_proj.weight": "model-00019-of-00029.safetensors",
449
+ "model.layers.53.input_layernorm.weight": "model-00020-of-00029.safetensors",
450
+ "model.layers.53.mlp.down_proj.weight": "model-00020-of-00029.safetensors",
451
+ "model.layers.53.mlp.gate_proj.weight": "model-00020-of-00029.safetensors",
452
+ "model.layers.53.mlp.up_proj.weight": "model-00020-of-00029.safetensors",
453
+ "model.layers.53.post_attention_layernorm.weight": "model-00020-of-00029.safetensors",
454
+ "model.layers.53.self_attn.k_proj.weight": "model-00020-of-00029.safetensors",
455
+ "model.layers.53.self_attn.o_proj.weight": "model-00020-of-00029.safetensors",
456
+ "model.layers.53.self_attn.q_proj.weight": "model-00020-of-00029.safetensors",
457
+ "model.layers.53.self_attn.v_proj.weight": "model-00020-of-00029.safetensors",
458
+ "model.layers.54.input_layernorm.weight": "model-00020-of-00029.safetensors",
459
+ "model.layers.54.mlp.down_proj.weight": "model-00020-of-00029.safetensors",
460
+ "model.layers.54.mlp.gate_proj.weight": "model-00020-of-00029.safetensors",
461
+ "model.layers.54.mlp.up_proj.weight": "model-00020-of-00029.safetensors",
462
+ "model.layers.54.post_attention_layernorm.weight": "model-00020-of-00029.safetensors",
463
+ "model.layers.54.self_attn.k_proj.weight": "model-00020-of-00029.safetensors",
464
+ "model.layers.54.self_attn.o_proj.weight": "model-00020-of-00029.safetensors",
465
+ "model.layers.54.self_attn.q_proj.weight": "model-00020-of-00029.safetensors",
466
+ "model.layers.54.self_attn.v_proj.weight": "model-00020-of-00029.safetensors",
467
+ "model.layers.55.input_layernorm.weight": "model-00021-of-00029.safetensors",
468
+ "model.layers.55.mlp.down_proj.weight": "model-00021-of-00029.safetensors",
469
+ "model.layers.55.mlp.gate_proj.weight": "model-00020-of-00029.safetensors",
470
+ "model.layers.55.mlp.up_proj.weight": "model-00020-of-00029.safetensors",
471
+ "model.layers.55.post_attention_layernorm.weight": "model-00021-of-00029.safetensors",
472
+ "model.layers.55.self_attn.k_proj.weight": "model-00020-of-00029.safetensors",
473
+ "model.layers.55.self_attn.o_proj.weight": "model-00020-of-00029.safetensors",
474
+ "model.layers.55.self_attn.q_proj.weight": "model-00020-of-00029.safetensors",
475
+ "model.layers.55.self_attn.v_proj.weight": "model-00020-of-00029.safetensors",
476
+ "model.layers.56.input_layernorm.weight": "model-00021-of-00029.safetensors",
477
+ "model.layers.56.mlp.down_proj.weight": "model-00021-of-00029.safetensors",
478
+ "model.layers.56.mlp.gate_proj.weight": "model-00021-of-00029.safetensors",
479
+ "model.layers.56.mlp.up_proj.weight": "model-00021-of-00029.safetensors",
480
+ "model.layers.56.post_attention_layernorm.weight": "model-00021-of-00029.safetensors",
481
+ "model.layers.56.self_attn.k_proj.weight": "model-00021-of-00029.safetensors",
482
+ "model.layers.56.self_attn.o_proj.weight": "model-00021-of-00029.safetensors",
483
+ "model.layers.56.self_attn.q_proj.weight": "model-00021-of-00029.safetensors",
484
+ "model.layers.56.self_attn.v_proj.weight": "model-00021-of-00029.safetensors",
485
+ "model.layers.57.input_layernorm.weight": "model-00021-of-00029.safetensors",
486
+ "model.layers.57.mlp.down_proj.weight": "model-00021-of-00029.safetensors",
487
+ "model.layers.57.mlp.gate_proj.weight": "model-00021-of-00029.safetensors",
488
+ "model.layers.57.mlp.up_proj.weight": "model-00021-of-00029.safetensors",
489
+ "model.layers.57.post_attention_layernorm.weight": "model-00021-of-00029.safetensors",
490
+ "model.layers.57.self_attn.k_proj.weight": "model-00021-of-00029.safetensors",
491
+ "model.layers.57.self_attn.o_proj.weight": "model-00021-of-00029.safetensors",
492
+ "model.layers.57.self_attn.q_proj.weight": "model-00021-of-00029.safetensors",
493
+ "model.layers.57.self_attn.v_proj.weight": "model-00021-of-00029.safetensors",
494
+ "model.layers.58.input_layernorm.weight": "model-00022-of-00029.safetensors",
495
+ "model.layers.58.mlp.down_proj.weight": "model-00022-of-00029.safetensors",
496
+ "model.layers.58.mlp.gate_proj.weight": "model-00021-of-00029.safetensors",
497
+ "model.layers.58.mlp.up_proj.weight": "model-00022-of-00029.safetensors",
498
+ "model.layers.58.post_attention_layernorm.weight": "model-00022-of-00029.safetensors",
499
+ "model.layers.58.self_attn.k_proj.weight": "model-00021-of-00029.safetensors",
500
+ "model.layers.58.self_attn.o_proj.weight": "model-00021-of-00029.safetensors",
501
+ "model.layers.58.self_attn.q_proj.weight": "model-00021-of-00029.safetensors",
502
+ "model.layers.58.self_attn.v_proj.weight": "model-00021-of-00029.safetensors",
503
+ "model.layers.59.input_layernorm.weight": "model-00022-of-00029.safetensors",
504
+ "model.layers.59.mlp.down_proj.weight": "model-00022-of-00029.safetensors",
505
+ "model.layers.59.mlp.gate_proj.weight": "model-00022-of-00029.safetensors",
506
+ "model.layers.59.mlp.up_proj.weight": "model-00022-of-00029.safetensors",
507
+ "model.layers.59.post_attention_layernorm.weight": "model-00022-of-00029.safetensors",
508
+ "model.layers.59.self_attn.k_proj.weight": "model-00022-of-00029.safetensors",
509
+ "model.layers.59.self_attn.o_proj.weight": "model-00022-of-00029.safetensors",
510
+ "model.layers.59.self_attn.q_proj.weight": "model-00022-of-00029.safetensors",
511
+ "model.layers.59.self_attn.v_proj.weight": "model-00022-of-00029.safetensors",
512
+ "model.layers.6.input_layernorm.weight": "model-00003-of-00029.safetensors",
513
+ "model.layers.6.mlp.down_proj.weight": "model-00003-of-00029.safetensors",
514
+ "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00029.safetensors",
515
+ "model.layers.6.mlp.up_proj.weight": "model-00003-of-00029.safetensors",
516
+ "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00029.safetensors",
517
+ "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00029.safetensors",
518
+ "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00029.safetensors",
519
+ "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00029.safetensors",
520
+ "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00029.safetensors",
521
+ "model.layers.60.input_layernorm.weight": "model-00022-of-00029.safetensors",
522
+ "model.layers.60.mlp.down_proj.weight": "model-00022-of-00029.safetensors",
523
+ "model.layers.60.mlp.gate_proj.weight": "model-00022-of-00029.safetensors",
524
+ "model.layers.60.mlp.up_proj.weight": "model-00022-of-00029.safetensors",
525
+ "model.layers.60.post_attention_layernorm.weight": "model-00022-of-00029.safetensors",
526
+ "model.layers.60.self_attn.k_proj.weight": "model-00022-of-00029.safetensors",
527
+ "model.layers.60.self_attn.o_proj.weight": "model-00022-of-00029.safetensors",
528
+ "model.layers.60.self_attn.q_proj.weight": "model-00022-of-00029.safetensors",
529
+ "model.layers.60.self_attn.v_proj.weight": "model-00022-of-00029.safetensors",
530
+ "model.layers.61.input_layernorm.weight": "model-00023-of-00029.safetensors",
531
+ "model.layers.61.mlp.down_proj.weight": "model-00023-of-00029.safetensors",
532
+ "model.layers.61.mlp.gate_proj.weight": "model-00023-of-00029.safetensors",
533
+ "model.layers.61.mlp.up_proj.weight": "model-00023-of-00029.safetensors",
534
+ "model.layers.61.post_attention_layernorm.weight": "model-00023-of-00029.safetensors",
535
+ "model.layers.61.self_attn.k_proj.weight": "model-00022-of-00029.safetensors",
536
+ "model.layers.61.self_attn.o_proj.weight": "model-00022-of-00029.safetensors",
537
+ "model.layers.61.self_attn.q_proj.weight": "model-00022-of-00029.safetensors",
538
+ "model.layers.61.self_attn.v_proj.weight": "model-00022-of-00029.safetensors",
539
+ "model.layers.62.input_layernorm.weight": "model-00023-of-00029.safetensors",
540
+ "model.layers.62.mlp.down_proj.weight": "model-00023-of-00029.safetensors",
541
+ "model.layers.62.mlp.gate_proj.weight": "model-00023-of-00029.safetensors",
542
+ "model.layers.62.mlp.up_proj.weight": "model-00023-of-00029.safetensors",
543
+ "model.layers.62.post_attention_layernorm.weight": "model-00023-of-00029.safetensors",
544
+ "model.layers.62.self_attn.k_proj.weight": "model-00023-of-00029.safetensors",
545
+ "model.layers.62.self_attn.o_proj.weight": "model-00023-of-00029.safetensors",
546
+ "model.layers.62.self_attn.q_proj.weight": "model-00023-of-00029.safetensors",
547
+ "model.layers.62.self_attn.v_proj.weight": "model-00023-of-00029.safetensors",
548
+ "model.layers.63.input_layernorm.weight": "model-00023-of-00029.safetensors",
549
+ "model.layers.63.mlp.down_proj.weight": "model-00023-of-00029.safetensors",
550
+ "model.layers.63.mlp.gate_proj.weight": "model-00023-of-00029.safetensors",
551
+ "model.layers.63.mlp.up_proj.weight": "model-00023-of-00029.safetensors",
552
+ "model.layers.63.post_attention_layernorm.weight": "model-00023-of-00029.safetensors",
553
+ "model.layers.63.self_attn.k_proj.weight": "model-00023-of-00029.safetensors",
554
+ "model.layers.63.self_attn.o_proj.weight": "model-00023-of-00029.safetensors",
555
+ "model.layers.63.self_attn.q_proj.weight": "model-00023-of-00029.safetensors",
556
+ "model.layers.63.self_attn.v_proj.weight": "model-00023-of-00029.safetensors",
557
+ "model.layers.64.input_layernorm.weight": "model-00024-of-00029.safetensors",
558
+ "model.layers.64.mlp.down_proj.weight": "model-00024-of-00029.safetensors",
559
+ "model.layers.64.mlp.gate_proj.weight": "model-00024-of-00029.safetensors",
560
+ "model.layers.64.mlp.up_proj.weight": "model-00024-of-00029.safetensors",
561
+ "model.layers.64.post_attention_layernorm.weight": "model-00024-of-00029.safetensors",
562
+ "model.layers.64.self_attn.k_proj.weight": "model-00023-of-00029.safetensors",
563
+ "model.layers.64.self_attn.o_proj.weight": "model-00024-of-00029.safetensors",
564
+ "model.layers.64.self_attn.q_proj.weight": "model-00023-of-00029.safetensors",
565
+ "model.layers.64.self_attn.v_proj.weight": "model-00023-of-00029.safetensors",
566
+ "model.layers.65.input_layernorm.weight": "model-00024-of-00029.safetensors",
567
+ "model.layers.65.mlp.down_proj.weight": "model-00024-of-00029.safetensors",
568
+ "model.layers.65.mlp.gate_proj.weight": "model-00024-of-00029.safetensors",
569
+ "model.layers.65.mlp.up_proj.weight": "model-00024-of-00029.safetensors",
570
+ "model.layers.65.post_attention_layernorm.weight": "model-00024-of-00029.safetensors",
571
+ "model.layers.65.self_attn.k_proj.weight": "model-00024-of-00029.safetensors",
572
+ "model.layers.65.self_attn.o_proj.weight": "model-00024-of-00029.safetensors",
573
+ "model.layers.65.self_attn.q_proj.weight": "model-00024-of-00029.safetensors",
574
+ "model.layers.65.self_attn.v_proj.weight": "model-00024-of-00029.safetensors",
575
+ "model.layers.66.input_layernorm.weight": "model-00024-of-00029.safetensors",
576
+ "model.layers.66.mlp.down_proj.weight": "model-00024-of-00029.safetensors",
577
+ "model.layers.66.mlp.gate_proj.weight": "model-00024-of-00029.safetensors",
578
+ "model.layers.66.mlp.up_proj.weight": "model-00024-of-00029.safetensors",
579
+ "model.layers.66.post_attention_layernorm.weight": "model-00024-of-00029.safetensors",
580
+ "model.layers.66.self_attn.k_proj.weight": "model-00024-of-00029.safetensors",
581
+ "model.layers.66.self_attn.o_proj.weight": "model-00024-of-00029.safetensors",
582
+ "model.layers.66.self_attn.q_proj.weight": "model-00024-of-00029.safetensors",
583
+ "model.layers.66.self_attn.v_proj.weight": "model-00024-of-00029.safetensors",
584
+ "model.layers.67.input_layernorm.weight": "model-00025-of-00029.safetensors",
585
+ "model.layers.67.mlp.down_proj.weight": "model-00025-of-00029.safetensors",
586
+ "model.layers.67.mlp.gate_proj.weight": "model-00025-of-00029.safetensors",
587
+ "model.layers.67.mlp.up_proj.weight": "model-00025-of-00029.safetensors",
588
+ "model.layers.67.post_attention_layernorm.weight": "model-00025-of-00029.safetensors",
589
+ "model.layers.67.self_attn.k_proj.weight": "model-00025-of-00029.safetensors",
590
+ "model.layers.67.self_attn.o_proj.weight": "model-00025-of-00029.safetensors",
591
+ "model.layers.67.self_attn.q_proj.weight": "model-00025-of-00029.safetensors",
592
+ "model.layers.67.self_attn.v_proj.weight": "model-00025-of-00029.safetensors",
593
+ "model.layers.68.input_layernorm.weight": "model-00025-of-00029.safetensors",
594
+ "model.layers.68.mlp.down_proj.weight": "model-00025-of-00029.safetensors",
595
+ "model.layers.68.mlp.gate_proj.weight": "model-00025-of-00029.safetensors",
596
+ "model.layers.68.mlp.up_proj.weight": "model-00025-of-00029.safetensors",
597
+ "model.layers.68.post_attention_layernorm.weight": "model-00025-of-00029.safetensors",
598
+ "model.layers.68.self_attn.k_proj.weight": "model-00025-of-00029.safetensors",
599
+ "model.layers.68.self_attn.o_proj.weight": "model-00025-of-00029.safetensors",
600
+ "model.layers.68.self_attn.q_proj.weight": "model-00025-of-00029.safetensors",
601
+ "model.layers.68.self_attn.v_proj.weight": "model-00025-of-00029.safetensors",
602
+ "model.layers.69.input_layernorm.weight": "model-00026-of-00029.safetensors",
603
+ "model.layers.69.mlp.down_proj.weight": "model-00026-of-00029.safetensors",
604
+ "model.layers.69.mlp.gate_proj.weight": "model-00025-of-00029.safetensors",
605
+ "model.layers.69.mlp.up_proj.weight": "model-00025-of-00029.safetensors",
606
+ "model.layers.69.post_attention_layernorm.weight": "model-00026-of-00029.safetensors",
607
+ "model.layers.69.self_attn.k_proj.weight": "model-00025-of-00029.safetensors",
608
+ "model.layers.69.self_attn.o_proj.weight": "model-00025-of-00029.safetensors",
609
+ "model.layers.69.self_attn.q_proj.weight": "model-00025-of-00029.safetensors",
610
+ "model.layers.69.self_attn.v_proj.weight": "model-00025-of-00029.safetensors",
611
+ "model.layers.7.input_layernorm.weight": "model-00003-of-00029.safetensors",
612
+ "model.layers.7.mlp.down_proj.weight": "model-00003-of-00029.safetensors",
613
+ "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00029.safetensors",
614
+ "model.layers.7.mlp.up_proj.weight": "model-00003-of-00029.safetensors",
615
+ "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00029.safetensors",
616
+ "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00029.safetensors",
617
+ "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00029.safetensors",
618
+ "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00029.safetensors",
619
+ "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00029.safetensors",
620
+ "model.layers.70.input_layernorm.weight": "model-00026-of-00029.safetensors",
621
+ "model.layers.70.mlp.down_proj.weight": "model-00026-of-00029.safetensors",
622
+ "model.layers.70.mlp.gate_proj.weight": "model-00026-of-00029.safetensors",
623
+ "model.layers.70.mlp.up_proj.weight": "model-00026-of-00029.safetensors",
624
+ "model.layers.70.post_attention_layernorm.weight": "model-00026-of-00029.safetensors",
625
+ "model.layers.70.self_attn.k_proj.weight": "model-00026-of-00029.safetensors",
626
+ "model.layers.70.self_attn.o_proj.weight": "model-00026-of-00029.safetensors",
627
+ "model.layers.70.self_attn.q_proj.weight": "model-00026-of-00029.safetensors",
628
+ "model.layers.70.self_attn.v_proj.weight": "model-00026-of-00029.safetensors",
629
+ "model.layers.71.input_layernorm.weight": "model-00026-of-00029.safetensors",
630
+ "model.layers.71.mlp.down_proj.weight": "model-00026-of-00029.safetensors",
631
+ "model.layers.71.mlp.gate_proj.weight": "model-00026-of-00029.safetensors",
632
+ "model.layers.71.mlp.up_proj.weight": "model-00026-of-00029.safetensors",
633
+ "model.layers.71.post_attention_layernorm.weight": "model-00026-of-00029.safetensors",
634
+ "model.layers.71.self_attn.k_proj.weight": "model-00026-of-00029.safetensors",
635
+ "model.layers.71.self_attn.o_proj.weight": "model-00026-of-00029.safetensors",
636
+ "model.layers.71.self_attn.q_proj.weight": "model-00026-of-00029.safetensors",
637
+ "model.layers.71.self_attn.v_proj.weight": "model-00026-of-00029.safetensors",
638
+ "model.layers.72.input_layernorm.weight": "model-00027-of-00029.safetensors",
639
+ "model.layers.72.mlp.down_proj.weight": "model-00027-of-00029.safetensors",
640
+ "model.layers.72.mlp.gate_proj.weight": "model-00026-of-00029.safetensors",
641
+ "model.layers.72.mlp.up_proj.weight": "model-00027-of-00029.safetensors",
642
+ "model.layers.72.post_attention_layernorm.weight": "model-00027-of-00029.safetensors",
643
+ "model.layers.72.self_attn.k_proj.weight": "model-00026-of-00029.safetensors",
644
+ "model.layers.72.self_attn.o_proj.weight": "model-00026-of-00029.safetensors",
645
+ "model.layers.72.self_attn.q_proj.weight": "model-00026-of-00029.safetensors",
646
+ "model.layers.72.self_attn.v_proj.weight": "model-00026-of-00029.safetensors",
647
+ "model.layers.73.input_layernorm.weight": "model-00027-of-00029.safetensors",
648
+ "model.layers.73.mlp.down_proj.weight": "model-00027-of-00029.safetensors",
649
+ "model.layers.73.mlp.gate_proj.weight": "model-00027-of-00029.safetensors",
650
+ "model.layers.73.mlp.up_proj.weight": "model-00027-of-00029.safetensors",
651
+ "model.layers.73.post_attention_layernorm.weight": "model-00027-of-00029.safetensors",
652
+ "model.layers.73.self_attn.k_proj.weight": "model-00027-of-00029.safetensors",
653
+ "model.layers.73.self_attn.o_proj.weight": "model-00027-of-00029.safetensors",
654
+ "model.layers.73.self_attn.q_proj.weight": "model-00027-of-00029.safetensors",
655
+ "model.layers.73.self_attn.v_proj.weight": "model-00027-of-00029.safetensors",
656
+ "model.layers.74.input_layernorm.weight": "model-00027-of-00029.safetensors",
657
+ "model.layers.74.mlp.down_proj.weight": "model-00027-of-00029.safetensors",
658
+ "model.layers.74.mlp.gate_proj.weight": "model-00027-of-00029.safetensors",
659
+ "model.layers.74.mlp.up_proj.weight": "model-00027-of-00029.safetensors",
660
+ "model.layers.74.post_attention_layernorm.weight": "model-00027-of-00029.safetensors",
661
+ "model.layers.74.self_attn.k_proj.weight": "model-00027-of-00029.safetensors",
662
+ "model.layers.74.self_attn.o_proj.weight": "model-00027-of-00029.safetensors",
663
+ "model.layers.74.self_attn.q_proj.weight": "model-00027-of-00029.safetensors",
664
+ "model.layers.74.self_attn.v_proj.weight": "model-00027-of-00029.safetensors",
665
+ "model.layers.75.input_layernorm.weight": "model-00028-of-00029.safetensors",
666
+ "model.layers.75.mlp.down_proj.weight": "model-00028-of-00029.safetensors",
667
+ "model.layers.75.mlp.gate_proj.weight": "model-00028-of-00029.safetensors",
668
+ "model.layers.75.mlp.up_proj.weight": "model-00028-of-00029.safetensors",
669
+ "model.layers.75.post_attention_layernorm.weight": "model-00028-of-00029.safetensors",
670
+ "model.layers.75.self_attn.k_proj.weight": "model-00027-of-00029.safetensors",
671
+ "model.layers.75.self_attn.o_proj.weight": "model-00027-of-00029.safetensors",
672
+ "model.layers.75.self_attn.q_proj.weight": "model-00027-of-00029.safetensors",
673
+ "model.layers.75.self_attn.v_proj.weight": "model-00027-of-00029.safetensors",
674
+ "model.layers.76.input_layernorm.weight": "model-00028-of-00029.safetensors",
675
+ "model.layers.76.mlp.down_proj.weight": "model-00028-of-00029.safetensors",
676
+ "model.layers.76.mlp.gate_proj.weight": "model-00028-of-00029.safetensors",
677
+ "model.layers.76.mlp.up_proj.weight": "model-00028-of-00029.safetensors",
678
+ "model.layers.76.post_attention_layernorm.weight": "model-00028-of-00029.safetensors",
679
+ "model.layers.76.self_attn.k_proj.weight": "model-00028-of-00029.safetensors",
680
+ "model.layers.76.self_attn.o_proj.weight": "model-00028-of-00029.safetensors",
681
+ "model.layers.76.self_attn.q_proj.weight": "model-00028-of-00029.safetensors",
682
+ "model.layers.76.self_attn.v_proj.weight": "model-00028-of-00029.safetensors",
683
+ "model.layers.77.input_layernorm.weight": "model-00028-of-00029.safetensors",
684
+ "model.layers.77.mlp.down_proj.weight": "model-00028-of-00029.safetensors",
685
+ "model.layers.77.mlp.gate_proj.weight": "model-00028-of-00029.safetensors",
686
+ "model.layers.77.mlp.up_proj.weight": "model-00028-of-00029.safetensors",
687
+ "model.layers.77.post_attention_layernorm.weight": "model-00028-of-00029.safetensors",
688
+ "model.layers.77.self_attn.k_proj.weight": "model-00028-of-00029.safetensors",
689
+ "model.layers.77.self_attn.o_proj.weight": "model-00028-of-00029.safetensors",
690
+ "model.layers.77.self_attn.q_proj.weight": "model-00028-of-00029.safetensors",
691
+ "model.layers.77.self_attn.v_proj.weight": "model-00028-of-00029.safetensors",
692
+ "model.layers.78.input_layernorm.weight": "model-00029-of-00029.safetensors",
693
+ "model.layers.78.mlp.down_proj.weight": "model-00029-of-00029.safetensors",
694
+ "model.layers.78.mlp.gate_proj.weight": "model-00029-of-00029.safetensors",
695
+ "model.layers.78.mlp.up_proj.weight": "model-00029-of-00029.safetensors",
696
+ "model.layers.78.post_attention_layernorm.weight": "model-00029-of-00029.safetensors",
697
+ "model.layers.78.self_attn.k_proj.weight": "model-00028-of-00029.safetensors",
698
+ "model.layers.78.self_attn.o_proj.weight": "model-00029-of-00029.safetensors",
699
+ "model.layers.78.self_attn.q_proj.weight": "model-00028-of-00029.safetensors",
700
+ "model.layers.78.self_attn.v_proj.weight": "model-00028-of-00029.safetensors",
701
+ "model.layers.79.input_layernorm.weight": "model-00029-of-00029.safetensors",
702
+ "model.layers.79.mlp.down_proj.weight": "model-00029-of-00029.safetensors",
703
+ "model.layers.79.mlp.gate_proj.weight": "model-00029-of-00029.safetensors",
704
+ "model.layers.79.mlp.up_proj.weight": "model-00029-of-00029.safetensors",
705
+ "model.layers.79.post_attention_layernorm.weight": "model-00029-of-00029.safetensors",
706
+ "model.layers.79.self_attn.k_proj.weight": "model-00029-of-00029.safetensors",
707
+ "model.layers.79.self_attn.o_proj.weight": "model-00029-of-00029.safetensors",
708
+ "model.layers.79.self_attn.q_proj.weight": "model-00029-of-00029.safetensors",
709
+ "model.layers.79.self_attn.v_proj.weight": "model-00029-of-00029.safetensors",
710
+ "model.layers.8.input_layernorm.weight": "model-00004-of-00029.safetensors",
711
+ "model.layers.8.mlp.down_proj.weight": "model-00004-of-00029.safetensors",
712
+ "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00029.safetensors",
713
+ "model.layers.8.mlp.up_proj.weight": "model-00004-of-00029.safetensors",
714
+ "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00029.safetensors",
715
+ "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00029.safetensors",
716
+ "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00029.safetensors",
717
+ "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00029.safetensors",
718
+ "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00029.safetensors",
719
+ "model.layers.9.input_layernorm.weight": "model-00004-of-00029.safetensors",
720
+ "model.layers.9.mlp.down_proj.weight": "model-00004-of-00029.safetensors",
721
+ "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00029.safetensors",
722
+ "model.layers.9.mlp.up_proj.weight": "model-00004-of-00029.safetensors",
723
+ "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00029.safetensors",
724
+ "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00029.safetensors",
725
+ "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00029.safetensors",
726
+ "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00029.safetensors",
727
+ "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00029.safetensors",
728
+ "model.norm.weight": "model-00029-of-00029.safetensors"
729
+ }
730
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<pad>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "32000": {
30
+ "content": "<pad>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ }
37
+ },
38
+ "bos_token": "<s>",
39
+ "clean_up_tokenization_spaces": false,
40
+ "eos_token": "</s>",
41
+ "legacy": false,
42
+ "model_max_length": 1000000000000000019884624838656,
43
+ "pad_token": "<pad>",
44
+ "padding_side": "right",
45
+ "sp_model_kwargs": {},
46
+ "spaces_between_special_tokens": false,
47
+ "tokenizer_class": "LlamaTokenizer",
48
+ "trust_remote_code": false,
49
+ "unk_token": "<unk>",
50
+ "use_default_system_prompt": false,
51
+ "use_fast": true
52
+ }