Hugging Face's logo

thrunlab
/
sparse_sparse_80_percent_pretraining_warmup_20K_steps_5k

Text Generation
Transformers
Safetensors
mistral
Generated from Trainer
Inference Endpoints
text-generation-inference
Model card Files Community
lukeleeai commited on
Commit
759985a
•
1 Parent(s): 564ceb7

End of training

Browse files
Files changed (7) hide show
  1. README.md +99 -0
  2. config.json +25 -0
  3. generation_config.json +6 -0
  4. model-00001-of-00003.safetensors +3 -0
  5. model-00002-of-00003.safetensors +3 -0
  6. model-00003-of-00003.safetensors +3 -0
  7. model.safetensors.index.json +298 -0
README.md ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: mistralai/Mistral-7B-Instruct-v0.1
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - openwebtext
8
+ model-index:
9
+ - name: sparse_sparse_80_percent_pretraining_warmup_20K_steps_5k
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # sparse_sparse_80_percent_pretraining_warmup_20K_steps_5k
17
+
18
+ This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on the openwebtext dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.7590
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 1e-05
40
+ - train_batch_size: 8
41
+ - eval_batch_size: 16
42
+ - seed: 0
43
+ - distributed_type: multi-GPU
44
+ - num_devices: 6
45
+ - gradient_accumulation_steps: 2
46
+ - total_train_batch_size: 96
47
+ - total_eval_batch_size: 96
48
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
+ - lr_scheduler_type: linear
50
+ - training_steps: 5000
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss |
55
+ |:-------------:|:-----:|:----:|:---------------:|
56
+ | 1.2712 | 0.05 | 50 | 1.2374 |
57
+ | 1.0533 | 0.1 | 100 | 1.0529 |
58
+ | 0.9603 | 0.15 | 150 | 0.9668 |
59
+ | 0.9102 | 0.19 | 200 | 0.9145 |
60
+ | 0.8754 | 0.24 | 250 | 0.8775 |
61
+ | 0.8514 | 0.29 | 300 | 0.8503 |
62
+ | 0.8417 | 0.34 | 350 | 0.8298 |
63
+ | 0.8217 | 0.39 | 400 | 0.8146 |
64
+ | 0.8019 | 0.44 | 450 | 0.8026 |
65
+ | 0.7902 | 0.48 | 500 | 0.7914 |
66
+ | 0.7856 | 0.53 | 550 | 0.7819 |
67
+ | 0.7599 | 0.58 | 600 | 0.7734 |
68
+ | 0.7646 | 0.63 | 650 | 0.7689 |
69
+ | 0.7542 | 0.68 | 700 | 0.7635 |
70
+ | 0.7529 | 0.73 | 750 | 0.7581 |
71
+ | 0.7594 | 0.78 | 800 | 0.7533 |
72
+ | 0.7489 | 0.82 | 850 | 0.7493 |
73
+ | 0.7494 | 0.87 | 900 | 0.7452 |
74
+ | 0.7441 | 0.92 | 950 | 0.7472 |
75
+ | 0.7467 | 0.97 | 1000 | 0.7442 |
76
+ | 0.728 | 1.02 | 1050 | 0.7413 |
77
+ | 0.7263 | 1.07 | 1100 | 0.7384 |
78
+ | 0.7206 | 1.11 | 1150 | 0.7362 |
79
+ | 0.7223 | 1.16 | 1200 | 0.7343 |
80
+ | 0.7362 | 1.21 | 1250 | 0.7421 |
81
+ | 0.7374 | 1.26 | 1300 | 0.7401 |
82
+ | 0.7284 | 1.31 | 1350 | 0.7378 |
83
+ | 0.7309 | 1.36 | 1400 | 0.7356 |
84
+ | 0.724 | 1.41 | 1450 | 0.7339 |
85
+ | 0.72 | 1.45 | 1500 | 0.7317 |
86
+ | 0.73 | 1.5 | 1550 | 0.7509 |
87
+ | 0.7464 | 1.55 | 1600 | 0.7489 |
88
+ | 0.742 | 1.6 | 1650 | 0.7461 |
89
+ | 0.7378 | 1.65 | 1700 | 0.7447 |
90
+ | 0.7328 | 1.7 | 1750 | 0.7433 |
91
+ | 0.7433 | 1.75 | 1800 | 0.7411 |
92
+
93
+
94
+ ### Framework versions
95
+
96
+ - Transformers 4.35.2
97
+ - Pytorch 2.1.1+cu121
98
+ - Datasets 2.15.0
99
+ - Tokenizers 0.15.0
config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.1",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 4096,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 14336,
12
+ "max_position_embeddings": 32768,
13
+ "model_type": "mistral",
14
+ "num_attention_heads": 32,
15
+ "num_hidden_layers": 32,
16
+ "num_key_value_heads": 8,
17
+ "rms_norm_eps": 1e-05,
18
+ "rope_theta": 10000.0,
19
+ "sliding_window": 4096,
20
+ "tie_word_embeddings": false,
21
+ "torch_dtype": "bfloat16",
22
+ "transformers_version": "4.35.2",
23
+ "use_cache": true,
24
+ "vocab_size": 32000
25
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.35.2"
6
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad5b95d6b3ff6cfa6166341054dc1d4cd6b91bc7dcac03506dc4442436b70c60
3
+ size 4943163992
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a754ac5a48b58fba0bdb138134d98c0cf4c01896cd4a99e3e7b26f1dc3ce20f7
3
+ size 4999821144
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7089b9f2077bf83ad02e8e04251fbd3534e52623fa9324c08c4f28c938af1b98
3
+ size 4540517840
model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 14483464192
4
+ },
5
+ "weight_map": {
6
+ "base_model.model.lm_head.weight": "model-00003-of-00003.safetensors",
7
+ "base_model.model.model.embed_tokens.weight": "model-00001-of-00003.safetensors",
8
+ "base_model.model.model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
9
+ "base_model.model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
10
+ "base_model.model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
11
+ "base_model.model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
12
+ "base_model.model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
13
+ "base_model.model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
14
+ "base_model.model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
15
+ "base_model.model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
16
+ "base_model.model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
17
+ "base_model.model.model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
18
+ "base_model.model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
19
+ "base_model.model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
20
+ "base_model.model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
21
+ "base_model.model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
22
+ "base_model.model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
23
+ "base_model.model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
24
+ "base_model.model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
25
+ "base_model.model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
26
+ "base_model.model.model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
27
+ "base_model.model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
28
+ "base_model.model.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
29
+ "base_model.model.model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
30
+ "base_model.model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
31
+ "base_model.model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
32
+ "base_model.model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
33
+ "base_model.model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
34
+ "base_model.model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
35
+ "base_model.model.model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
36
+ "base_model.model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
37
+ "base_model.model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
38
+ "base_model.model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
39
+ "base_model.model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
40
+ "base_model.model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
41
+ "base_model.model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
42
+ "base_model.model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
43
+ "base_model.model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
44
+ "base_model.model.model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
45
+ "base_model.model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
46
+ "base_model.model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
47
+ "base_model.model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
48
+ "base_model.model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
49
+ "base_model.model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
50
+ "base_model.model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
51
+ "base_model.model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
52
+ "base_model.model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
53
+ "base_model.model.model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
54
+ "base_model.model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
55
+ "base_model.model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
56
+ "base_model.model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
57
+ "base_model.model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
58
+ "base_model.model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
59
+ "base_model.model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
60
+ "base_model.model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
61
+ "base_model.model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
62
+ "base_model.model.model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
63
+ "base_model.model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
64
+ "base_model.model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
65
+ "base_model.model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
66
+ "base_model.model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
67
+ "base_model.model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
68
+ "base_model.model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
69
+ "base_model.model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
70
+ "base_model.model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
71
+ "base_model.model.model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
72
+ "base_model.model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
73
+ "base_model.model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
74
+ "base_model.model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
75
+ "base_model.model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
76
+ "base_model.model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
77
+ "base_model.model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
78
+ "base_model.model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
79
+ "base_model.model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
80
+ "base_model.model.model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
81
+ "base_model.model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
82
+ "base_model.model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
83
+ "base_model.model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
84
+ "base_model.model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
85
+ "base_model.model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
86
+ "base_model.model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
87
+ "base_model.model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
88
+ "base_model.model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
89
+ "base_model.model.model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
90
+ "base_model.model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
91
+ "base_model.model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
92
+ "base_model.model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
93
+ "base_model.model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
94
+ "base_model.model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
95
+ "base_model.model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
96
+ "base_model.model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
97
+ "base_model.model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
98
+ "base_model.model.model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
99
+ "base_model.model.model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
100
+ "base_model.model.model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
101
+ "base_model.model.model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
102
+ "base_model.model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
103
+ "base_model.model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
104
+ "base_model.model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
105
+ "base_model.model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
106
+ "base_model.model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
107
+ "base_model.model.model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
108
+ "base_model.model.model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
109
+ "base_model.model.model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
110
+ "base_model.model.model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
111
+ "base_model.model.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
112
+ "base_model.model.model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
113
+ "base_model.model.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
114
+ "base_model.model.model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
115
+ "base_model.model.model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
116
+ "base_model.model.model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
117
+ "base_model.model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
118
+ "base_model.model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
119
+ "base_model.model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
120
+ "base_model.model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
121
+ "base_model.model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
122
+ "base_model.model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
123
+ "base_model.model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
124
+ "base_model.model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
125
+ "base_model.model.model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
126
+ "base_model.model.model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
127
+ "base_model.model.model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
128
+ "base_model.model.model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
129
+ "base_model.model.model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
130
+ "base_model.model.model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
131
+ "base_model.model.model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
132
+ "base_model.model.model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
133
+ "base_model.model.model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
134
+ "base_model.model.model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
135
+ "base_model.model.model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
136
+ "base_model.model.model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
137
+ "base_model.model.model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
138
+ "base_model.model.model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
139
+ "base_model.model.model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
140
+ "base_model.model.model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
141
+ "base_model.model.model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
142
+ "base_model.model.model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
143
+ "base_model.model.model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
144
+ "base_model.model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
145
+ "base_model.model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
146
+ "base_model.model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
147
+ "base_model.model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
148
+ "base_model.model.model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
149
+ "base_model.model.model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
150
+ "base_model.model.model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
151
+ "base_model.model.model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
152
+ "base_model.model.model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
153
+ "base_model.model.model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
154
+ "base_model.model.model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
155
+ "base_model.model.model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
156
+ "base_model.model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
157
+ "base_model.model.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
158
+ "base_model.model.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
159
+ "base_model.model.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
160
+ "base_model.model.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
161
+ "base_model.model.model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
162
+ "base_model.model.model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
163
+ "base_model.model.model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
164
+ "base_model.model.model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
165
+ "base_model.model.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
166
+ "base_model.model.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
167
+ "base_model.model.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
168
+ "base_model.model.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
169
+ "base_model.model.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
170
+ "base_model.model.model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
171
+ "base_model.model.model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
172
+ "base_model.model.model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
173
+ "base_model.model.model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
174
+ "base_model.model.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
175
+ "base_model.model.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
176
+ "base_model.model.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
177
+ "base_model.model.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
178
+ "base_model.model.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
179
+ "base_model.model.model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
180
+ "base_model.model.model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
181
+ "base_model.model.model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
182
+ "base_model.model.model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
183
+ "base_model.model.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
184
+ "base_model.model.model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
185
+ "base_model.model.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
186
+ "base_model.model.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
187
+ "base_model.model.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
188
+ "base_model.model.model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
189
+ "base_model.model.model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
190
+ "base_model.model.model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
191
+ "base_model.model.model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
192
+ "base_model.model.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
193
+ "base_model.model.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
194
+ "base_model.model.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
195
+ "base_model.model.model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
196
+ "base_model.model.model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
197
+ "base_model.model.model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
198
+ "base_model.model.model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
199
+ "base_model.model.model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
200
+ "base_model.model.model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
201
+ "base_model.model.model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
202
+ "base_model.model.model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
203
+ "base_model.model.model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
204
+ "base_model.model.model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
205
+ "base_model.model.model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
206
+ "base_model.model.model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
207
+ "base_model.model.model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
208
+ "base_model.model.model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
209
+ "base_model.model.model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
210
+ "base_model.model.model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
211
+ "base_model.model.model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
212
+ "base_model.model.model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
213
+ "base_model.model.model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
214
+ "base_model.model.model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
215
+ "base_model.model.model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
216
+ "base_model.model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
217
+ "base_model.model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
218
+ "base_model.model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
219
+ "base_model.model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
220
+ "base_model.model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
221
+ "base_model.model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
222
+ "base_model.model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
223
+ "base_model.model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
224
+ "base_model.model.model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
225
+ "base_model.model.model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
226
+ "base_model.model.model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
227
+ "base_model.model.model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
228
+ "base_model.model.model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
229
+ "base_model.model.model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
230
+ "base_model.model.model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
231
+ "base_model.model.model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
232
+ "base_model.model.model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
233
+ "base_model.model.model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
234
+ "base_model.model.model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
235
+ "base_model.model.model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
236
+ "base_model.model.model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
237
+ "base_model.model.model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
238
+ "base_model.model.model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
239
+ "base_model.model.model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
240
+ "base_model.model.model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
241
+ "base_model.model.model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
242
+ "base_model.model.model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
243
+ "base_model.model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
244
+ "base_model.model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
245
+ "base_model.model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
246
+ "base_model.model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
247
+ "base_model.model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
248
+ "base_model.model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
249
+ "base_model.model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
250
+ "base_model.model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
251
+ "base_model.model.model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
252
+ "base_model.model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
253
+ "base_model.model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
254
+ "base_model.model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
255
+ "base_model.model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
256
+ "base_model.model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
257
+ "base_model.model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
258
+ "base_model.model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
259
+ "base_model.model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
260
+ "base_model.model.model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
261
+ "base_model.model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
262
+ "base_model.model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
263
+ "base_model.model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
264
+ "base_model.model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
265
+ "base_model.model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
266
+ "base_model.model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
267
+ "base_model.model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
268
+ "base_model.model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
269
+ "base_model.model.model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
270
+ "base_model.model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
271
+ "base_model.model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
272
+ "base_model.model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
273
+ "base_model.model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
274
+ "base_model.model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
275
+ "base_model.model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
276
+ "base_model.model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
277
+ "base_model.model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
278
+ "base_model.model.model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
279
+ "base_model.model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
280
+ "base_model.model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
281
+ "base_model.model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
282
+ "base_model.model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
283
+ "base_model.model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
284
+ "base_model.model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
285
+ "base_model.model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
286
+ "base_model.model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
287
+ "base_model.model.model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
288
+ "base_model.model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
289
+ "base_model.model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
290
+ "base_model.model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
291
+ "base_model.model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
292
+ "base_model.model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
293
+ "base_model.model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
294
+ "base_model.model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
295
+ "base_model.model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
296
+ "base_model.model.model.norm.weight": "model-00003-of-00003.safetensors"
297
+ }
298
+ }