flydust commited on
Commit
e2635be
1 Parent(s): 63567a5

End of training

Browse files
README.md ADDED
@@ -0,0 +1,141 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: llama3
3
+ base_model: meta-llama/Meta-Llama-3-8B
4
+ tags:
5
+ - axolotl
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: Llama-3-8B-SynDa-70BQA-300K-Filtered-MR-L
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ [<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)
16
+ <details><summary>See axolotl config</summary>
17
+
18
+ axolotl version: `0.4.0`
19
+ ```yaml
20
+
21
+ base_model: meta-llama/Meta-Llama-3-8B
22
+ model_type: LlamaForCausalLM
23
+ tokenizer_type: AutoTokenizer
24
+
25
+ load_in_8bit: false
26
+ load_in_4bit: false
27
+ strict: false
28
+
29
+ datasets:
30
+ - path: SynDa/Llama-3-70B-SynDa-MultiRound-300K-Filtered-L
31
+ type: sharegpt
32
+ conversation: llama3
33
+ dataset_prepared_path: last_run_prepared
34
+ val_set_size: 0.001
35
+ output_dir: ./out_Llama-3-70B-SynDa-300K-Multi-Round2-L
36
+
37
+ sequence_len: 8192
38
+ sample_packing: true
39
+ eval_sample_packing: false
40
+ pad_to_sequence_len: true
41
+
42
+ wandb_project: SynDa
43
+ wandb_entity:
44
+ wandb_watch:
45
+ wandb_name: Llama-3-70B-SynDa-300K-MR-L-2EP-FFT
46
+ wandb_log_model:
47
+ hub_model_id: SynDa/Llama-3-8B-SynDa-70BQA-300K-Filtered-MR-L
48
+
49
+ gradient_accumulation_steps: 8
50
+ micro_batch_size: 1
51
+ num_epochs: 2
52
+ optimizer: paged_adamw_8bit
53
+ lr_scheduler: cosine
54
+ learning_rate: 2e-5
55
+
56
+ train_on_inputs: false
57
+ group_by_length: false
58
+ bf16: auto
59
+ fp16:
60
+ tf32: false
61
+
62
+ gradient_checkpointing: true
63
+ gradient_checkpointing_kwargs:
64
+ use_reentrant: false
65
+ early_stopping_patience:
66
+ resume_from_checkpoint:
67
+ logging_steps: 1
68
+ xformers_attention:
69
+ flash_attention: true
70
+
71
+ warmup_steps: 100
72
+ evals_per_epoch: 3
73
+ eval_table_size:
74
+ saves_per_epoch: 3
75
+ debug:
76
+ deepspeed:
77
+ weight_decay: 0.0
78
+ fsdp:
79
+ fsdp_config:
80
+ special_tokens:
81
+ pad_token: <|end_of_text|>
82
+
83
+ ```
84
+
85
+ </details><br>
86
+
87
+ # Llama-3-8B-SynDa-70BQA-300K-Filtered-MR-L
88
+
89
+ This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the None dataset.
90
+ It achieves the following results on the evaluation set:
91
+ - Loss: 0.4555
92
+
93
+ ## Model description
94
+
95
+ More information needed
96
+
97
+ ## Intended uses & limitations
98
+
99
+ More information needed
100
+
101
+ ## Training and evaluation data
102
+
103
+ More information needed
104
+
105
+ ## Training procedure
106
+
107
+ ### Training hyperparameters
108
+
109
+ The following hyperparameters were used during training:
110
+ - learning_rate: 2e-05
111
+ - train_batch_size: 1
112
+ - eval_batch_size: 1
113
+ - seed: 42
114
+ - distributed_type: multi-GPU
115
+ - num_devices: 4
116
+ - gradient_accumulation_steps: 8
117
+ - total_train_batch_size: 32
118
+ - total_eval_batch_size: 4
119
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
120
+ - lr_scheduler_type: cosine
121
+ - lr_scheduler_warmup_steps: 100
122
+ - num_epochs: 2
123
+
124
+ ### Training results
125
+
126
+ | Training Loss | Epoch | Step | Validation Loss |
127
+ |:-------------:|:------:|:----:|:---------------:|
128
+ | 0.8807 | 0.0007 | 1 | 0.9001 |
129
+ | 0.5113 | 0.3337 | 464 | 0.5178 |
130
+ | 0.4668 | 0.6673 | 928 | 0.4792 |
131
+ | 0.4492 | 1.0010 | 1392 | 0.4582 |
132
+ | 0.3498 | 1.3205 | 1856 | 0.4575 |
133
+ | 0.3525 | 1.6542 | 2320 | 0.4555 |
134
+
135
+
136
+ ### Framework versions
137
+
138
+ - Transformers 4.40.2
139
+ - Pytorch 2.3.0+cu121
140
+ - Datasets 2.19.1
141
+ - Tokenizers 0.19.1
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": 128001,
5
+ "max_length": 4096,
6
+ "temperature": 0.6,
7
+ "top_p": 0.9,
8
+ "transformers_version": "4.40.2"
9
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c689e235b47650faff6059be9cb3a0272507105082d8f5d623a880ea7eb8829
3
+ size 4976698672
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27c26fcacd6753c9ff102cc70fe5301bdd833d113413e008c6c935255611ca03
3
+ size 4999802720
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e4c59f065b03d260e82492f5a24c26206ed036a2cce9dc1b1bc0e05a0cdf680
3
+ size 4915916176
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb8c56020acf335eb6d4ec6a3061d5c5d59e7e70bd18de4ebb1d6e159c1dc4b7
3
+ size 1168138808
model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16060522496
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
296
+ "model.norm.weight": "model-00004-of-00004.safetensors"
297
+ }
298
+ }
pytorch_model-00001-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01eb1fc5649b9222546f014c9e44e22e2c33d8c680f49ca7214ba45fdc70e0d5
3
+ size 4976718466
pytorch_model-00002-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cd61d9649c9f0ebe3e1402d91f5dab59ffe390e0e67834c06e0ce5a77fc0ceb
3
+ size 4999827718
pytorch_model-00003-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e2f00b4ee7fa9ae4bcfdf2b51d760dc32ece82912150c5076b7d42c5c39618f
3
+ size 4915940170
pytorch_model-00004-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ccdb90c376e4c3c221a3023eb87b3f41a0c6ea0c887e5eaa8ca7562c9358ad0
3
+ size 1168140873
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16060522496
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00004-of-00004.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00004.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
10
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
11
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
13
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
14
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
15
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
16
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
17
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
18
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
19
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
20
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
21
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
22
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
23
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
24
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
25
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
26
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
27
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
28
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
29
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
30
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
31
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
32
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
33
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
34
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
35
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
36
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
37
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
38
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
39
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
40
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
41
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
42
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
43
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
44
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
45
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
46
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
47
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
48
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
49
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
50
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
51
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
52
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
53
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
54
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
55
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
56
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
57
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
58
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
59
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
60
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
61
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
62
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
63
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
64
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
65
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
66
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
67
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
68
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
69
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
70
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
71
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
72
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
73
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
74
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
75
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
76
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
77
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
78
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
79
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
80
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
81
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
82
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
83
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
84
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
85
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
86
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
87
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
88
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
89
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
90
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
91
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
92
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
93
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
94
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
95
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
96
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
97
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
98
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
99
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
100
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
101
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
102
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
103
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
104
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
105
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
106
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
107
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
108
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
109
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
110
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
111
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
112
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
113
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
114
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
115
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
116
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
117
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
118
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
119
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
120
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
121
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
122
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
123
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
124
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
125
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
126
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
127
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
128
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
129
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
130
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
131
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
132
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
133
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
134
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
135
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
136
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
137
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
138
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
139
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
140
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
141
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
142
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
143
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
144
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
145
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
146
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
147
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
148
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
149
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
150
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
151
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
152
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
153
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
154
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
155
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
156
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
157
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
158
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
159
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
160
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
161
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
162
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
163
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
164
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
165
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
166
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
167
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
168
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
169
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
170
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
171
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
172
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
173
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
174
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
175
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
176
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
177
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
178
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
179
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
180
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
181
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
182
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
183
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
184
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
185
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
186
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
187
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
188
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
189
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
190
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
191
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
192
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
193
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
194
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
195
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
196
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
197
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
198
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
199
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
200
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
201
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
202
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
203
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
204
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
205
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
206
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
207
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
208
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
209
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
210
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
211
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
212
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
213
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
214
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
215
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
216
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
217
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
218
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
219
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
220
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
221
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
222
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
223
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
224
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
225
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
226
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
227
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
228
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
229
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
230
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
231
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
232
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
233
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
234
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
235
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
236
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
237
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
238
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
239
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
240
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
241
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
242
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
243
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
244
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
245
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
246
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
247
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
248
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
249
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
250
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
251
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
252
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
253
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
254
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
255
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
256
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
257
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
258
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
259
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
260
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
261
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
262
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
263
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
264
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
265
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
266
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
267
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
268
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
269
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
270
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
271
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
272
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
273
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
274
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
275
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
276
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
277
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
278
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
279
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
280
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
281
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
282
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
283
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
284
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
285
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
286
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
287
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
288
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
289
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
290
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
291
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
292
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
293
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
294
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
295
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
296
+ "model.norm.weight": "pytorch_model-00004-of-00004.bin"
297
+ }
298
+ }