TheDrummer commited on
Commit
8603224
1 Parent(s): 30931ba

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,169 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: BeaverAI/Theia-21B-v2a
3
+ tags:
4
+ - axolotl
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: Theia-21B-v2b-WS
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ [<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
15
+ <details><summary>See axolotl config</summary>
16
+
17
+ axolotl version: `0.4.1`
18
+ ```yaml
19
+ base_model: BeaverAI/Theia-21B-v2a
20
+ model_type: AutoModelForCausalLM
21
+ tokenizer_type: AutoTokenizer
22
+
23
+ load_in_8bit: false
24
+ load_in_4bit: false
25
+ strict: false
26
+ sequence_len: 16384
27
+ bf16: auto
28
+ fp16:
29
+ tf32: false
30
+ flash_attention: true
31
+ special_tokens:
32
+ pad_token: "<pad>"
33
+ tokens:
34
+ - "<|im_start|>"
35
+ - "<|im_end|>"
36
+
37
+ # PLAN
38
+ # instruct = mistral
39
+ # siayn = alpaca
40
+ # RP = chatml
41
+
42
+ # Data
43
+ datasets:
44
+ - path: BeaverAI/saosauce-v2-creative-only
45
+ type: sharegpt
46
+ conversation: chatml
47
+ warmup_steps: 150
48
+
49
+ save_safetensors: true
50
+
51
+ mlflow_tracking_uri: http://127.0.0.1:7860
52
+ mlflow_experiment_name: Default
53
+ # WandB
54
+ #wandb_project: theia
55
+ #wandb_entity:
56
+
57
+ # Iterations
58
+ num_epochs: 2
59
+
60
+ # Output
61
+ output_dir: ./Theia-21B-v2b-Workspace
62
+ hub_model_id: BeaverAI/Theia-21B-v2b-WS
63
+ hub_strategy: "all_checkpoints"
64
+
65
+ # Sampling
66
+ sample_packing: true
67
+ pad_to_sequence_len: true
68
+
69
+ # Batching
70
+ gradient_accumulation_steps: 1
71
+ micro_batch_size: 1
72
+ gradient_checkpointing: true
73
+ gradient_checkpointing_kwargs:
74
+ use_reentrant: true
75
+
76
+ # Evaluation
77
+ val_set_size: 0.025
78
+ evals_per_epoch: 4
79
+ eval_table_size:
80
+ eval_max_new_tokens: 256
81
+ eval_sample_packing: false
82
+ eval_batch_size: 1
83
+
84
+ # Optimizer
85
+ optimizer: paged_adamw_8bit # adamw_8bit
86
+ lr_scheduler: cosine
87
+ learning_rate: 0.0000025
88
+ lr_scheduler: cosine_with_min_lr
89
+ lr_scheduler_kwargs:
90
+ min_lr: 0.00000025
91
+ weight_decay: 0.01
92
+ max_grad_norm: 10.0
93
+
94
+ # Misc
95
+ train_on_inputs: false
96
+ group_by_length: false
97
+ early_stopping_patience:
98
+ local_rank:
99
+ logging_steps: 1
100
+ xformers_attention:
101
+ debug:
102
+ deepspeed: deepspeed_configs/zero3_bf16.json # previously blank
103
+ fsdp:
104
+ fsdp_config:
105
+
106
+ # Checkpoints
107
+ resume_from_checkpoint:
108
+ saves_per_epoch: 1
109
+
110
+ ```
111
+
112
+ </details><br>
113
+
114
+ # Theia-21B-v2b-WS
115
+
116
+ This model is a fine-tuned version of [BeaverAI/Theia-21B-v2a](https://huggingface.co/BeaverAI/Theia-21B-v2a) on the None dataset.
117
+ It achieves the following results on the evaluation set:
118
+ - Loss: 1.0491
119
+
120
+ ## Model description
121
+
122
+ More information needed
123
+
124
+ ## Intended uses & limitations
125
+
126
+ More information needed
127
+
128
+ ## Training and evaluation data
129
+
130
+ More information needed
131
+
132
+ ## Training procedure
133
+
134
+ ### Training hyperparameters
135
+
136
+ The following hyperparameters were used during training:
137
+ - learning_rate: 2.5e-06
138
+ - train_batch_size: 1
139
+ - eval_batch_size: 1
140
+ - seed: 42
141
+ - distributed_type: multi-GPU
142
+ - num_devices: 8
143
+ - total_train_batch_size: 8
144
+ - total_eval_batch_size: 8
145
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
146
+ - lr_scheduler_type: cosine_with_min_lr
147
+ - lr_scheduler_warmup_steps: 150
148
+ - num_epochs: 2
149
+
150
+ ### Training results
151
+
152
+ | Training Loss | Epoch | Step | Validation Loss |
153
+ |:-------------:|:------:|:----:|:---------------:|
154
+ | 1.5956 | 0.0030 | 1 | 1.5014 |
155
+ | 1.2309 | 0.2508 | 83 | 1.2064 |
156
+ | 1.1063 | 0.5015 | 166 | 1.1376 |
157
+ | 1.1885 | 0.7523 | 249 | 1.1021 |
158
+ | 1.1518 | 1.0030 | 332 | 1.0772 |
159
+ | 0.9328 | 1.2356 | 415 | 1.0693 |
160
+ | 0.9149 | 1.4864 | 498 | 1.0569 |
161
+ | 0.9377 | 1.7372 | 581 | 1.0491 |
162
+
163
+
164
+ ### Framework versions
165
+
166
+ - Transformers 4.44.0.dev0
167
+ - Pytorch 2.2.2
168
+ - Datasets 2.19.1
169
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "BeaverAI/Theia-21B-v2a",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 5120,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 1024000,
15
+ "model_type": "mistral",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 70,
18
+ "num_key_value_heads": 8,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_theta": 1000000.0,
21
+ "sliding_window": null,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.44.0.dev0",
25
+ "use_cache": false,
26
+ "vocab_size": 131074
27
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "do_sample": true,
5
+ "eos_token_id": 2,
6
+ "transformers_version": "4.44.0.dev0"
7
+ }
model-00001-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7076b4a42c3b889f8a760e7430f4d9e86655724fd6d437bbad6e2d97b40dd4e
3
+ size 4865542976
model-00002-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7993aa00009141d75e33ea9b5464995e4d23d864027afcfbca94b609824f1226
3
+ size 4907529424
model-00003-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54e2997b2106342b562e59cdf95a877640c4da94cfea16c508a0be099183c3b4
3
+ size 4907529456
model-00004-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7a161e28be861bc47952d7c297b15268242a8030e7db39314eb699f2ae738e0
3
+ size 4907529456
model-00005-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2a36e48c23549f944d76df2e41ced6b3707828b742c67a03405f2c6c1094daf
3
+ size 4907529456
model-00006-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2620927216d866ce33705c03c461bf90de8ac4a29f8ba96b47f670de77c4951
3
+ size 4907529456
model-00007-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96102d51a38a27e1cc4ae31f3f5924e6eb44f3c4cec6fec50be4ae356e2b0c77
3
+ size 4907529456
model-00008-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f48a8419f2f8b8ca32a8f3ee92cbf4a163f27f85a6170d2989cab327b7cfb71b
3
+ size 4907529456
model-00009-of-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efaa650c8ef5681e7e65de2371fe301d414c1927eda6d0a51aa82faf5e35383c
3
+ size 1635830440
model.safetensors.index.json ADDED
@@ -0,0 +1,640 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 40854005760
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00009-of-00009.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00009.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00009.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00009.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00009.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00009.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00009.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00009.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00009.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00003-of-00009.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00003-of-00009.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00003-of-00009.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00009.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00009.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00009.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00009.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00009.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00009.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00009.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00004-of-00009.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00004-of-00009.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00004-of-00009.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00004-of-00009.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00004-of-00009.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00004-of-00009.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00009.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00004-of-00009.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00004-of-00009.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
242
+ "model.layers.32.input_layernorm.weight": "model-00004-of-00009.safetensors",
243
+ "model.layers.32.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
244
+ "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
245
+ "model.layers.32.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
246
+ "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
247
+ "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
248
+ "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
249
+ "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
250
+ "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
251
+ "model.layers.33.input_layernorm.weight": "model-00005-of-00009.safetensors",
252
+ "model.layers.33.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
253
+ "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
254
+ "model.layers.33.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
255
+ "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
256
+ "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
257
+ "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
258
+ "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
259
+ "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
260
+ "model.layers.34.input_layernorm.weight": "model-00005-of-00009.safetensors",
261
+ "model.layers.34.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
262
+ "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
263
+ "model.layers.34.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
264
+ "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
265
+ "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
266
+ "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
267
+ "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
268
+ "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
269
+ "model.layers.35.input_layernorm.weight": "model-00005-of-00009.safetensors",
270
+ "model.layers.35.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
271
+ "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
272
+ "model.layers.35.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
273
+ "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
274
+ "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
275
+ "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
276
+ "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
277
+ "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
278
+ "model.layers.36.input_layernorm.weight": "model-00005-of-00009.safetensors",
279
+ "model.layers.36.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
280
+ "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
281
+ "model.layers.36.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
282
+ "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
283
+ "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
284
+ "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
285
+ "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
286
+ "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
287
+ "model.layers.37.input_layernorm.weight": "model-00005-of-00009.safetensors",
288
+ "model.layers.37.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
289
+ "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
290
+ "model.layers.37.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
291
+ "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
292
+ "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
293
+ "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
294
+ "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
295
+ "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
296
+ "model.layers.38.input_layernorm.weight": "model-00005-of-00009.safetensors",
297
+ "model.layers.38.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
298
+ "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
299
+ "model.layers.38.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
300
+ "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
301
+ "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
302
+ "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
303
+ "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
304
+ "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
305
+ "model.layers.39.input_layernorm.weight": "model-00005-of-00009.safetensors",
306
+ "model.layers.39.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
307
+ "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
308
+ "model.layers.39.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
309
+ "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
310
+ "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
311
+ "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
312
+ "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
313
+ "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
314
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00009.safetensors",
315
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
316
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
317
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
318
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
319
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
320
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
321
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
322
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
323
+ "model.layers.40.input_layernorm.weight": "model-00005-of-00009.safetensors",
324
+ "model.layers.40.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
325
+ "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
326
+ "model.layers.40.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
327
+ "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
328
+ "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
329
+ "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
330
+ "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
331
+ "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
332
+ "model.layers.41.input_layernorm.weight": "model-00005-of-00009.safetensors",
333
+ "model.layers.41.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
334
+ "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
335
+ "model.layers.41.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
336
+ "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
337
+ "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
338
+ "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
339
+ "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
340
+ "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
341
+ "model.layers.42.input_layernorm.weight": "model-00006-of-00009.safetensors",
342
+ "model.layers.42.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
343
+ "model.layers.42.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
344
+ "model.layers.42.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
345
+ "model.layers.42.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
346
+ "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
347
+ "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
348
+ "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
349
+ "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
350
+ "model.layers.43.input_layernorm.weight": "model-00006-of-00009.safetensors",
351
+ "model.layers.43.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
352
+ "model.layers.43.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
353
+ "model.layers.43.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
354
+ "model.layers.43.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
355
+ "model.layers.43.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
356
+ "model.layers.43.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
357
+ "model.layers.43.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
358
+ "model.layers.43.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
359
+ "model.layers.44.input_layernorm.weight": "model-00006-of-00009.safetensors",
360
+ "model.layers.44.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
361
+ "model.layers.44.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
362
+ "model.layers.44.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
363
+ "model.layers.44.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
364
+ "model.layers.44.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
365
+ "model.layers.44.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
366
+ "model.layers.44.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
367
+ "model.layers.44.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
368
+ "model.layers.45.input_layernorm.weight": "model-00006-of-00009.safetensors",
369
+ "model.layers.45.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
370
+ "model.layers.45.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
371
+ "model.layers.45.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
372
+ "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
373
+ "model.layers.45.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
374
+ "model.layers.45.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
375
+ "model.layers.45.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
376
+ "model.layers.45.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
377
+ "model.layers.46.input_layernorm.weight": "model-00006-of-00009.safetensors",
378
+ "model.layers.46.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
379
+ "model.layers.46.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
380
+ "model.layers.46.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
381
+ "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
382
+ "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
383
+ "model.layers.46.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
384
+ "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
385
+ "model.layers.46.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
386
+ "model.layers.47.input_layernorm.weight": "model-00006-of-00009.safetensors",
387
+ "model.layers.47.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
388
+ "model.layers.47.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
389
+ "model.layers.47.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
390
+ "model.layers.47.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
391
+ "model.layers.47.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
392
+ "model.layers.47.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
393
+ "model.layers.47.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
394
+ "model.layers.47.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
395
+ "model.layers.48.input_layernorm.weight": "model-00006-of-00009.safetensors",
396
+ "model.layers.48.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
397
+ "model.layers.48.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
398
+ "model.layers.48.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
399
+ "model.layers.48.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
400
+ "model.layers.48.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
401
+ "model.layers.48.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
402
+ "model.layers.48.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
403
+ "model.layers.48.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
404
+ "model.layers.49.input_layernorm.weight": "model-00006-of-00009.safetensors",
405
+ "model.layers.49.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
406
+ "model.layers.49.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
407
+ "model.layers.49.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
408
+ "model.layers.49.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
409
+ "model.layers.49.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
410
+ "model.layers.49.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
411
+ "model.layers.49.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
412
+ "model.layers.49.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
413
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00009.safetensors",
414
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
415
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
416
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
417
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
418
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
419
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
420
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
421
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
422
+ "model.layers.50.input_layernorm.weight": "model-00006-of-00009.safetensors",
423
+ "model.layers.50.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
424
+ "model.layers.50.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
425
+ "model.layers.50.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
426
+ "model.layers.50.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
427
+ "model.layers.50.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
428
+ "model.layers.50.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
429
+ "model.layers.50.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
430
+ "model.layers.50.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
431
+ "model.layers.51.input_layernorm.weight": "model-00007-of-00009.safetensors",
432
+ "model.layers.51.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
433
+ "model.layers.51.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
434
+ "model.layers.51.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
435
+ "model.layers.51.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
436
+ "model.layers.51.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
437
+ "model.layers.51.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
438
+ "model.layers.51.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
439
+ "model.layers.51.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
440
+ "model.layers.52.input_layernorm.weight": "model-00007-of-00009.safetensors",
441
+ "model.layers.52.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
442
+ "model.layers.52.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
443
+ "model.layers.52.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
444
+ "model.layers.52.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
445
+ "model.layers.52.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
446
+ "model.layers.52.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
447
+ "model.layers.52.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
448
+ "model.layers.52.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
449
+ "model.layers.53.input_layernorm.weight": "model-00007-of-00009.safetensors",
450
+ "model.layers.53.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
451
+ "model.layers.53.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
452
+ "model.layers.53.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
453
+ "model.layers.53.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
454
+ "model.layers.53.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
455
+ "model.layers.53.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
456
+ "model.layers.53.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
457
+ "model.layers.53.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
458
+ "model.layers.54.input_layernorm.weight": "model-00007-of-00009.safetensors",
459
+ "model.layers.54.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
460
+ "model.layers.54.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
461
+ "model.layers.54.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
462
+ "model.layers.54.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
463
+ "model.layers.54.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
464
+ "model.layers.54.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
465
+ "model.layers.54.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
466
+ "model.layers.54.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
467
+ "model.layers.55.input_layernorm.weight": "model-00007-of-00009.safetensors",
468
+ "model.layers.55.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
469
+ "model.layers.55.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
470
+ "model.layers.55.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
471
+ "model.layers.55.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
472
+ "model.layers.55.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
473
+ "model.layers.55.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
474
+ "model.layers.55.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
475
+ "model.layers.55.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
476
+ "model.layers.56.input_layernorm.weight": "model-00007-of-00009.safetensors",
477
+ "model.layers.56.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
478
+ "model.layers.56.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
479
+ "model.layers.56.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
480
+ "model.layers.56.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
481
+ "model.layers.56.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
482
+ "model.layers.56.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
483
+ "model.layers.56.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
484
+ "model.layers.56.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
485
+ "model.layers.57.input_layernorm.weight": "model-00007-of-00009.safetensors",
486
+ "model.layers.57.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
487
+ "model.layers.57.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
488
+ "model.layers.57.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
489
+ "model.layers.57.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
490
+ "model.layers.57.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
491
+ "model.layers.57.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
492
+ "model.layers.57.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
493
+ "model.layers.57.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
494
+ "model.layers.58.input_layernorm.weight": "model-00007-of-00009.safetensors",
495
+ "model.layers.58.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
496
+ "model.layers.58.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
497
+ "model.layers.58.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
498
+ "model.layers.58.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
499
+ "model.layers.58.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
500
+ "model.layers.58.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
501
+ "model.layers.58.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
502
+ "model.layers.58.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
503
+ "model.layers.59.input_layernorm.weight": "model-00007-of-00009.safetensors",
504
+ "model.layers.59.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
505
+ "model.layers.59.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
506
+ "model.layers.59.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
507
+ "model.layers.59.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
508
+ "model.layers.59.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
509
+ "model.layers.59.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
510
+ "model.layers.59.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
511
+ "model.layers.59.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
512
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00009.safetensors",
513
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
514
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
515
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
516
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
517
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
518
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
519
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
520
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
521
+ "model.layers.60.input_layernorm.weight": "model-00008-of-00009.safetensors",
522
+ "model.layers.60.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
523
+ "model.layers.60.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
524
+ "model.layers.60.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
525
+ "model.layers.60.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
526
+ "model.layers.60.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
527
+ "model.layers.60.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
528
+ "model.layers.60.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
529
+ "model.layers.60.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
530
+ "model.layers.61.input_layernorm.weight": "model-00008-of-00009.safetensors",
531
+ "model.layers.61.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
532
+ "model.layers.61.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
533
+ "model.layers.61.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
534
+ "model.layers.61.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
535
+ "model.layers.61.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
536
+ "model.layers.61.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
537
+ "model.layers.61.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
538
+ "model.layers.61.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
539
+ "model.layers.62.input_layernorm.weight": "model-00008-of-00009.safetensors",
540
+ "model.layers.62.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
541
+ "model.layers.62.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
542
+ "model.layers.62.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
543
+ "model.layers.62.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
544
+ "model.layers.62.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
545
+ "model.layers.62.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
546
+ "model.layers.62.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
547
+ "model.layers.62.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
548
+ "model.layers.63.input_layernorm.weight": "model-00008-of-00009.safetensors",
549
+ "model.layers.63.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
550
+ "model.layers.63.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
551
+ "model.layers.63.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
552
+ "model.layers.63.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
553
+ "model.layers.63.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
554
+ "model.layers.63.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
555
+ "model.layers.63.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
556
+ "model.layers.63.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
557
+ "model.layers.64.input_layernorm.weight": "model-00008-of-00009.safetensors",
558
+ "model.layers.64.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
559
+ "model.layers.64.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
560
+ "model.layers.64.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
561
+ "model.layers.64.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
562
+ "model.layers.64.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
563
+ "model.layers.64.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
564
+ "model.layers.64.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
565
+ "model.layers.64.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
566
+ "model.layers.65.input_layernorm.weight": "model-00008-of-00009.safetensors",
567
+ "model.layers.65.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
568
+ "model.layers.65.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
569
+ "model.layers.65.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
570
+ "model.layers.65.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
571
+ "model.layers.65.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
572
+ "model.layers.65.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
573
+ "model.layers.65.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
574
+ "model.layers.65.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
575
+ "model.layers.66.input_layernorm.weight": "model-00008-of-00009.safetensors",
576
+ "model.layers.66.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
577
+ "model.layers.66.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
578
+ "model.layers.66.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
579
+ "model.layers.66.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
580
+ "model.layers.66.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
581
+ "model.layers.66.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
582
+ "model.layers.66.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
583
+ "model.layers.66.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
584
+ "model.layers.67.input_layernorm.weight": "model-00008-of-00009.safetensors",
585
+ "model.layers.67.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
586
+ "model.layers.67.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
587
+ "model.layers.67.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
588
+ "model.layers.67.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
589
+ "model.layers.67.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
590
+ "model.layers.67.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
591
+ "model.layers.67.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
592
+ "model.layers.67.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
593
+ "model.layers.68.input_layernorm.weight": "model-00008-of-00009.safetensors",
594
+ "model.layers.68.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
595
+ "model.layers.68.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
596
+ "model.layers.68.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
597
+ "model.layers.68.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
598
+ "model.layers.68.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
599
+ "model.layers.68.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
600
+ "model.layers.68.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
601
+ "model.layers.68.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
602
+ "model.layers.69.input_layernorm.weight": "model-00009-of-00009.safetensors",
603
+ "model.layers.69.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
604
+ "model.layers.69.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
605
+ "model.layers.69.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
606
+ "model.layers.69.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
607
+ "model.layers.69.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
608
+ "model.layers.69.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
609
+ "model.layers.69.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
610
+ "model.layers.69.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
611
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00009.safetensors",
612
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
613
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
614
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
615
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
616
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
617
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
618
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
619
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
620
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00009.safetensors",
621
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
622
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
623
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
624
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
625
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
626
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
627
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
628
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
629
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00009.safetensors",
630
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
631
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
632
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
633
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
634
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
635
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
636
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
637
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
638
+ "model.norm.weight": "model-00009-of-00009.safetensors"
639
+ }
640
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<pad>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e286e9c8a8a509ee42037a8972e7d9e7efa88d8054ad452ca8457415340c4e8
3
+ size 8120