Markus Pernpointner
commited on
Commit
•
581851e
1
Parent(s):
5348c1c
Initial model commit
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- config.yml +229 -0
- model_state_layer_0_EmbeddingInput.pt +3 -0
- model_state_layer_10_TransformerLayer.pt +3 -0
- model_state_layer_10_TransformerLayer_adapter_embed.pt +3 -0
- model_state_layer_11_TransformerLayer.pt +3 -0
- model_state_layer_11_TransformerLayer_adapter_embed.pt +3 -0
- model_state_layer_12_TransformerLayer.pt +3 -0
- model_state_layer_12_TransformerLayer_adapter_embed.pt +3 -0
- model_state_layer_13_TransformerLayer.pt +3 -0
- model_state_layer_13_TransformerLayer_adapter_embed.pt +3 -0
- model_state_layer_14_TransformerLayer.pt +3 -0
- model_state_layer_14_TransformerLayer_adapter_embed.pt +3 -0
- model_state_layer_15_TransformerLayer.pt +3 -0
- model_state_layer_15_TransformerLayer_adapter_embed.pt +3 -0
- model_state_layer_16_TransformerLayer.pt +3 -0
- model_state_layer_16_TransformerLayer_adapter_embed.pt +3 -0
- model_state_layer_17_TransformerLayer.pt +3 -0
- model_state_layer_17_TransformerLayer_adapter_embed.pt +3 -0
- model_state_layer_18_TransformerLayer.pt +3 -0
- model_state_layer_18_TransformerLayer_adapter_embed.pt +3 -0
- model_state_layer_19_TransformerLayer.pt +3 -0
- model_state_layer_19_TransformerLayer_adapter_embed.pt +3 -0
- model_state_layer_1_TransformerLayer.pt +3 -0
- model_state_layer_1_TransformerLayer_adapter_embed.pt +3 -0
- model_state_layer_20_TransformerLayer.pt +3 -0
- model_state_layer_20_TransformerLayer_adapter_embed.pt +3 -0
- model_state_layer_21_TransformerLayer.pt +3 -0
- model_state_layer_21_TransformerLayer_adapter_embed.pt +3 -0
- model_state_layer_22_TransformerLayer.pt +3 -0
- model_state_layer_22_TransformerLayer_adapter_embed.pt +3 -0
- model_state_layer_23_TransformerLayer.pt +3 -0
- model_state_layer_23_TransformerLayer_adapter_embed.pt +3 -0
- model_state_layer_24_TransformerLayer.pt +3 -0
- model_state_layer_24_TransformerLayer_adapter_embed.pt +3 -0
- model_state_layer_25_TransformerLayer.pt +3 -0
- model_state_layer_25_TransformerLayer_adapter_embed.pt +3 -0
- model_state_layer_26_TransformerLayer.pt +3 -0
- model_state_layer_26_TransformerLayer_adapter_embed.pt +3 -0
- model_state_layer_27_TransformerLayer.pt +3 -0
- model_state_layer_27_TransformerLayer_adapter_embed.pt +3 -0
- model_state_layer_28_LayerNormWrapper.pt +3 -0
- model_state_layer_29_TransformerEmbeddingHead.pt +3 -0
- model_state_layer_2_TransformerLayer.pt +3 -0
- model_state_layer_2_TransformerLayer_adapter_embed.pt +3 -0
- model_state_layer_3_TransformerLayer.pt +3 -0
- model_state_layer_3_TransformerLayer_adapter_embed.pt +3 -0
- model_state_layer_4_TransformerLayer.pt +3 -0
- model_state_layer_4_TransformerLayer_adapter_embed.pt +3 -0
- model_state_layer_5_TransformerLayer.pt +3 -0
- model_state_layer_5_TransformerLayer_adapter_embed.pt +3 -0
config.yml
ADDED
@@ -0,0 +1,229 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"version": ".unknown.",
|
3 |
+
"runner": {
|
4 |
+
"runner_type": "pdsh",
|
5 |
+
"hostsfile": null,
|
6 |
+
"hosts": null,
|
7 |
+
"master_port": 29500,
|
8 |
+
"master_addr": null,
|
9 |
+
"script": "src/scaling/transformer/train.py",
|
10 |
+
"default_gpu_count": 8,
|
11 |
+
"docker_config": {
|
12 |
+
"docker_container": null,
|
13 |
+
"docker_sudo": false,
|
14 |
+
"docker_mounts": [
|
15 |
+
[
|
16 |
+
"/mnt/",
|
17 |
+
"/mnt/"
|
18 |
+
]
|
19 |
+
]
|
20 |
+
},
|
21 |
+
"use_determined": true
|
22 |
+
},
|
23 |
+
"logger": {
|
24 |
+
"log_level": "info",
|
25 |
+
"log_dir": null,
|
26 |
+
"metrics_ranks": null,
|
27 |
+
"use_wandb": true,
|
28 |
+
"wandb_ranks": null,
|
29 |
+
"wandb_host": "https://api.wandb.ai",
|
30 |
+
"wandb_team": "aleph-alpha",
|
31 |
+
"wandb_project": "ng-semantic-embedding",
|
32 |
+
"wandb_group": "pharia_7B_embedding_all_source_256-2024-10-01-19-28-52",
|
33 |
+
"wandb_api_key": "d80060c84c496915fcad15283809dbde65087d73",
|
34 |
+
"use_tensorboard": false,
|
35 |
+
"tensorboard_ranks": null,
|
36 |
+
"determined_metrics_ranks": null
|
37 |
+
},
|
38 |
+
"topology": {
|
39 |
+
"global_rank": 0,
|
40 |
+
"world_size": 256,
|
41 |
+
"local_slot": 0,
|
42 |
+
"model_parallel_size": 1,
|
43 |
+
"pipe_parallel_size": 1,
|
44 |
+
"data_parallel_size": 256,
|
45 |
+
"global_batch_size": 2048,
|
46 |
+
"micro_batch_size": 8,
|
47 |
+
"gradient_accumulation_steps": 1,
|
48 |
+
"pipe_partition_method": "balanced",
|
49 |
+
"pipe_partition_overwrite": null,
|
50 |
+
"activation_checkpointing_type": "every_layer",
|
51 |
+
"sequence_parallel": false
|
52 |
+
},
|
53 |
+
"optimizer": {
|
54 |
+
"method": "adamw",
|
55 |
+
"beta1": 0.9,
|
56 |
+
"beta2": 0.95,
|
57 |
+
"eps": 1e-15,
|
58 |
+
"gradient_clipping": 0.0,
|
59 |
+
"allreduce_bucket_size": 500000000,
|
60 |
+
"loss_scaler": {
|
61 |
+
"enable": false,
|
62 |
+
"initial_scale": 4294967296.0,
|
63 |
+
"window": 1000,
|
64 |
+
"hysteresis": 2.0,
|
65 |
+
"consecutive_hysteresis": false,
|
66 |
+
"min_scale": 1.0,
|
67 |
+
"factor": 2.0
|
68 |
+
},
|
69 |
+
"zero": true,
|
70 |
+
"zero_save_static": false,
|
71 |
+
"debug_log": false
|
72 |
+
},
|
73 |
+
"learning_rate_scheduler": {
|
74 |
+
"learning_rate": 2e-05,
|
75 |
+
"learning_rate_minimum": 0.0,
|
76 |
+
"learning_rate_decay_style": "linear",
|
77 |
+
"learning_rate_decay_iters": 938,
|
78 |
+
"learning_rate_warmup_steps": 50
|
79 |
+
},
|
80 |
+
"embedding_learning_rate_scheduler": {
|
81 |
+
"learning_rate": 0.0,
|
82 |
+
"learning_rate_minimum": 0.0,
|
83 |
+
"learning_rate_decay_style": "cosine",
|
84 |
+
"learning_rate_decay_iters": 0,
|
85 |
+
"learning_rate_warmup_steps": 0
|
86 |
+
},
|
87 |
+
"training": {
|
88 |
+
"weight_decay": 0.0001,
|
89 |
+
"finetune": true,
|
90 |
+
"finetunable_parameters": [
|
91 |
+
"embed"
|
92 |
+
],
|
93 |
+
"parameters_exclude": [],
|
94 |
+
"use_separate_lr_on_embeddings": false,
|
95 |
+
"use_deterministic_torch_algorithms": false,
|
96 |
+
"loss_function_config": {
|
97 |
+
"loss_type": "contrastive_loss",
|
98 |
+
"number_of_hard_negatives": 1,
|
99 |
+
"use_instructions": true,
|
100 |
+
"query_side_only": false,
|
101 |
+
"scale": 50,
|
102 |
+
"log_verbose_metrics": true
|
103 |
+
}
|
104 |
+
},
|
105 |
+
"trainer": {
|
106 |
+
"save_dir": "checkpoints",
|
107 |
+
"save_interval": 938,
|
108 |
+
"load_dir": "/scratch/samuel/Pharia-1-LLM-7B-control",
|
109 |
+
"train_iterations": 938,
|
110 |
+
"assert_checkpoint_loaded": true,
|
111 |
+
"load_optimizer_states": false,
|
112 |
+
"delete_past_optimizer_states": true,
|
113 |
+
"load_context": false,
|
114 |
+
"allowed_missing_keys_in_checkpoint": [
|
115 |
+
"embed"
|
116 |
+
],
|
117 |
+
"allowed_unexpected_keys_in_checkpoint": null,
|
118 |
+
"ignore_keys_in_checkpoint": null,
|
119 |
+
"merge_lora_after_loading_checkpoint": false,
|
120 |
+
"seed": 42,
|
121 |
+
"dataloader_num_workers": 0,
|
122 |
+
"dataloader_pin_memory": true,
|
123 |
+
"dataloader_prefetch_factor": null,
|
124 |
+
"eval_iterations": 1,
|
125 |
+
"eval_interval": null,
|
126 |
+
"separate_file_for_parameters": [
|
127 |
+
"adapter_embed"
|
128 |
+
]
|
129 |
+
},
|
130 |
+
"profiler": {
|
131 |
+
"profile_steps": 0,
|
132 |
+
"profile_start_at_step": 0,
|
133 |
+
"profiler_output": null
|
134 |
+
},
|
135 |
+
"transformer_architecture": {
|
136 |
+
"vocab_size": 128000,
|
137 |
+
"vocab_file": "/scratch/samuel/Pharia-1-LLM-7B-control/vocab.json",
|
138 |
+
"hidden_size": 4608,
|
139 |
+
"num_layers": 27,
|
140 |
+
"num_attention_heads": 36,
|
141 |
+
"num_local_attention_heads": 0,
|
142 |
+
"local_attention_window_size": null,
|
143 |
+
"rotary_embedding_base": 1000000,
|
144 |
+
"rotary_percentage": 1.0,
|
145 |
+
"sequence_length": 2048,
|
146 |
+
"norm_type": "layernorm",
|
147 |
+
"relative_position_embedding_type": "rotary_complex",
|
148 |
+
"mlp_type": "default",
|
149 |
+
"mlp_factor": 4.0,
|
150 |
+
"attention_bias": true,
|
151 |
+
"attention_qkv_in_one": false,
|
152 |
+
"attention_num_kv_heads": 4,
|
153 |
+
"attention_use_matmul": false,
|
154 |
+
"mlp_bias": true,
|
155 |
+
"key_query_norm": false,
|
156 |
+
"weight_tying": false,
|
157 |
+
"masked_softmax": {
|
158 |
+
"kernel": "torch",
|
159 |
+
"softmax_in_fp32": true,
|
160 |
+
"scale": 1.0,
|
161 |
+
"deterministic_flash_attn_bwd": false
|
162 |
+
},
|
163 |
+
"layernorm": {
|
164 |
+
"optimization_type": "torch",
|
165 |
+
"layernorm_epsilon": 1e-05
|
166 |
+
},
|
167 |
+
"precision": "bfloat16",
|
168 |
+
"dropout_embedding": 0.0,
|
169 |
+
"dropout_attention_probs": 0.0,
|
170 |
+
"dropout_after_attention": 0.0,
|
171 |
+
"dropout_after_mlp": 0.0,
|
172 |
+
"bitfit_bias_config": null,
|
173 |
+
"finetunable_token_ids": [],
|
174 |
+
"image_encoder": false,
|
175 |
+
"dropout_image_encoder": 0.0,
|
176 |
+
"softprompt_config": null,
|
177 |
+
"adapter_config": {
|
178 |
+
"name": "embed",
|
179 |
+
"attention_downsampling_factor": 0.25,
|
180 |
+
"mlp_downsampling_factor": 0.25,
|
181 |
+
"init_std": 1e-05,
|
182 |
+
"version": ".unknown."
|
183 |
+
},
|
184 |
+
"lora_config": null,
|
185 |
+
"embedding_head_config": {
|
186 |
+
"name": "pooling_only",
|
187 |
+
"proj_layers": [
|
188 |
+
256
|
189 |
+
],
|
190 |
+
"pooling": "weighted_mean"
|
191 |
+
},
|
192 |
+
"lm_head": false,
|
193 |
+
"causal": true
|
194 |
+
},
|
195 |
+
"data": {
|
196 |
+
"legacy_dataset": false,
|
197 |
+
"load_mmap_index_to_memory": false,
|
198 |
+
"use_mmap": false,
|
199 |
+
"load_data_item_mmap_index_to_memory": false,
|
200 |
+
"finetuning_dataset": false,
|
201 |
+
"finetuning_chat_dataset": false,
|
202 |
+
"finetuning_dataset_memory_map": false,
|
203 |
+
"embedding_dataset": true,
|
204 |
+
"embedding_dataset_memory_map": false,
|
205 |
+
"data_prefixes": [
|
206 |
+
"/scratch/samuel/all_source_data_templated/allnli_eng.jsonl",
|
207 |
+
"/scratch/samuel/all_source_data_templated/hotpot_with_bm25_negatives.jsonl",
|
208 |
+
"/scratch/samuel/all_source_data_templated/medi_1.jsonl",
|
209 |
+
"/scratch/samuel/all_source_data_templated/msmarco.jsonl"
|
210 |
+
],
|
211 |
+
"validation_data_prefixes": null,
|
212 |
+
"blended_dataset": {
|
213 |
+
"weight_by_num_documents": true,
|
214 |
+
"weighted_sampler_alpha": 1.0,
|
215 |
+
"weights": null,
|
216 |
+
"weight_examples_proportional": false,
|
217 |
+
"ep_maximum": null,
|
218 |
+
"ep_temperature": 1.0,
|
219 |
+
"minimum_dataset_size": 0,
|
220 |
+
"cache_directory": "/scratch/samuel/blended_dataset_cache",
|
221 |
+
"shuffle_dataset_indices": false,
|
222 |
+
"load_dataset_indices_to_memory": false
|
223 |
+
},
|
224 |
+
"only_full_sequences": false,
|
225 |
+
"allow_incomplete_sequences_every_n": 0
|
226 |
+
},
|
227 |
+
"determined_experiment_id": 2965,
|
228 |
+
"determined_trial_id": 86040
|
229 |
+
}
|
model_state_layer_0_EmbeddingInput.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3722b0053cc854fcf13733cf9d10317d041d9aae5b65643f697974cc2882efb3
|
3 |
+
size 1179649443
|
model_state_layer_10_TransformerLayer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef63496e306c9f3e0112742300dd47b51c31fd2226fd3d7aa5c2adc1a5ffb265
|
3 |
+
size 434219902
|
model_state_layer_10_TransformerLayer_adapter_embed.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3071455dec4665113216f294ea7cd1af7196380dda917a59c3efb0285b7e7c1f
|
3 |
+
size 42469872
|
model_state_layer_11_TransformerLayer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:38ae21f20ea4e1492bdf2369f7ef91dda55015f81ab4eab9604a9362086d12cb
|
3 |
+
size 434219902
|
model_state_layer_11_TransformerLayer_adapter_embed.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:55da45ccc291c5dd372ad890c4d050f1d3cbb7f8408a284bbc70ec8128988f11
|
3 |
+
size 42469872
|
model_state_layer_12_TransformerLayer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd902b46a5a353687a2f31e754164e3db18fe72c769a69ed13284bbff224f455
|
3 |
+
size 434219902
|
model_state_layer_12_TransformerLayer_adapter_embed.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:db75b1193e64fe400550066600e0cac3444a7ccada4a8a44c2d13a3c084c1fed
|
3 |
+
size 42469872
|
model_state_layer_13_TransformerLayer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:664c1b719da7b9218debdc2e9794798ca9d0f22568b138996e182229d79c3444
|
3 |
+
size 434219902
|
model_state_layer_13_TransformerLayer_adapter_embed.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:97f60798bafe4179fda66410bc6ea4d926b4bc10be86c565187a505387ecc9ec
|
3 |
+
size 42469872
|
model_state_layer_14_TransformerLayer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1ef77d20a502e6c8d8908cbd7cb222d04ccea69002e78042a57ac11a8a0b4362
|
3 |
+
size 434219902
|
model_state_layer_14_TransformerLayer_adapter_embed.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2416a2626b40f412a01b9177bbc4b295856663430abbf4c1f3770f2bb2c33170
|
3 |
+
size 42469872
|
model_state_layer_15_TransformerLayer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b7de81299e97471d03af358c730a40238867eb6032c93c4cebcba714f2db5d47
|
3 |
+
size 434219902
|
model_state_layer_15_TransformerLayer_adapter_embed.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:00c68832f2ed909e3663b9317413b6f08e37e3326553b63b4d87b5f99b25e05e
|
3 |
+
size 42469872
|
model_state_layer_16_TransformerLayer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e866357f6d06e90c4a4785e7b0cc2056b50361904168d54fb6fc314ef9f4639b
|
3 |
+
size 434219902
|
model_state_layer_16_TransformerLayer_adapter_embed.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:00f14bd76f5e18b3d790ad6b15b49273dadad3b6682cdb39c1690505e01a8b6f
|
3 |
+
size 42469872
|
model_state_layer_17_TransformerLayer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:03b4c380ed92cd055a067919127a7365bcd66f18fa8dfa8d38653018ac0f597c
|
3 |
+
size 434219902
|
model_state_layer_17_TransformerLayer_adapter_embed.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c6fd7770f7910dfb57aee214b30d8be581c1621c83eabbdab0ae76421d244ac
|
3 |
+
size 42469872
|
model_state_layer_18_TransformerLayer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c34494e568a417b9adae97acb4d7c76012a9903a3e3d596e68d0020f1af6d2b0
|
3 |
+
size 434219902
|
model_state_layer_18_TransformerLayer_adapter_embed.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d8a4cdc5f694d1607a2c0824f49a5a43e36917ba31e7cbdbaecd17179fa85e9
|
3 |
+
size 42469872
|
model_state_layer_19_TransformerLayer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2807c758304a165e6140b8942fa9eab390814f81c26fd327628822ce004ebfe7
|
3 |
+
size 434219902
|
model_state_layer_19_TransformerLayer_adapter_embed.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:88ff78dc09729fe2a641b665b06bbe51537bf12f702269759abbc94335c66a30
|
3 |
+
size 42469872
|
model_state_layer_1_TransformerLayer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3c2679a5ca251090f3a75c87b7add5f42e975a213ec8aaee90bde27da688a3d1
|
3 |
+
size 434219882
|
model_state_layer_1_TransformerLayer_adapter_embed.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5e21ae05b1e2d5e791b3aaeacca8f47668b2f93ff4c1c046a765be91aae26f95
|
3 |
+
size 42469864
|
model_state_layer_20_TransformerLayer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:197bec6a16feca3ac18653521b975673a56a071bf59ae3a9bfce737648bda775
|
3 |
+
size 434219902
|
model_state_layer_20_TransformerLayer_adapter_embed.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:85b5a318c6ecabdf8019452d2d74e50f9ae4ad99ef1d034a180133503afcd190
|
3 |
+
size 42469872
|
model_state_layer_21_TransformerLayer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:31eb0f91b2b326f7b869a2dc5dae07be2a6831efb72d3193d1d6d457a2d6fcff
|
3 |
+
size 434219902
|
model_state_layer_21_TransformerLayer_adapter_embed.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:02d4de53679a0261925cc092fa0be06ba6d663735f037cbbb8f506a61baa88c2
|
3 |
+
size 42469872
|
model_state_layer_22_TransformerLayer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8deac3ee07d0285db53ce915d9315491287708edec05a9f16e17e3b0c2395ceb
|
3 |
+
size 434219902
|
model_state_layer_22_TransformerLayer_adapter_embed.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b85af03d8a9ed9c6bf66619563e5cd26b8894b30a0301cb8cd0e45df52a7a0f
|
3 |
+
size 42469872
|
model_state_layer_23_TransformerLayer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:28a4de46c226702e34dbf4d5cd8ead1d366f7cd94b5c5a0f9481dc0f5d502214
|
3 |
+
size 434219902
|
model_state_layer_23_TransformerLayer_adapter_embed.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb864841645a7ae04dc3867d1fe26a307be28da55a787ccb1c8ab044352c13fd
|
3 |
+
size 42469872
|
model_state_layer_24_TransformerLayer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:290bde2e41ce42a45bef1ae6977cbc4f8add6ca43f1493fedeac5d17b7497248
|
3 |
+
size 434219902
|
model_state_layer_24_TransformerLayer_adapter_embed.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a671aed521d6783c25d80f43a9530599d2a15d48f6f2d98b3eceba8294a94c77
|
3 |
+
size 42469872
|
model_state_layer_25_TransformerLayer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:45968daef6d99223322950b1251b22b8462b8d95fd355edb67421feaef60fc49
|
3 |
+
size 434219902
|
model_state_layer_25_TransformerLayer_adapter_embed.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:487b308e165857cdbd6e52deb2df0239372dad547befb07bdd0f7ff7662d0314
|
3 |
+
size 42469872
|
model_state_layer_26_TransformerLayer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:47274e293886f267b6ef434f55b4087c3400132b40e33ea732762fdcf544648d
|
3 |
+
size 434219902
|
model_state_layer_26_TransformerLayer_adapter_embed.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ac9f37f0eb3b2aa48338ae92482917cede328234aac94cb5acd4e6e0535826a
|
3 |
+
size 42469872
|
model_state_layer_27_TransformerLayer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2f25827475fe28d36d12002c77f4e337f01af1d38524d74163c804f387ebcad4
|
3 |
+
size 434219902
|
model_state_layer_27_TransformerLayer_adapter_embed.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8619d0cd488dc2f267dc84bf9a85094894e93e6067b623223442bc706ed88f52
|
3 |
+
size 42469872
|
model_state_layer_28_LayerNormWrapper.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6cd1372d2ae21d66d644fb98394d0868cc9aeff84ccc20619a9bbf95eeebcd62
|
3 |
+
size 20172
|
model_state_layer_29_TransformerEmbeddingHead.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:84863b3c4b23eb9d18224b2c4275f2998fd48901ce5361bfe4cd5618598c2386
|
3 |
+
size 2360794
|
model_state_layer_2_TransformerLayer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:15decebd9fe0f57b1d69766411ab106d37f354b7dc1b6b280d48baca79626756
|
3 |
+
size 434219882
|
model_state_layer_2_TransformerLayer_adapter_embed.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2cecf3037992e2b5d443fae5d312368032dc3e3191bf4c466c69cd90380b4bc0
|
3 |
+
size 42469864
|
model_state_layer_3_TransformerLayer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c9465e9dcb05d29f2c9e320c53e486825e05341a6c5097fcefa86ca1384f495
|
3 |
+
size 434219882
|
model_state_layer_3_TransformerLayer_adapter_embed.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fbe555db4a265531edfd537af40a1c62de8a0b363aeb310af820aedc8eac1a3c
|
3 |
+
size 42469864
|
model_state_layer_4_TransformerLayer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f8449ff2999f09a5ae6a621104c5d8929bb9f6969315cf4210bfe327dd0bc72
|
3 |
+
size 434219882
|
model_state_layer_4_TransformerLayer_adapter_embed.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:36242c30fb06de70fe7a674fbf2b8aef6291f837847e90b365d58f9314ca2345
|
3 |
+
size 42469864
|
model_state_layer_5_TransformerLayer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a4b77dab79cedd475c6335c22188eefd71bcb07cf39a11d8f80deb7b678f2ac
|
3 |
+
size 434219882
|
model_state_layer_5_TransformerLayer_adapter_embed.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:25e9e8c698d343cfd55e21e113ade823149883e63fe38b0c550e061c28acff54
|
3 |
+
size 42469864
|