Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +0 -0
- model_config.yaml +232 -0
- model_weights/common.pt +3 -0
- model_weights/metadata.json +1 -0
- model_weights/model.decoder.final_layernorm.weight/.zarray +14 -0
- model_weights/model.decoder.final_layernorm.weight/0 +0 -0
- model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_0_80.pt +3 -0
- model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_10_80.pt +3 -0
- model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_11_80.pt +3 -0
- model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_12_80.pt +3 -0
- model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_13_80.pt +3 -0
- model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_14_80.pt +3 -0
- model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_15_80.pt +3 -0
- model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_16_80.pt +3 -0
- model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_17_80.pt +3 -0
- model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_18_80.pt +3 -0
- model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_19_80.pt +3 -0
- model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_1_80.pt +3 -0
- model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_20_80.pt +3 -0
- model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_21_80.pt +3 -0
- model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_22_80.pt +3 -0
- model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_23_80.pt +3 -0
- model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_24_80.pt +3 -0
- model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_25_80.pt +3 -0
- model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_26_80.pt +3 -0
- model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_27_80.pt +3 -0
- model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_28_80.pt +3 -0
- model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_29_80.pt +3 -0
- model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_2_80.pt +3 -0
- model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_30_80.pt +3 -0
- model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_31_80.pt +3 -0
- model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_32_80.pt +3 -0
- model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_33_80.pt +3 -0
- model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_34_80.pt +3 -0
- model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_35_80.pt +3 -0
- model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_36_80.pt +3 -0
- model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_37_80.pt +3 -0
- model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_38_80.pt +3 -0
- model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_39_80.pt +3 -0
- model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_3_80.pt +3 -0
- model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_40_80.pt +3 -0
- model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_41_80.pt +3 -0
- model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_42_80.pt +3 -0
- model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_43_80.pt +3 -0
- model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_44_80.pt +3 -0
- model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_45_80.pt +3 -0
- model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_46_80.pt +3 -0
- model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_47_80.pt +3 -0
- model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_48_80.pt +3 -0
- model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_49_80.pt +3 -0
.gitattributes
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
model_config.yaml
ADDED
@@ -0,0 +1,232 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
mcore_gpt: true
|
2 |
+
micro_batch_size: 1
|
3 |
+
global_batch_size: 128
|
4 |
+
tensor_model_parallel_size: 8
|
5 |
+
pipeline_model_parallel_size: 1
|
6 |
+
virtual_pipeline_model_parallel_size: null
|
7 |
+
encoder_seq_length: 8192
|
8 |
+
max_position_embeddings: 8192
|
9 |
+
num_layers: 80
|
10 |
+
hidden_size: 8192
|
11 |
+
ffn_hidden_size: 28672
|
12 |
+
num_attention_heads: 64
|
13 |
+
init_method_std: 0.02
|
14 |
+
use_scaled_init_method: true
|
15 |
+
hidden_dropout: 0.0
|
16 |
+
attention_dropout: 0.0
|
17 |
+
ffn_dropout: 0.0
|
18 |
+
kv_channels: null
|
19 |
+
apply_query_key_layer_scaling: true
|
20 |
+
normalization: rmsnorm
|
21 |
+
layernorm_epsilon: 1.0e-05
|
22 |
+
do_layer_norm_weight_decay: false
|
23 |
+
make_vocab_size_divisible_by: 128
|
24 |
+
pre_process: true
|
25 |
+
post_process: true
|
26 |
+
persist_layer_norm: true
|
27 |
+
bias: false
|
28 |
+
activation: fast-swiglu
|
29 |
+
headscale: false
|
30 |
+
transformer_block_type: pre_ln
|
31 |
+
openai_gelu: false
|
32 |
+
normalize_attention_scores: true
|
33 |
+
position_embedding_type: rope
|
34 |
+
rotary_percentage: 1.0
|
35 |
+
attention_type: multihead
|
36 |
+
share_embeddings_and_output_weights: false
|
37 |
+
overlap_p2p_comm: false
|
38 |
+
batch_p2p_comm: true
|
39 |
+
num_query_groups: 8
|
40 |
+
tokenizer:
|
41 |
+
library: huggingface
|
42 |
+
type: meta-llama/Meta-Llama-3-70B
|
43 |
+
model: /dataset/models/llama2-13b/llama-tokenizer.model
|
44 |
+
vocab_file: null
|
45 |
+
merge_file: null
|
46 |
+
tokenizer_model: /dataset/models/llama2-13b/llama-tokenizer.model
|
47 |
+
sentencepiece_legacy: false
|
48 |
+
use_fast: true
|
49 |
+
native_amp_init_scale: 4294967296
|
50 |
+
native_amp_growth_interval: 1000
|
51 |
+
hysteresis: 2
|
52 |
+
fp32_residual_connection: false
|
53 |
+
fp16_lm_cross_entropy: false
|
54 |
+
megatron_amp_O2: true
|
55 |
+
grad_allreduce_chunk_size_mb: 125
|
56 |
+
grad_div_ar_fusion: true
|
57 |
+
gradient_accumulation_fusion: false
|
58 |
+
bias_activation_fusion: false
|
59 |
+
bias_dropout_add_fusion: false
|
60 |
+
masked_softmax_fusion: true
|
61 |
+
get_attention_mask_from_fusion: true
|
62 |
+
apply_rope_fusion: false
|
63 |
+
seed: 1234
|
64 |
+
resume_from_checkpoint: null
|
65 |
+
use_cpu_initialization: false
|
66 |
+
onnx_safe: false
|
67 |
+
apex_transformer_log_level: 30
|
68 |
+
gradient_as_bucket_view: false
|
69 |
+
sync_batch_comm: false
|
70 |
+
activations_checkpoint_granularity: null
|
71 |
+
activations_checkpoint_method: null
|
72 |
+
activations_checkpoint_num_layers: null
|
73 |
+
num_micro_batches_with_partial_activation_checkpoints: null
|
74 |
+
activations_checkpoint_layers_per_pipeline: null
|
75 |
+
sequence_parallel: false
|
76 |
+
transformer_engine: true
|
77 |
+
fp8: false
|
78 |
+
fp8_e4m3: false
|
79 |
+
fp8_hybrid: true
|
80 |
+
fp8_margin: 0
|
81 |
+
fp8_interval: 1
|
82 |
+
fp8_amax_history_len: 1024
|
83 |
+
fp8_amax_compute_algo: max
|
84 |
+
reduce_amax: true
|
85 |
+
use_emha: false
|
86 |
+
data:
|
87 |
+
chat: true
|
88 |
+
chat_prompt_tokens:
|
89 |
+
system_turn_start: <extra_id_0>
|
90 |
+
turn_start: <extra_id_1>
|
91 |
+
label_start: <extra_id_2>
|
92 |
+
end_of_turn: '
|
93 |
+
|
94 |
+
'
|
95 |
+
end_of_name: '
|
96 |
+
|
97 |
+
'
|
98 |
+
steerlm2_weight_micro_batch_size: 1
|
99 |
+
steerlm2_micro_batch_size: 1
|
100 |
+
sample: true
|
101 |
+
num_workers: 0
|
102 |
+
dataloader_type: single
|
103 |
+
train_ds:
|
104 |
+
file_path: /dataset/output_daring_anteater_2k_v2_full_clean.jsonl
|
105 |
+
global_batch_size: 128
|
106 |
+
micro_batch_size: 1
|
107 |
+
shuffle: true
|
108 |
+
memmap_workers: null
|
109 |
+
max_seq_length: 4096
|
110 |
+
min_seq_length: 1
|
111 |
+
drop_last: true
|
112 |
+
label_key: output
|
113 |
+
add_eos: false
|
114 |
+
add_sep: false
|
115 |
+
add_bos: false
|
116 |
+
truncation_field: input
|
117 |
+
index_mapping_dir: /indexmap_dir
|
118 |
+
prompt_template: '<extra_id_0>System
|
119 |
+
|
120 |
+
{system message}
|
121 |
+
|
122 |
+
<extra_id_1>User
|
123 |
+
|
124 |
+
{turn 1 user message}
|
125 |
+
|
126 |
+
<extra_id_1>Assistant
|
127 |
+
|
128 |
+
<extra_id_2>{turn 1 assistant label}
|
129 |
+
|
130 |
+
{turn 1 assistant message}
|
131 |
+
|
132 |
+
<extra_id_1>User
|
133 |
+
|
134 |
+
{turn 2 user message}
|
135 |
+
|
136 |
+
<extra_id_1>Assistant
|
137 |
+
|
138 |
+
<extra_id_2>{turn 2 assistant label}
|
139 |
+
|
140 |
+
{turn 2 assistant message}
|
141 |
+
|
142 |
+
<extra_id_1>'
|
143 |
+
hf_dataset: true
|
144 |
+
truncation_method: right
|
145 |
+
validation_ds:
|
146 |
+
file_path: /dataset/output_daring_anteater_2k_v2_full_clean.jsonl
|
147 |
+
global_batch_size: 128
|
148 |
+
micro_batch_size: 1
|
149 |
+
shuffle: false
|
150 |
+
memmap_workers: null
|
151 |
+
max_seq_length: 4096
|
152 |
+
min_seq_length: 1
|
153 |
+
drop_last: true
|
154 |
+
label_key: output
|
155 |
+
add_eos: false
|
156 |
+
add_sep: false
|
157 |
+
add_bos: false
|
158 |
+
truncation_field: input
|
159 |
+
index_mapping_dir: /indexmap_dir
|
160 |
+
prompt_template: '<extra_id_0>System
|
161 |
+
|
162 |
+
{system message}
|
163 |
+
|
164 |
+
<extra_id_1>User
|
165 |
+
|
166 |
+
{turn 1 user message}
|
167 |
+
|
168 |
+
<extra_id_1>Assistant
|
169 |
+
|
170 |
+
<extra_id_2>{turn 1 assistant label}
|
171 |
+
|
172 |
+
{turn 1 assistant message}
|
173 |
+
|
174 |
+
<extra_id_1>User
|
175 |
+
|
176 |
+
{turn 2 user message}
|
177 |
+
|
178 |
+
<extra_id_1>Assistant
|
179 |
+
|
180 |
+
<extra_id_2>{turn 2 assistant label}
|
181 |
+
|
182 |
+
{turn 2 assistant message}
|
183 |
+
|
184 |
+
<extra_id_1>'
|
185 |
+
hf_dataset: true
|
186 |
+
truncation_method: right
|
187 |
+
output_original_text: true
|
188 |
+
nsys_profile:
|
189 |
+
enabled: false
|
190 |
+
start_step: 10
|
191 |
+
end_step: 10
|
192 |
+
ranks:
|
193 |
+
- 0
|
194 |
+
gen_shape: false
|
195 |
+
optim:
|
196 |
+
name: distributed_fused_adam
|
197 |
+
lr: 1.03e-07
|
198 |
+
weight_decay: 0.01
|
199 |
+
betas:
|
200 |
+
- 0.9
|
201 |
+
- 0.98
|
202 |
+
sched:
|
203 |
+
name: CosineAnnealing
|
204 |
+
warmup_steps: 1
|
205 |
+
constant_steps: 300
|
206 |
+
min_lr: 1.02e-07
|
207 |
+
bucket_cap_mb: 200
|
208 |
+
overlap_grad_sync: false
|
209 |
+
contiguous_grad_buffer: true
|
210 |
+
rotary_base: 500000.0
|
211 |
+
precision: bf16-mixed
|
212 |
+
target: nemo_aligner.models.nlp.gpt.gpt_sft_model.GPTSFTModel
|
213 |
+
nemo_version: 1.23.0rc0
|
214 |
+
answer_only_loss: true
|
215 |
+
restore_from_path: /models/unpack_70b_daring_anteater_20k_full_1e-7_small_gbs_100
|
216 |
+
save_nemo_on_validation_end: true
|
217 |
+
use_flash_attention: null
|
218 |
+
pipeline_model_parallel_split_rank: 0
|
219 |
+
peft:
|
220 |
+
peft_scheme: none
|
221 |
+
restore_from_path: null
|
222 |
+
lora_tuning:
|
223 |
+
target_modules:
|
224 |
+
- attention_qkv
|
225 |
+
adapter_dim: 32
|
226 |
+
adapter_dropout: 0.0
|
227 |
+
column_init_method: xavier
|
228 |
+
row_init_method: zero
|
229 |
+
layer_selection: null
|
230 |
+
weight_tying: false
|
231 |
+
position_embedding_strategy: null
|
232 |
+
inference: {}
|
model_weights/common.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e4e4090fa34d96307127606cccef3ae99aedae58279e8bdf1746d44d3bf7aa47
|
3 |
+
size 860
|
model_weights/metadata.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"sharded_backend": "zarr", "sharded_backend_version": 1, "common_backend": "torch", "common_backend_version": 1}
|
model_weights/model.decoder.final_layernorm.weight/.zarray
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"chunks": [
|
3 |
+
8192
|
4 |
+
],
|
5 |
+
"compressor": null,
|
6 |
+
"dtype": "bfloat16",
|
7 |
+
"fill_value": null,
|
8 |
+
"filters": null,
|
9 |
+
"order": "C",
|
10 |
+
"shape": [
|
11 |
+
8192
|
12 |
+
],
|
13 |
+
"zarr_format": 2
|
14 |
+
}
|
model_weights/model.decoder.final_layernorm.weight/0
ADDED
Binary file (16.4 kB). View file
|
|
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_0_80.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e9a729975a47eb62643f3ac6a8bf145c719b877b2ce5b967be11c2b18801913
|
3 |
+
size 1836
|
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_10_80.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:faac9f0f6c1329624b1cad1daa596a7833bf7475949da3e7e4ec86709dca4952
|
3 |
+
size 1840
|
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_11_80.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:158179c28c9e196e80f0eb646eb219fce5fff77cd50a03ab445e028d2ac8bf76
|
3 |
+
size 1840
|
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_12_80.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:87fe00dd30d5e94f76b7c60e50c4fac2b19594743a26da4d5081a1d56fa54c47
|
3 |
+
size 1840
|
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_13_80.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c9a51a0705943fe66ca2db9ac36923dee52b1dadb1b32efcf1c50c1e62eb54f0
|
3 |
+
size 1840
|
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_14_80.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d96cc54ddbca63e537764caffb8b3602a65f652827354e19907c5980de821b9
|
3 |
+
size 1840
|
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_15_80.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:41cb45e944859eb6dcedcd8e7e56c7332ae31753f6daa3f61289ca04368db067
|
3 |
+
size 1840
|
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_16_80.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:34e4d66af34f6390b2bc1b83973f1ebe6ad6b32b391e0f1795f426ddcbdda783
|
3 |
+
size 1840
|
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_17_80.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e5732c2a0c0f07c0d4d11616be40ad87ac2a80986400cdc1f7d55a98f1d094d4
|
3 |
+
size 1840
|
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_18_80.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:66833ba47bee314a4c94098e985aa831ca98533ee2ec794b1c5dd95149f9f82c
|
3 |
+
size 1840
|
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_19_80.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:01b45b3f4ef6b69193217eb1bbdd50781c76efcb176194b72f28b2caeb617799
|
3 |
+
size 1840
|
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_1_80.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:15b6735d1668ebc2574d56235fd254e7c2977a571e8b2aa717f53158adaa76b8
|
3 |
+
size 1836
|
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_20_80.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:27682c2cd23ed3f1a7a3a5d40c5c84f0ac24ff07e1528665e3574d52ea707d71
|
3 |
+
size 1840
|
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_21_80.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:040aa73c2be92a7ed400cac3319ef89eede969f585b0e12c2cddd9c01800f2cc
|
3 |
+
size 1840
|
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_22_80.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:02368a8b8351735ecb4d892cea21dea8c5cbaee51e9ab6e0f42994c093e42f53
|
3 |
+
size 1840
|
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_23_80.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b738c1a25114960e407fa1d35e3417e1b9f9e4a5d4d7e45c777f4ddffaa24a2b
|
3 |
+
size 1840
|
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_24_80.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c72f2341f3ef6ebc07f2d7f409c29e85a27730089b09fd2c30e2cc1c9e30b17b
|
3 |
+
size 1840
|
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_25_80.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e5130873b235257ae1630a2f83dfb3bfb073e49d469ad1e802cbe797fb4ea1bb
|
3 |
+
size 1840
|
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_26_80.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:249b210a061b725c547cb1855b4afd0feaef02593d6e8c371fc8d96c7ae019f4
|
3 |
+
size 1840
|
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_27_80.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1266642f65d8d695707e2eaa9631ea2472f16f4f97d3e22e0065da6875daf252
|
3 |
+
size 1840
|
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_28_80.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e5b09e3f9f634bf19a80bb9abb0b45f49ee4b3c7f007e35cd8e7925daabbe32
|
3 |
+
size 1840
|
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_29_80.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ba77cb7bb7ee730d9e91fe35e1084a89c45eb32ff363a94133b8f30c50c229f1
|
3 |
+
size 1840
|
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_2_80.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:026af90a314db680105fea6a1aae98989ebe2d6f52eaf062006550d077bda05a
|
3 |
+
size 1836
|
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_30_80.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:78b87e344c6ce15fc3190ed5741823cc913defc8da276302cd704de63ddf3f85
|
3 |
+
size 1840
|
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_31_80.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ae569fddb6d7b9d201e4e935ea33b736dee2487c533fe330b1f4b20edbf0175
|
3 |
+
size 1840
|
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_32_80.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:433659103399b2f5ea6533ab08d9cd213c58e13501de3f3f049a84b8d7a58ac0
|
3 |
+
size 1840
|
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_33_80.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f9169d2efa0cc9cc2c46021569a1140179409233c658576499376f5db9d1d8c8
|
3 |
+
size 1840
|
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_34_80.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:abebd91eaa58bf1577d69ce1c0bfb8b91f05002d3b26edf434c0b7eb55f7475d
|
3 |
+
size 1840
|
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_35_80.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c3d95be77323d1eb8c0716e39d9ddb8d06cfa3cda9c5189d82afb91e459a9146
|
3 |
+
size 1840
|
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_36_80.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e38c7ed5c1127ea72da184b561f154c2393e512769ee59e77512c6c85f7517a7
|
3 |
+
size 1840
|
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_37_80.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dc79248144069a2751c43f604917cca98519c9fe514dd53be67d2a955d48c7b1
|
3 |
+
size 1840
|
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_38_80.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c894260cb35b9c59a8501e743bee84de53188279a4d31791f63a33f4ad56f229
|
3 |
+
size 1840
|
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_39_80.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ed58173cd24c9b37daef9ef2c3ceac4da6f2927c2320d3eefb3c222b6b68d8f6
|
3 |
+
size 1840
|
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_3_80.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:28ae5501b97631ba9aff2524f117edd3eb863dfebb29395610f689c851282d58
|
3 |
+
size 1836
|
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_40_80.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:01530e6ee0f9dd2007409746855c10469ff5e93da59ccc5eb4e678cd478a9c17
|
3 |
+
size 1840
|
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_41_80.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3477e4945e17e402f8190e1d9937627097783ba125917bb0df1760ed25844bda
|
3 |
+
size 1840
|
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_42_80.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a7f9dcbf8f93adbcf221e0ae8117118a069ce4eadeb0c11cc44cf661eb1c860f
|
3 |
+
size 1840
|
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_43_80.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:74147b0cf9114f4966c081b94393a9ada2b3fc27eed18e0ac34d580ed8f5d2d2
|
3 |
+
size 1840
|
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_44_80.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2bc4cbaf569529f6b36bfc4ab323c0581d32135a021837ee0e932ff41f1c5e42
|
3 |
+
size 1840
|
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_45_80.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:56f96e00f6542f620b6ee51e64bc9aa76e3907c9e117e27825af4ef10f4d3cd7
|
3 |
+
size 1840
|
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_46_80.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:36515ee57e2e8b16b0ee22dc8b9176a29aa212a901eadb82a6d133c2487939b9
|
3 |
+
size 1840
|
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_47_80.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ce91aff8cb5ebdeeb73dd871ed4aa4b19efb94861f55757cfc2d3ebb037dca78
|
3 |
+
size 1840
|
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_48_80.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bc878f893ca0b2bd6a4556a1b8ef3e13dabbf7c2001e556a4939383886e2f857
|
3 |
+
size 1840
|
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_49_80.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9187866aa84481d462ec5d43082b88c1c92363c6207de7a1a7b43a7744b2fda6
|
3 |
+
size 1840
|