34245A0131EAF5C7@tum.de commited on
Commit ·
f156ce5
1
Parent(s): aa1bfa9
MoReS-rank4-r4l5 for tinyllava_phi2
Browse files- added_tokens.json +40 -0
- config.json +64 -0
- connector/pytorch_model.bin +3 -0
- language_model/config.json +30 -0
- language_model/pytorch_model.bin +3 -0
- merges.txt +0 -0
- mores/language_model/config.json +622 -0
- mores/language_model/intervention_config.json +356 -0
- mores/language_model/intkey_layer.0.comp.block_output.unit.pos.nunit.1#0.bin +3 -0
- mores/language_model/intkey_layer.1.comp.block_output.unit.pos.nunit.1#0.bin +3 -0
- mores/language_model/intkey_layer.10.comp.block_output.unit.pos.nunit.1#0.bin +3 -0
- mores/language_model/intkey_layer.11.comp.block_output.unit.pos.nunit.1#0.bin +3 -0
- mores/language_model/intkey_layer.12.comp.block_output.unit.pos.nunit.1#0.bin +3 -0
- mores/language_model/intkey_layer.13.comp.block_output.unit.pos.nunit.1#0.bin +3 -0
- mores/language_model/intkey_layer.14.comp.block_output.unit.pos.nunit.1#0.bin +3 -0
- mores/language_model/intkey_layer.15.comp.block_output.unit.pos.nunit.1#0.bin +3 -0
- mores/language_model/intkey_layer.16.comp.block_output.unit.pos.nunit.1#0.bin +3 -0
- mores/language_model/intkey_layer.17.comp.block_output.unit.pos.nunit.1#0.bin +3 -0
- mores/language_model/intkey_layer.18.comp.block_output.unit.pos.nunit.1#0.bin +3 -0
- mores/language_model/intkey_layer.19.comp.block_output.unit.pos.nunit.1#0.bin +3 -0
- mores/language_model/intkey_layer.2.comp.block_output.unit.pos.nunit.1#0.bin +3 -0
- mores/language_model/intkey_layer.20.comp.block_output.unit.pos.nunit.1#0.bin +3 -0
- mores/language_model/intkey_layer.21.comp.block_output.unit.pos.nunit.1#0.bin +3 -0
- mores/language_model/intkey_layer.22.comp.block_output.unit.pos.nunit.1#0.bin +3 -0
- mores/language_model/intkey_layer.23.comp.block_output.unit.pos.nunit.1#0.bin +3 -0
- mores/language_model/intkey_layer.24.comp.block_output.unit.pos.nunit.1#0.bin +3 -0
- mores/language_model/intkey_layer.25.comp.block_output.unit.pos.nunit.1#0.bin +3 -0
- mores/language_model/intkey_layer.26.comp.block_output.unit.pos.nunit.1#0.bin +3 -0
- mores/language_model/intkey_layer.27.comp.block_output.unit.pos.nunit.1#0.bin +3 -0
- mores/language_model/intkey_layer.28.comp.block_output.unit.pos.nunit.1#0.bin +3 -0
- mores/language_model/intkey_layer.29.comp.block_output.unit.pos.nunit.1#0.bin +3 -0
- mores/language_model/intkey_layer.3.comp.block_output.unit.pos.nunit.1#0.bin +3 -0
- mores/language_model/intkey_layer.30.comp.block_output.unit.pos.nunit.1#0.bin +3 -0
- mores/language_model/intkey_layer.31.comp.block_output.unit.pos.nunit.1#0.bin +3 -0
- mores/language_model/intkey_layer.4.comp.block_output.unit.pos.nunit.1#0.bin +3 -0
- mores/language_model/intkey_layer.5.comp.block_output.unit.pos.nunit.1#0.bin +3 -0
- mores/language_model/intkey_layer.6.comp.block_output.unit.pos.nunit.1#0.bin +3 -0
- mores/language_model/intkey_layer.7.comp.block_output.unit.pos.nunit.1#0.bin +3 -0
- mores/language_model/intkey_layer.8.comp.block_output.unit.pos.nunit.1#0.bin +3 -0
- mores/language_model/intkey_layer.9.comp.block_output.unit.pos.nunit.1#0.bin +3 -0
- mores/language_model/mores_pos_configs.json +10 -0
- special_tokens_map.json +24 -0
- tokenizer_config.json +327 -0
- trainer_state.json +0 -0
- vision_tower/config.json +16 -0
- vision_tower/pytorch_model.bin +3 -0
- vocab.json +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"\t\t": 50294,
|
| 3 |
+
"\t\t\t": 50293,
|
| 4 |
+
"\t\t\t\t": 50292,
|
| 5 |
+
"\t\t\t\t\t": 50291,
|
| 6 |
+
"\t\t\t\t\t\t": 50290,
|
| 7 |
+
"\t\t\t\t\t\t\t": 50289,
|
| 8 |
+
"\t\t\t\t\t\t\t\t": 50288,
|
| 9 |
+
"\t\t\t\t\t\t\t\t\t": 50287,
|
| 10 |
+
" ": 50286,
|
| 11 |
+
" ": 50285,
|
| 12 |
+
" ": 50284,
|
| 13 |
+
" ": 50283,
|
| 14 |
+
" ": 50282,
|
| 15 |
+
" ": 50281,
|
| 16 |
+
" ": 50280,
|
| 17 |
+
" ": 50279,
|
| 18 |
+
" ": 50278,
|
| 19 |
+
" ": 50277,
|
| 20 |
+
" ": 50276,
|
| 21 |
+
" ": 50275,
|
| 22 |
+
" ": 50274,
|
| 23 |
+
" ": 50273,
|
| 24 |
+
" ": 50272,
|
| 25 |
+
" ": 50271,
|
| 26 |
+
" ": 50270,
|
| 27 |
+
" ": 50269,
|
| 28 |
+
" ": 50268,
|
| 29 |
+
" ": 50267,
|
| 30 |
+
" ": 50266,
|
| 31 |
+
" ": 50265,
|
| 32 |
+
" ": 50264,
|
| 33 |
+
" ": 50263,
|
| 34 |
+
" ": 50262,
|
| 35 |
+
" ": 50261,
|
| 36 |
+
" ": 50260,
|
| 37 |
+
" ": 50259,
|
| 38 |
+
" ": 50258,
|
| 39 |
+
" ": 50257
|
| 40 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cache_dir": null,
|
| 3 |
+
"connector_type": "mlp2x_gelu",
|
| 4 |
+
"hidden_size": 2560,
|
| 5 |
+
"ignore_index": -100,
|
| 6 |
+
"image_aspect_ratio": "square",
|
| 7 |
+
"image_token_index": -200,
|
| 8 |
+
"llm_model_name_or_path": "microsoft/phi-2",
|
| 9 |
+
"model_type": "tinyllava",
|
| 10 |
+
"num_queries": 128,
|
| 11 |
+
"num_resampler_layers": 3,
|
| 12 |
+
"pad_token": "<|endoftext|>",
|
| 13 |
+
"pad_token_id": 50256,
|
| 14 |
+
"resampler_hidden_size": 768,
|
| 15 |
+
"text_config": {
|
| 16 |
+
"_name_or_path": "microsoft/phi-2",
|
| 17 |
+
"architectures": [
|
| 18 |
+
"PhiForCausalLM"
|
| 19 |
+
],
|
| 20 |
+
"bos_token_id": 50256,
|
| 21 |
+
"embd_pdrop": 0.0,
|
| 22 |
+
"eos_token_id": 50256,
|
| 23 |
+
"hidden_act": "gelu_new",
|
| 24 |
+
"hidden_size": 2560,
|
| 25 |
+
"intermediate_size": 10240,
|
| 26 |
+
"layer_norm_eps": 1e-05,
|
| 27 |
+
"model_type": "phi",
|
| 28 |
+
"num_hidden_layers": 32,
|
| 29 |
+
"partial_rotary_factor": 0.4,
|
| 30 |
+
"qk_layernorm": false,
|
| 31 |
+
"resid_pdrop": 0.1,
|
| 32 |
+
"torch_dtype": "float16",
|
| 33 |
+
"vocab_size": 51200
|
| 34 |
+
},
|
| 35 |
+
"tokenizer_model_max_length": 3072,
|
| 36 |
+
"tokenizer_name_or_path": "microsoft/phi-2",
|
| 37 |
+
"tokenizer_padding_side": "right",
|
| 38 |
+
"tokenizer_use_fast": false,
|
| 39 |
+
"transformers_version": "4.39.3",
|
| 40 |
+
"tune_type_connector": "full",
|
| 41 |
+
"tune_type_llm": "mores",
|
| 42 |
+
"tune_type_vision_tower": "frozen",
|
| 43 |
+
"tune_vision_tower_from_layer": 0,
|
| 44 |
+
"use_cache": true,
|
| 45 |
+
"vision_config": {
|
| 46 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 47 |
+
"hidden_size": 1152,
|
| 48 |
+
"image_size": 384,
|
| 49 |
+
"intermediate_size": 4304,
|
| 50 |
+
"layer_norm_eps": 1e-06,
|
| 51 |
+
"model_name_or_path": "google/siglip-so400m-patch14-384",
|
| 52 |
+
"model_name_or_path2": "",
|
| 53 |
+
"model_type": "siglip_vision_model",
|
| 54 |
+
"num_attention_heads": 16,
|
| 55 |
+
"num_hidden_layers": 27,
|
| 56 |
+
"patch_size": 14
|
| 57 |
+
},
|
| 58 |
+
"vision_feature_layer": -2,
|
| 59 |
+
"vision_feature_select_strategy": "patch",
|
| 60 |
+
"vision_hidden_size": 1152,
|
| 61 |
+
"vision_model_name_or_path": "google/siglip-so400m-patch14-384",
|
| 62 |
+
"vision_model_name_or_path2": "",
|
| 63 |
+
"vocab_size": 51200
|
| 64 |
+
}
|
connector/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d5756ac422d84ce28962625b0d96d4e819a4e0bbe570d4c96aba11f7d166bac1
|
| 3 |
+
size 19017728
|
language_model/config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/phi-2",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"PhiForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 50256,
|
| 8 |
+
"embd_pdrop": 0.0,
|
| 9 |
+
"eos_token_id": 50256,
|
| 10 |
+
"hidden_act": "gelu_new",
|
| 11 |
+
"hidden_size": 2560,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 10240,
|
| 14 |
+
"layer_norm_eps": 1e-05,
|
| 15 |
+
"max_position_embeddings": 2048,
|
| 16 |
+
"model_type": "phi",
|
| 17 |
+
"num_attention_heads": 32,
|
| 18 |
+
"num_hidden_layers": 32,
|
| 19 |
+
"num_key_value_heads": 32,
|
| 20 |
+
"partial_rotary_factor": 0.4,
|
| 21 |
+
"qk_layernorm": false,
|
| 22 |
+
"resid_pdrop": 0.1,
|
| 23 |
+
"rope_scaling": null,
|
| 24 |
+
"rope_theta": 10000.0,
|
| 25 |
+
"tie_word_embeddings": false,
|
| 26 |
+
"torch_dtype": "float16",
|
| 27 |
+
"transformers_version": "4.39.3",
|
| 28 |
+
"use_cache": true,
|
| 29 |
+
"vocab_size": 51200
|
| 30 |
+
}
|
language_model/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0d9fddc56d9983857268436105a3544842bb8dcd6cb82bf0387bc88781c7da85
|
| 3 |
+
size 5559512874
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
mores/language_model/config.json
ADDED
|
@@ -0,0 +1,622 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"intervention_constant_sources": [
|
| 3 |
+
true,
|
| 4 |
+
true,
|
| 5 |
+
true,
|
| 6 |
+
true,
|
| 7 |
+
true,
|
| 8 |
+
true,
|
| 9 |
+
true,
|
| 10 |
+
true,
|
| 11 |
+
true,
|
| 12 |
+
true,
|
| 13 |
+
true,
|
| 14 |
+
true,
|
| 15 |
+
true,
|
| 16 |
+
true,
|
| 17 |
+
true,
|
| 18 |
+
true,
|
| 19 |
+
true,
|
| 20 |
+
true,
|
| 21 |
+
true,
|
| 22 |
+
true,
|
| 23 |
+
true,
|
| 24 |
+
true,
|
| 25 |
+
true,
|
| 26 |
+
true,
|
| 27 |
+
true,
|
| 28 |
+
true,
|
| 29 |
+
true,
|
| 30 |
+
true,
|
| 31 |
+
true,
|
| 32 |
+
true,
|
| 33 |
+
true,
|
| 34 |
+
true
|
| 35 |
+
],
|
| 36 |
+
"intervention_dimensions": [
|
| 37 |
+
2560,
|
| 38 |
+
2560,
|
| 39 |
+
2560,
|
| 40 |
+
2560,
|
| 41 |
+
2560,
|
| 42 |
+
2560,
|
| 43 |
+
2560,
|
| 44 |
+
2560,
|
| 45 |
+
2560,
|
| 46 |
+
2560,
|
| 47 |
+
2560,
|
| 48 |
+
2560,
|
| 49 |
+
2560,
|
| 50 |
+
2560,
|
| 51 |
+
2560,
|
| 52 |
+
2560,
|
| 53 |
+
2560,
|
| 54 |
+
2560,
|
| 55 |
+
2560,
|
| 56 |
+
2560,
|
| 57 |
+
2560,
|
| 58 |
+
2560,
|
| 59 |
+
2560,
|
| 60 |
+
2560,
|
| 61 |
+
2560,
|
| 62 |
+
2560,
|
| 63 |
+
2560,
|
| 64 |
+
2560,
|
| 65 |
+
2560,
|
| 66 |
+
2560,
|
| 67 |
+
2560,
|
| 68 |
+
2560
|
| 69 |
+
],
|
| 70 |
+
"intervention_types": [
|
| 71 |
+
"<class 'tinyllava.model.intervention_models.MoReSIntervention'>",
|
| 72 |
+
"<class 'tinyllava.model.intervention_models.MoReSIntervention'>",
|
| 73 |
+
"<class 'tinyllava.model.intervention_models.MoReSIntervention'>",
|
| 74 |
+
"<class 'tinyllava.model.intervention_models.MoReSIntervention'>",
|
| 75 |
+
"<class 'tinyllava.model.intervention_models.MoReSIntervention'>",
|
| 76 |
+
"<class 'tinyllava.model.intervention_models.MoReSIntervention'>",
|
| 77 |
+
"<class 'tinyllava.model.intervention_models.MoReSIntervention'>",
|
| 78 |
+
"<class 'tinyllava.model.intervention_models.MoReSIntervention'>",
|
| 79 |
+
"<class 'tinyllava.model.intervention_models.MoReSIntervention'>",
|
| 80 |
+
"<class 'tinyllava.model.intervention_models.MoReSIntervention'>",
|
| 81 |
+
"<class 'tinyllava.model.intervention_models.MoReSIntervention'>",
|
| 82 |
+
"<class 'tinyllava.model.intervention_models.MoReSIntervention'>",
|
| 83 |
+
"<class 'tinyllava.model.intervention_models.MoReSIntervention'>",
|
| 84 |
+
"<class 'tinyllava.model.intervention_models.MoReSIntervention'>",
|
| 85 |
+
"<class 'tinyllava.model.intervention_models.MoReSIntervention'>",
|
| 86 |
+
"<class 'tinyllava.model.intervention_models.MoReSIntervention'>",
|
| 87 |
+
"<class 'tinyllava.model.intervention_models.MoReSIntervention'>",
|
| 88 |
+
"<class 'tinyllava.model.intervention_models.MoReSIntervention'>",
|
| 89 |
+
"<class 'tinyllava.model.intervention_models.MoReSIntervention'>",
|
| 90 |
+
"<class 'tinyllava.model.intervention_models.MoReSIntervention'>",
|
| 91 |
+
"<class 'tinyllava.model.intervention_models.MoReSIntervention'>",
|
| 92 |
+
"<class 'tinyllava.model.intervention_models.MoReSIntervention'>",
|
| 93 |
+
"<class 'tinyllava.model.intervention_models.MoReSIntervention'>",
|
| 94 |
+
"<class 'tinyllava.model.intervention_models.MoReSIntervention'>",
|
| 95 |
+
"<class 'tinyllava.model.intervention_models.MoReSIntervention'>",
|
| 96 |
+
"<class 'tinyllava.model.intervention_models.MoReSIntervention'>",
|
| 97 |
+
"<class 'tinyllava.model.intervention_models.MoReSIntervention'>",
|
| 98 |
+
"<class 'tinyllava.model.intervention_models.MoReSIntervention'>",
|
| 99 |
+
"<class 'tinyllava.model.intervention_models.MoReSIntervention'>",
|
| 100 |
+
"<class 'tinyllava.model.intervention_models.MoReSIntervention'>",
|
| 101 |
+
"<class 'tinyllava.model.intervention_models.MoReSIntervention'>",
|
| 102 |
+
"<class 'tinyllava.model.intervention_models.MoReSIntervention'>"
|
| 103 |
+
],
|
| 104 |
+
"mode": "parallel",
|
| 105 |
+
"representations": [
|
| 106 |
+
[
|
| 107 |
+
0,
|
| 108 |
+
"block_output",
|
| 109 |
+
"pos",
|
| 110 |
+
1,
|
| 111 |
+
4,
|
| 112 |
+
null,
|
| 113 |
+
null,
|
| 114 |
+
null,
|
| 115 |
+
null,
|
| 116 |
+
null,
|
| 117 |
+
null,
|
| 118 |
+
null,
|
| 119 |
+
null
|
| 120 |
+
],
|
| 121 |
+
[
|
| 122 |
+
1,
|
| 123 |
+
"block_output",
|
| 124 |
+
"pos",
|
| 125 |
+
1,
|
| 126 |
+
4,
|
| 127 |
+
null,
|
| 128 |
+
null,
|
| 129 |
+
null,
|
| 130 |
+
null,
|
| 131 |
+
null,
|
| 132 |
+
null,
|
| 133 |
+
null,
|
| 134 |
+
null
|
| 135 |
+
],
|
| 136 |
+
[
|
| 137 |
+
2,
|
| 138 |
+
"block_output",
|
| 139 |
+
"pos",
|
| 140 |
+
1,
|
| 141 |
+
4,
|
| 142 |
+
null,
|
| 143 |
+
null,
|
| 144 |
+
null,
|
| 145 |
+
null,
|
| 146 |
+
null,
|
| 147 |
+
null,
|
| 148 |
+
null,
|
| 149 |
+
null
|
| 150 |
+
],
|
| 151 |
+
[
|
| 152 |
+
3,
|
| 153 |
+
"block_output",
|
| 154 |
+
"pos",
|
| 155 |
+
1,
|
| 156 |
+
4,
|
| 157 |
+
null,
|
| 158 |
+
null,
|
| 159 |
+
null,
|
| 160 |
+
null,
|
| 161 |
+
null,
|
| 162 |
+
null,
|
| 163 |
+
null,
|
| 164 |
+
null
|
| 165 |
+
],
|
| 166 |
+
[
|
| 167 |
+
4,
|
| 168 |
+
"block_output",
|
| 169 |
+
"pos",
|
| 170 |
+
1,
|
| 171 |
+
4,
|
| 172 |
+
null,
|
| 173 |
+
null,
|
| 174 |
+
null,
|
| 175 |
+
null,
|
| 176 |
+
null,
|
| 177 |
+
null,
|
| 178 |
+
null,
|
| 179 |
+
null
|
| 180 |
+
],
|
| 181 |
+
[
|
| 182 |
+
5,
|
| 183 |
+
"block_output",
|
| 184 |
+
"pos",
|
| 185 |
+
1,
|
| 186 |
+
4,
|
| 187 |
+
null,
|
| 188 |
+
null,
|
| 189 |
+
null,
|
| 190 |
+
null,
|
| 191 |
+
null,
|
| 192 |
+
null,
|
| 193 |
+
null,
|
| 194 |
+
null
|
| 195 |
+
],
|
| 196 |
+
[
|
| 197 |
+
6,
|
| 198 |
+
"block_output",
|
| 199 |
+
"pos",
|
| 200 |
+
1,
|
| 201 |
+
4,
|
| 202 |
+
null,
|
| 203 |
+
null,
|
| 204 |
+
null,
|
| 205 |
+
null,
|
| 206 |
+
null,
|
| 207 |
+
null,
|
| 208 |
+
null,
|
| 209 |
+
null
|
| 210 |
+
],
|
| 211 |
+
[
|
| 212 |
+
7,
|
| 213 |
+
"block_output",
|
| 214 |
+
"pos",
|
| 215 |
+
1,
|
| 216 |
+
4,
|
| 217 |
+
null,
|
| 218 |
+
null,
|
| 219 |
+
null,
|
| 220 |
+
null,
|
| 221 |
+
null,
|
| 222 |
+
null,
|
| 223 |
+
null,
|
| 224 |
+
null
|
| 225 |
+
],
|
| 226 |
+
[
|
| 227 |
+
8,
|
| 228 |
+
"block_output",
|
| 229 |
+
"pos",
|
| 230 |
+
1,
|
| 231 |
+
4,
|
| 232 |
+
null,
|
| 233 |
+
null,
|
| 234 |
+
null,
|
| 235 |
+
null,
|
| 236 |
+
null,
|
| 237 |
+
null,
|
| 238 |
+
null,
|
| 239 |
+
null
|
| 240 |
+
],
|
| 241 |
+
[
|
| 242 |
+
9,
|
| 243 |
+
"block_output",
|
| 244 |
+
"pos",
|
| 245 |
+
1,
|
| 246 |
+
4,
|
| 247 |
+
null,
|
| 248 |
+
null,
|
| 249 |
+
null,
|
| 250 |
+
null,
|
| 251 |
+
null,
|
| 252 |
+
null,
|
| 253 |
+
null,
|
| 254 |
+
null
|
| 255 |
+
],
|
| 256 |
+
[
|
| 257 |
+
10,
|
| 258 |
+
"block_output",
|
| 259 |
+
"pos",
|
| 260 |
+
1,
|
| 261 |
+
4,
|
| 262 |
+
null,
|
| 263 |
+
null,
|
| 264 |
+
null,
|
| 265 |
+
null,
|
| 266 |
+
null,
|
| 267 |
+
null,
|
| 268 |
+
null,
|
| 269 |
+
null
|
| 270 |
+
],
|
| 271 |
+
[
|
| 272 |
+
11,
|
| 273 |
+
"block_output",
|
| 274 |
+
"pos",
|
| 275 |
+
1,
|
| 276 |
+
4,
|
| 277 |
+
null,
|
| 278 |
+
null,
|
| 279 |
+
null,
|
| 280 |
+
null,
|
| 281 |
+
null,
|
| 282 |
+
null,
|
| 283 |
+
null,
|
| 284 |
+
null
|
| 285 |
+
],
|
| 286 |
+
[
|
| 287 |
+
12,
|
| 288 |
+
"block_output",
|
| 289 |
+
"pos",
|
| 290 |
+
1,
|
| 291 |
+
4,
|
| 292 |
+
null,
|
| 293 |
+
null,
|
| 294 |
+
null,
|
| 295 |
+
null,
|
| 296 |
+
null,
|
| 297 |
+
null,
|
| 298 |
+
null,
|
| 299 |
+
null
|
| 300 |
+
],
|
| 301 |
+
[
|
| 302 |
+
13,
|
| 303 |
+
"block_output",
|
| 304 |
+
"pos",
|
| 305 |
+
1,
|
| 306 |
+
4,
|
| 307 |
+
null,
|
| 308 |
+
null,
|
| 309 |
+
null,
|
| 310 |
+
null,
|
| 311 |
+
null,
|
| 312 |
+
null,
|
| 313 |
+
null,
|
| 314 |
+
null
|
| 315 |
+
],
|
| 316 |
+
[
|
| 317 |
+
14,
|
| 318 |
+
"block_output",
|
| 319 |
+
"pos",
|
| 320 |
+
1,
|
| 321 |
+
4,
|
| 322 |
+
null,
|
| 323 |
+
null,
|
| 324 |
+
null,
|
| 325 |
+
null,
|
| 326 |
+
null,
|
| 327 |
+
null,
|
| 328 |
+
null,
|
| 329 |
+
null
|
| 330 |
+
],
|
| 331 |
+
[
|
| 332 |
+
15,
|
| 333 |
+
"block_output",
|
| 334 |
+
"pos",
|
| 335 |
+
1,
|
| 336 |
+
4,
|
| 337 |
+
null,
|
| 338 |
+
null,
|
| 339 |
+
null,
|
| 340 |
+
null,
|
| 341 |
+
null,
|
| 342 |
+
null,
|
| 343 |
+
null,
|
| 344 |
+
null
|
| 345 |
+
],
|
| 346 |
+
[
|
| 347 |
+
16,
|
| 348 |
+
"block_output",
|
| 349 |
+
"pos",
|
| 350 |
+
1,
|
| 351 |
+
4,
|
| 352 |
+
null,
|
| 353 |
+
null,
|
| 354 |
+
null,
|
| 355 |
+
null,
|
| 356 |
+
null,
|
| 357 |
+
null,
|
| 358 |
+
null,
|
| 359 |
+
null
|
| 360 |
+
],
|
| 361 |
+
[
|
| 362 |
+
17,
|
| 363 |
+
"block_output",
|
| 364 |
+
"pos",
|
| 365 |
+
1,
|
| 366 |
+
4,
|
| 367 |
+
null,
|
| 368 |
+
null,
|
| 369 |
+
null,
|
| 370 |
+
null,
|
| 371 |
+
null,
|
| 372 |
+
null,
|
| 373 |
+
null,
|
| 374 |
+
null
|
| 375 |
+
],
|
| 376 |
+
[
|
| 377 |
+
18,
|
| 378 |
+
"block_output",
|
| 379 |
+
"pos",
|
| 380 |
+
1,
|
| 381 |
+
4,
|
| 382 |
+
null,
|
| 383 |
+
null,
|
| 384 |
+
null,
|
| 385 |
+
null,
|
| 386 |
+
null,
|
| 387 |
+
null,
|
| 388 |
+
null,
|
| 389 |
+
null
|
| 390 |
+
],
|
| 391 |
+
[
|
| 392 |
+
19,
|
| 393 |
+
"block_output",
|
| 394 |
+
"pos",
|
| 395 |
+
1,
|
| 396 |
+
4,
|
| 397 |
+
null,
|
| 398 |
+
null,
|
| 399 |
+
null,
|
| 400 |
+
null,
|
| 401 |
+
null,
|
| 402 |
+
null,
|
| 403 |
+
null,
|
| 404 |
+
null
|
| 405 |
+
],
|
| 406 |
+
[
|
| 407 |
+
20,
|
| 408 |
+
"block_output",
|
| 409 |
+
"pos",
|
| 410 |
+
1,
|
| 411 |
+
4,
|
| 412 |
+
null,
|
| 413 |
+
null,
|
| 414 |
+
null,
|
| 415 |
+
null,
|
| 416 |
+
null,
|
| 417 |
+
null,
|
| 418 |
+
null,
|
| 419 |
+
null
|
| 420 |
+
],
|
| 421 |
+
[
|
| 422 |
+
21,
|
| 423 |
+
"block_output",
|
| 424 |
+
"pos",
|
| 425 |
+
1,
|
| 426 |
+
4,
|
| 427 |
+
null,
|
| 428 |
+
null,
|
| 429 |
+
null,
|
| 430 |
+
null,
|
| 431 |
+
null,
|
| 432 |
+
null,
|
| 433 |
+
null,
|
| 434 |
+
null
|
| 435 |
+
],
|
| 436 |
+
[
|
| 437 |
+
22,
|
| 438 |
+
"block_output",
|
| 439 |
+
"pos",
|
| 440 |
+
1,
|
| 441 |
+
4,
|
| 442 |
+
null,
|
| 443 |
+
null,
|
| 444 |
+
null,
|
| 445 |
+
null,
|
| 446 |
+
null,
|
| 447 |
+
null,
|
| 448 |
+
null,
|
| 449 |
+
null
|
| 450 |
+
],
|
| 451 |
+
[
|
| 452 |
+
23,
|
| 453 |
+
"block_output",
|
| 454 |
+
"pos",
|
| 455 |
+
1,
|
| 456 |
+
4,
|
| 457 |
+
null,
|
| 458 |
+
null,
|
| 459 |
+
null,
|
| 460 |
+
null,
|
| 461 |
+
null,
|
| 462 |
+
null,
|
| 463 |
+
null,
|
| 464 |
+
null
|
| 465 |
+
],
|
| 466 |
+
[
|
| 467 |
+
24,
|
| 468 |
+
"block_output",
|
| 469 |
+
"pos",
|
| 470 |
+
1,
|
| 471 |
+
4,
|
| 472 |
+
null,
|
| 473 |
+
null,
|
| 474 |
+
null,
|
| 475 |
+
null,
|
| 476 |
+
null,
|
| 477 |
+
null,
|
| 478 |
+
null,
|
| 479 |
+
null
|
| 480 |
+
],
|
| 481 |
+
[
|
| 482 |
+
25,
|
| 483 |
+
"block_output",
|
| 484 |
+
"pos",
|
| 485 |
+
1,
|
| 486 |
+
4,
|
| 487 |
+
null,
|
| 488 |
+
null,
|
| 489 |
+
null,
|
| 490 |
+
null,
|
| 491 |
+
null,
|
| 492 |
+
null,
|
| 493 |
+
null,
|
| 494 |
+
null
|
| 495 |
+
],
|
| 496 |
+
[
|
| 497 |
+
26,
|
| 498 |
+
"block_output",
|
| 499 |
+
"pos",
|
| 500 |
+
1,
|
| 501 |
+
4,
|
| 502 |
+
null,
|
| 503 |
+
null,
|
| 504 |
+
null,
|
| 505 |
+
null,
|
| 506 |
+
null,
|
| 507 |
+
null,
|
| 508 |
+
null,
|
| 509 |
+
null
|
| 510 |
+
],
|
| 511 |
+
[
|
| 512 |
+
27,
|
| 513 |
+
"block_output",
|
| 514 |
+
"pos",
|
| 515 |
+
1,
|
| 516 |
+
4,
|
| 517 |
+
null,
|
| 518 |
+
null,
|
| 519 |
+
null,
|
| 520 |
+
null,
|
| 521 |
+
null,
|
| 522 |
+
null,
|
| 523 |
+
null,
|
| 524 |
+
null
|
| 525 |
+
],
|
| 526 |
+
[
|
| 527 |
+
28,
|
| 528 |
+
"block_output",
|
| 529 |
+
"pos",
|
| 530 |
+
1,
|
| 531 |
+
4,
|
| 532 |
+
null,
|
| 533 |
+
null,
|
| 534 |
+
null,
|
| 535 |
+
null,
|
| 536 |
+
null,
|
| 537 |
+
null,
|
| 538 |
+
null,
|
| 539 |
+
null
|
| 540 |
+
],
|
| 541 |
+
[
|
| 542 |
+
29,
|
| 543 |
+
"block_output",
|
| 544 |
+
"pos",
|
| 545 |
+
1,
|
| 546 |
+
4,
|
| 547 |
+
null,
|
| 548 |
+
null,
|
| 549 |
+
null,
|
| 550 |
+
null,
|
| 551 |
+
null,
|
| 552 |
+
null,
|
| 553 |
+
null,
|
| 554 |
+
null
|
| 555 |
+
],
|
| 556 |
+
[
|
| 557 |
+
30,
|
| 558 |
+
"block_output",
|
| 559 |
+
"pos",
|
| 560 |
+
1,
|
| 561 |
+
4,
|
| 562 |
+
null,
|
| 563 |
+
null,
|
| 564 |
+
null,
|
| 565 |
+
null,
|
| 566 |
+
null,
|
| 567 |
+
null,
|
| 568 |
+
null,
|
| 569 |
+
null
|
| 570 |
+
],
|
| 571 |
+
[
|
| 572 |
+
31,
|
| 573 |
+
"block_output",
|
| 574 |
+
"pos",
|
| 575 |
+
1,
|
| 576 |
+
4,
|
| 577 |
+
null,
|
| 578 |
+
null,
|
| 579 |
+
null,
|
| 580 |
+
null,
|
| 581 |
+
null,
|
| 582 |
+
null,
|
| 583 |
+
null,
|
| 584 |
+
null
|
| 585 |
+
]
|
| 586 |
+
],
|
| 587 |
+
"sorted_keys": [
|
| 588 |
+
"layer.0.comp.block_output.unit.pos.nunit.1#0",
|
| 589 |
+
"layer.1.comp.block_output.unit.pos.nunit.1#0",
|
| 590 |
+
"layer.2.comp.block_output.unit.pos.nunit.1#0",
|
| 591 |
+
"layer.3.comp.block_output.unit.pos.nunit.1#0",
|
| 592 |
+
"layer.4.comp.block_output.unit.pos.nunit.1#0",
|
| 593 |
+
"layer.5.comp.block_output.unit.pos.nunit.1#0",
|
| 594 |
+
"layer.6.comp.block_output.unit.pos.nunit.1#0",
|
| 595 |
+
"layer.7.comp.block_output.unit.pos.nunit.1#0",
|
| 596 |
+
"layer.8.comp.block_output.unit.pos.nunit.1#0",
|
| 597 |
+
"layer.9.comp.block_output.unit.pos.nunit.1#0",
|
| 598 |
+
"layer.10.comp.block_output.unit.pos.nunit.1#0",
|
| 599 |
+
"layer.11.comp.block_output.unit.pos.nunit.1#0",
|
| 600 |
+
"layer.12.comp.block_output.unit.pos.nunit.1#0",
|
| 601 |
+
"layer.13.comp.block_output.unit.pos.nunit.1#0",
|
| 602 |
+
"layer.14.comp.block_output.unit.pos.nunit.1#0",
|
| 603 |
+
"layer.15.comp.block_output.unit.pos.nunit.1#0",
|
| 604 |
+
"layer.16.comp.block_output.unit.pos.nunit.1#0",
|
| 605 |
+
"layer.17.comp.block_output.unit.pos.nunit.1#0",
|
| 606 |
+
"layer.18.comp.block_output.unit.pos.nunit.1#0",
|
| 607 |
+
"layer.19.comp.block_output.unit.pos.nunit.1#0",
|
| 608 |
+
"layer.20.comp.block_output.unit.pos.nunit.1#0",
|
| 609 |
+
"layer.21.comp.block_output.unit.pos.nunit.1#0",
|
| 610 |
+
"layer.22.comp.block_output.unit.pos.nunit.1#0",
|
| 611 |
+
"layer.23.comp.block_output.unit.pos.nunit.1#0",
|
| 612 |
+
"layer.24.comp.block_output.unit.pos.nunit.1#0",
|
| 613 |
+
"layer.25.comp.block_output.unit.pos.nunit.1#0",
|
| 614 |
+
"layer.26.comp.block_output.unit.pos.nunit.1#0",
|
| 615 |
+
"layer.27.comp.block_output.unit.pos.nunit.1#0",
|
| 616 |
+
"layer.28.comp.block_output.unit.pos.nunit.1#0",
|
| 617 |
+
"layer.29.comp.block_output.unit.pos.nunit.1#0",
|
| 618 |
+
"layer.30.comp.block_output.unit.pos.nunit.1#0",
|
| 619 |
+
"layer.31.comp.block_output.unit.pos.nunit.1#0"
|
| 620 |
+
],
|
| 621 |
+
"transformers_version": "4.39.3"
|
| 622 |
+
}
|
mores/language_model/intervention_config.json
ADDED
|
@@ -0,0 +1,356 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"representations": [
|
| 3 |
+
{
|
| 4 |
+
"layer": 0,
|
| 5 |
+
"component": "block_output",
|
| 6 |
+
"low_rank_dimension": 4,
|
| 7 |
+
"intervention": {
|
| 8 |
+
"type": "mores",
|
| 9 |
+
"embed_dim": 2560,
|
| 10 |
+
"low_rank_dimension": 4,
|
| 11 |
+
"dropout": 0.05
|
| 12 |
+
}
|
| 13 |
+
},
|
| 14 |
+
{
|
| 15 |
+
"layer": 1,
|
| 16 |
+
"component": "block_output",
|
| 17 |
+
"low_rank_dimension": 4,
|
| 18 |
+
"intervention": {
|
| 19 |
+
"type": "mores",
|
| 20 |
+
"embed_dim": 2560,
|
| 21 |
+
"low_rank_dimension": 4,
|
| 22 |
+
"dropout": 0.05
|
| 23 |
+
}
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"layer": 2,
|
| 27 |
+
"component": "block_output",
|
| 28 |
+
"low_rank_dimension": 4,
|
| 29 |
+
"intervention": {
|
| 30 |
+
"type": "mores",
|
| 31 |
+
"embed_dim": 2560,
|
| 32 |
+
"low_rank_dimension": 4,
|
| 33 |
+
"dropout": 0.05
|
| 34 |
+
}
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"layer": 3,
|
| 38 |
+
"component": "block_output",
|
| 39 |
+
"low_rank_dimension": 4,
|
| 40 |
+
"intervention": {
|
| 41 |
+
"type": "mores",
|
| 42 |
+
"embed_dim": 2560,
|
| 43 |
+
"low_rank_dimension": 4,
|
| 44 |
+
"dropout": 0.05
|
| 45 |
+
}
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"layer": 4,
|
| 49 |
+
"component": "block_output",
|
| 50 |
+
"low_rank_dimension": 4,
|
| 51 |
+
"intervention": {
|
| 52 |
+
"type": "mores",
|
| 53 |
+
"embed_dim": 2560,
|
| 54 |
+
"low_rank_dimension": 4,
|
| 55 |
+
"dropout": 0.05
|
| 56 |
+
}
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"layer": 5,
|
| 60 |
+
"component": "block_output",
|
| 61 |
+
"low_rank_dimension": 4,
|
| 62 |
+
"intervention": {
|
| 63 |
+
"type": "mores",
|
| 64 |
+
"embed_dim": 2560,
|
| 65 |
+
"low_rank_dimension": 4,
|
| 66 |
+
"dropout": 0.05
|
| 67 |
+
}
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"layer": 6,
|
| 71 |
+
"component": "block_output",
|
| 72 |
+
"low_rank_dimension": 4,
|
| 73 |
+
"intervention": {
|
| 74 |
+
"type": "mores",
|
| 75 |
+
"embed_dim": 2560,
|
| 76 |
+
"low_rank_dimension": 4,
|
| 77 |
+
"dropout": 0.05
|
| 78 |
+
}
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"layer": 7,
|
| 82 |
+
"component": "block_output",
|
| 83 |
+
"low_rank_dimension": 4,
|
| 84 |
+
"intervention": {
|
| 85 |
+
"type": "mores",
|
| 86 |
+
"embed_dim": 2560,
|
| 87 |
+
"low_rank_dimension": 4,
|
| 88 |
+
"dropout": 0.05
|
| 89 |
+
}
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"layer": 8,
|
| 93 |
+
"component": "block_output",
|
| 94 |
+
"low_rank_dimension": 4,
|
| 95 |
+
"intervention": {
|
| 96 |
+
"type": "mores",
|
| 97 |
+
"embed_dim": 2560,
|
| 98 |
+
"low_rank_dimension": 4,
|
| 99 |
+
"dropout": 0.05
|
| 100 |
+
}
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"layer": 9,
|
| 104 |
+
"component": "block_output",
|
| 105 |
+
"low_rank_dimension": 4,
|
| 106 |
+
"intervention": {
|
| 107 |
+
"type": "mores",
|
| 108 |
+
"embed_dim": 2560,
|
| 109 |
+
"low_rank_dimension": 4,
|
| 110 |
+
"dropout": 0.05
|
| 111 |
+
}
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"layer": 10,
|
| 115 |
+
"component": "block_output",
|
| 116 |
+
"low_rank_dimension": 4,
|
| 117 |
+
"intervention": {
|
| 118 |
+
"type": "mores",
|
| 119 |
+
"embed_dim": 2560,
|
| 120 |
+
"low_rank_dimension": 4,
|
| 121 |
+
"dropout": 0.05
|
| 122 |
+
}
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"layer": 11,
|
| 126 |
+
"component": "block_output",
|
| 127 |
+
"low_rank_dimension": 4,
|
| 128 |
+
"intervention": {
|
| 129 |
+
"type": "mores",
|
| 130 |
+
"embed_dim": 2560,
|
| 131 |
+
"low_rank_dimension": 4,
|
| 132 |
+
"dropout": 0.05
|
| 133 |
+
}
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"layer": 12,
|
| 137 |
+
"component": "block_output",
|
| 138 |
+
"low_rank_dimension": 4,
|
| 139 |
+
"intervention": {
|
| 140 |
+
"type": "mores",
|
| 141 |
+
"embed_dim": 2560,
|
| 142 |
+
"low_rank_dimension": 4,
|
| 143 |
+
"dropout": 0.05
|
| 144 |
+
}
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"layer": 13,
|
| 148 |
+
"component": "block_output",
|
| 149 |
+
"low_rank_dimension": 4,
|
| 150 |
+
"intervention": {
|
| 151 |
+
"type": "mores",
|
| 152 |
+
"embed_dim": 2560,
|
| 153 |
+
"low_rank_dimension": 4,
|
| 154 |
+
"dropout": 0.05
|
| 155 |
+
}
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"layer": 14,
|
| 159 |
+
"component": "block_output",
|
| 160 |
+
"low_rank_dimension": 4,
|
| 161 |
+
"intervention": {
|
| 162 |
+
"type": "mores",
|
| 163 |
+
"embed_dim": 2560,
|
| 164 |
+
"low_rank_dimension": 4,
|
| 165 |
+
"dropout": 0.05
|
| 166 |
+
}
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"layer": 15,
|
| 170 |
+
"component": "block_output",
|
| 171 |
+
"low_rank_dimension": 4,
|
| 172 |
+
"intervention": {
|
| 173 |
+
"type": "mores",
|
| 174 |
+
"embed_dim": 2560,
|
| 175 |
+
"low_rank_dimension": 4,
|
| 176 |
+
"dropout": 0.05
|
| 177 |
+
}
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"layer": 16,
|
| 181 |
+
"component": "block_output",
|
| 182 |
+
"low_rank_dimension": 4,
|
| 183 |
+
"intervention": {
|
| 184 |
+
"type": "mores",
|
| 185 |
+
"embed_dim": 2560,
|
| 186 |
+
"low_rank_dimension": 4,
|
| 187 |
+
"dropout": 0.05
|
| 188 |
+
}
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"layer": 17,
|
| 192 |
+
"component": "block_output",
|
| 193 |
+
"low_rank_dimension": 4,
|
| 194 |
+
"intervention": {
|
| 195 |
+
"type": "mores",
|
| 196 |
+
"embed_dim": 2560,
|
| 197 |
+
"low_rank_dimension": 4,
|
| 198 |
+
"dropout": 0.05
|
| 199 |
+
}
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"layer": 18,
|
| 203 |
+
"component": "block_output",
|
| 204 |
+
"low_rank_dimension": 4,
|
| 205 |
+
"intervention": {
|
| 206 |
+
"type": "mores",
|
| 207 |
+
"embed_dim": 2560,
|
| 208 |
+
"low_rank_dimension": 4,
|
| 209 |
+
"dropout": 0.05
|
| 210 |
+
}
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"layer": 19,
|
| 214 |
+
"component": "block_output",
|
| 215 |
+
"low_rank_dimension": 4,
|
| 216 |
+
"intervention": {
|
| 217 |
+
"type": "mores",
|
| 218 |
+
"embed_dim": 2560,
|
| 219 |
+
"low_rank_dimension": 4,
|
| 220 |
+
"dropout": 0.05
|
| 221 |
+
}
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"layer": 20,
|
| 225 |
+
"component": "block_output",
|
| 226 |
+
"low_rank_dimension": 4,
|
| 227 |
+
"intervention": {
|
| 228 |
+
"type": "mores",
|
| 229 |
+
"embed_dim": 2560,
|
| 230 |
+
"low_rank_dimension": 4,
|
| 231 |
+
"dropout": 0.05
|
| 232 |
+
}
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"layer": 21,
|
| 236 |
+
"component": "block_output",
|
| 237 |
+
"low_rank_dimension": 4,
|
| 238 |
+
"intervention": {
|
| 239 |
+
"type": "mores",
|
| 240 |
+
"embed_dim": 2560,
|
| 241 |
+
"low_rank_dimension": 4,
|
| 242 |
+
"dropout": 0.05
|
| 243 |
+
}
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"layer": 22,
|
| 247 |
+
"component": "block_output",
|
| 248 |
+
"low_rank_dimension": 4,
|
| 249 |
+
"intervention": {
|
| 250 |
+
"type": "mores",
|
| 251 |
+
"embed_dim": 2560,
|
| 252 |
+
"low_rank_dimension": 4,
|
| 253 |
+
"dropout": 0.05
|
| 254 |
+
}
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"layer": 23,
|
| 258 |
+
"component": "block_output",
|
| 259 |
+
"low_rank_dimension": 4,
|
| 260 |
+
"intervention": {
|
| 261 |
+
"type": "mores",
|
| 262 |
+
"embed_dim": 2560,
|
| 263 |
+
"low_rank_dimension": 4,
|
| 264 |
+
"dropout": 0.05
|
| 265 |
+
}
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"layer": 24,
|
| 269 |
+
"component": "block_output",
|
| 270 |
+
"low_rank_dimension": 4,
|
| 271 |
+
"intervention": {
|
| 272 |
+
"type": "mores",
|
| 273 |
+
"embed_dim": 2560,
|
| 274 |
+
"low_rank_dimension": 4,
|
| 275 |
+
"dropout": 0.05
|
| 276 |
+
}
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"layer": 25,
|
| 280 |
+
"component": "block_output",
|
| 281 |
+
"low_rank_dimension": 4,
|
| 282 |
+
"intervention": {
|
| 283 |
+
"type": "mores",
|
| 284 |
+
"embed_dim": 2560,
|
| 285 |
+
"low_rank_dimension": 4,
|
| 286 |
+
"dropout": 0.05
|
| 287 |
+
}
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"layer": 26,
|
| 291 |
+
"component": "block_output",
|
| 292 |
+
"low_rank_dimension": 4,
|
| 293 |
+
"intervention": {
|
| 294 |
+
"type": "mores",
|
| 295 |
+
"embed_dim": 2560,
|
| 296 |
+
"low_rank_dimension": 4,
|
| 297 |
+
"dropout": 0.05
|
| 298 |
+
}
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"layer": 27,
|
| 302 |
+
"component": "block_output",
|
| 303 |
+
"low_rank_dimension": 4,
|
| 304 |
+
"intervention": {
|
| 305 |
+
"type": "mores",
|
| 306 |
+
"embed_dim": 2560,
|
| 307 |
+
"low_rank_dimension": 4,
|
| 308 |
+
"dropout": 0.05
|
| 309 |
+
}
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"layer": 28,
|
| 313 |
+
"component": "block_output",
|
| 314 |
+
"low_rank_dimension": 4,
|
| 315 |
+
"intervention": {
|
| 316 |
+
"type": "mores",
|
| 317 |
+
"embed_dim": 2560,
|
| 318 |
+
"low_rank_dimension": 4,
|
| 319 |
+
"dropout": 0.05
|
| 320 |
+
}
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"layer": 29,
|
| 324 |
+
"component": "block_output",
|
| 325 |
+
"low_rank_dimension": 4,
|
| 326 |
+
"intervention": {
|
| 327 |
+
"type": "mores",
|
| 328 |
+
"embed_dim": 2560,
|
| 329 |
+
"low_rank_dimension": 4,
|
| 330 |
+
"dropout": 0.05
|
| 331 |
+
}
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"layer": 30,
|
| 335 |
+
"component": "block_output",
|
| 336 |
+
"low_rank_dimension": 4,
|
| 337 |
+
"intervention": {
|
| 338 |
+
"type": "mores",
|
| 339 |
+
"embed_dim": 2560,
|
| 340 |
+
"low_rank_dimension": 4,
|
| 341 |
+
"dropout": 0.05
|
| 342 |
+
}
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"layer": 31,
|
| 346 |
+
"component": "block_output",
|
| 347 |
+
"low_rank_dimension": 4,
|
| 348 |
+
"intervention": {
|
| 349 |
+
"type": "mores",
|
| 350 |
+
"embed_dim": 2560,
|
| 351 |
+
"low_rank_dimension": 4,
|
| 352 |
+
"dropout": 0.05
|
| 353 |
+
}
|
| 354 |
+
}
|
| 355 |
+
]
|
| 356 |
+
}
|
mores/language_model/intkey_layer.0.comp.block_output.unit.pos.nunit.1#0.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:30b4edb4cfb1d7ae68ea3f8a44d228ca922b03a076de72891addc5db58d64f1a
|
| 3 |
+
size 63560
|
mores/language_model/intkey_layer.1.comp.block_output.unit.pos.nunit.1#0.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:55d0594ea27ff3f1cc867e023fc4f41183069aa6374edb50803a6c5877809eb0
|
| 3 |
+
size 63560
|
mores/language_model/intkey_layer.10.comp.block_output.unit.pos.nunit.1#0.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:35d45b3fa179107f9ba5cf078632bb166bc963a615e7d2adc64067bc8b7aaaf2
|
| 3 |
+
size 63567
|
mores/language_model/intkey_layer.11.comp.block_output.unit.pos.nunit.1#0.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bd985ce425b214118fe5ad16c05a34a8d3ba5cab13b1dcd562f48fe57dbfc9f4
|
| 3 |
+
size 63567
|
mores/language_model/intkey_layer.12.comp.block_output.unit.pos.nunit.1#0.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f53348905931df778d6233387d574dbd29f76f35aa83391fd625ac122d2339eb
|
| 3 |
+
size 63567
|
mores/language_model/intkey_layer.13.comp.block_output.unit.pos.nunit.1#0.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c64c4b39b9906f468f8559170c4f13520ea8a648539331d028e6e4c97ddd6321
|
| 3 |
+
size 63567
|
mores/language_model/intkey_layer.14.comp.block_output.unit.pos.nunit.1#0.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:588e000b9be651851fdc193e306f7c490a2e5cad65a35a5a54dad56eb77cc205
|
| 3 |
+
size 63567
|
mores/language_model/intkey_layer.15.comp.block_output.unit.pos.nunit.1#0.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c967032cf751551b1c9636d5f75f0c98b54dfc3494a2eb7026869ef05abe7c15
|
| 3 |
+
size 63567
|
mores/language_model/intkey_layer.16.comp.block_output.unit.pos.nunit.1#0.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88efd22fc040096081b3e9ed724eb7da00e1e581f6a0481724e200163991192c
|
| 3 |
+
size 63567
|
mores/language_model/intkey_layer.17.comp.block_output.unit.pos.nunit.1#0.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1fc0e2115bc3b0ee4faddded685376b04959b7a11fe5e671f00407bede431285
|
| 3 |
+
size 63567
|
mores/language_model/intkey_layer.18.comp.block_output.unit.pos.nunit.1#0.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:131513a60a46fc0eebba00f0588bd758f06c59c76e6c585b4b749a91e6eb2569
|
| 3 |
+
size 63567
|
mores/language_model/intkey_layer.19.comp.block_output.unit.pos.nunit.1#0.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b7b34e009459e649a626f6c2b0fb955541d4e0394a2b8be57d7b90616ca479d
|
| 3 |
+
size 63567
|
mores/language_model/intkey_layer.2.comp.block_output.unit.pos.nunit.1#0.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fa73fb595ee4a665896d70cc1fab76e80b04e4aed57f293e07ada4b0805c9cca
|
| 3 |
+
size 63560
|
mores/language_model/intkey_layer.20.comp.block_output.unit.pos.nunit.1#0.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2dde9fb488feacf834e565d328f6374bac87c9876d4bd9820fe4dd0d31cb4d1e
|
| 3 |
+
size 63567
|
mores/language_model/intkey_layer.21.comp.block_output.unit.pos.nunit.1#0.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:edfc425d2b072f409996e8784669ca7a9015bbeb550ac31b9db44b82d43c9761
|
| 3 |
+
size 63567
|
mores/language_model/intkey_layer.22.comp.block_output.unit.pos.nunit.1#0.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:20fc574bc77e0d608e5cf57c9b4e0c4f3938563716f4cc84b11387eb2a074005
|
| 3 |
+
size 63567
|
mores/language_model/intkey_layer.23.comp.block_output.unit.pos.nunit.1#0.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:60f7066bfe093d517487357ddb8bb606b8bc77868d97d3a320cca017ce0cfe95
|
| 3 |
+
size 63567
|
mores/language_model/intkey_layer.24.comp.block_output.unit.pos.nunit.1#0.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ef25fd4ceb7af5fb800c414cb8771e2f1c0e9daf3bf2610d722175e7ad3b596
|
| 3 |
+
size 63567
|
mores/language_model/intkey_layer.25.comp.block_output.unit.pos.nunit.1#0.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d71386217bba105b416fdaafa5839fbf040702a4aeccbc76b894bebb417fa389
|
| 3 |
+
size 63567
|
mores/language_model/intkey_layer.26.comp.block_output.unit.pos.nunit.1#0.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:caee12bc5322ff67c5934e603022951360b73ee9201b143e44568e078f5363de
|
| 3 |
+
size 63567
|
mores/language_model/intkey_layer.27.comp.block_output.unit.pos.nunit.1#0.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f96c58801aa0a2a96e303de19a9058edbc298d01911aa687caa11a2ef420064d
|
| 3 |
+
size 63567
|
mores/language_model/intkey_layer.28.comp.block_output.unit.pos.nunit.1#0.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2cdd1a79ebd43d2f4f986e7fdba1191cd0cadfbdf897efebae7b6028609c3201
|
| 3 |
+
size 63567
|
mores/language_model/intkey_layer.29.comp.block_output.unit.pos.nunit.1#0.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f175213cf683885c34215ba7b485247d298ed4b17b9180fdccc758a88a3632d3
|
| 3 |
+
size 63567
|
mores/language_model/intkey_layer.3.comp.block_output.unit.pos.nunit.1#0.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:59dcce6a95b4b4bdeb5241c3cf5c818c5b396d54fb39e5e238fac6bfa61bcde7
|
| 3 |
+
size 63560
|
mores/language_model/intkey_layer.30.comp.block_output.unit.pos.nunit.1#0.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea5cec01073e24afd3edd6033f1395e18d2517b43abd0ac504a5af184bd24cff
|
| 3 |
+
size 63567
|
mores/language_model/intkey_layer.31.comp.block_output.unit.pos.nunit.1#0.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:765dfa71b1391df34b7cc32b7f6258f7f956d593ea90f463ba0a87c4e8b91a4d
|
| 3 |
+
size 63567
|
mores/language_model/intkey_layer.4.comp.block_output.unit.pos.nunit.1#0.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:efe004dacfffa763f24e31ff8c96ec706392e6a7cae0a4b4da4284fd1d836902
|
| 3 |
+
size 63560
|
mores/language_model/intkey_layer.5.comp.block_output.unit.pos.nunit.1#0.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:986d1290c2e427da2364ee1587d7ad7f620d91329989178195b55d4c8d92ddb3
|
| 3 |
+
size 63560
|
mores/language_model/intkey_layer.6.comp.block_output.unit.pos.nunit.1#0.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:152cfb8cf8dd3f6813c71e7d9b5d95b558ce6eef2904a2a9d87f6d170374ba72
|
| 3 |
+
size 63560
|
mores/language_model/intkey_layer.7.comp.block_output.unit.pos.nunit.1#0.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6f07d469d2bd76a423db4b2033d1a709569af0d1e2a091660da6d66a77eb08d6
|
| 3 |
+
size 63560
|
mores/language_model/intkey_layer.8.comp.block_output.unit.pos.nunit.1#0.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a09e04bc1a7d0f7cfa961f9a24980e754da0e5dc36a69e56ec8b6b0e4c1095de
|
| 3 |
+
size 63560
|
mores/language_model/intkey_layer.9.comp.block_output.unit.pos.nunit.1#0.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:99388787564c281181e68dc1c026ea46bab2993a5a5db9520a9f8c4ada5c54f2
|
| 3 |
+
size 63560
|
mores/language_model/mores_pos_configs.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"intervention_positions": "f4+l5",
|
| 3 |
+
"mores_share_weights": true,
|
| 4 |
+
"intervened_prompt_part": "first_round",
|
| 5 |
+
"intervene_modality": "vis",
|
| 6 |
+
"num_interventions": {
|
| 7 |
+
"llm": 32
|
| 8 |
+
},
|
| 9 |
+
"img_embed_token_len": 728
|
| 10 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<|endoftext|>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<|endoftext|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,327 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"50256": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"50257": {
|
| 14 |
+
"content": " ",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": true,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": false
|
| 20 |
+
},
|
| 21 |
+
"50258": {
|
| 22 |
+
"content": " ",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": true,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": false
|
| 28 |
+
},
|
| 29 |
+
"50259": {
|
| 30 |
+
"content": " ",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": true,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": false
|
| 36 |
+
},
|
| 37 |
+
"50260": {
|
| 38 |
+
"content": " ",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": false
|
| 44 |
+
},
|
| 45 |
+
"50261": {
|
| 46 |
+
"content": " ",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": true,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": false
|
| 52 |
+
},
|
| 53 |
+
"50262": {
|
| 54 |
+
"content": " ",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": true,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": false
|
| 60 |
+
},
|
| 61 |
+
"50263": {
|
| 62 |
+
"content": " ",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": true,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": false
|
| 68 |
+
},
|
| 69 |
+
"50264": {
|
| 70 |
+
"content": " ",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": true,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": false
|
| 76 |
+
},
|
| 77 |
+
"50265": {
|
| 78 |
+
"content": " ",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": true,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": false
|
| 84 |
+
},
|
| 85 |
+
"50266": {
|
| 86 |
+
"content": " ",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": true,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": false
|
| 92 |
+
},
|
| 93 |
+
"50267": {
|
| 94 |
+
"content": " ",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": true,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": false
|
| 100 |
+
},
|
| 101 |
+
"50268": {
|
| 102 |
+
"content": " ",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": true,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": false
|
| 108 |
+
},
|
| 109 |
+
"50269": {
|
| 110 |
+
"content": " ",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": true,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": false
|
| 116 |
+
},
|
| 117 |
+
"50270": {
|
| 118 |
+
"content": " ",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": true,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"50271": {
|
| 126 |
+
"content": " ",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": true,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"50272": {
|
| 134 |
+
"content": " ",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": true,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"50273": {
|
| 142 |
+
"content": " ",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": true,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"50274": {
|
| 150 |
+
"content": " ",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": true,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"50275": {
|
| 158 |
+
"content": " ",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": true,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"50276": {
|
| 166 |
+
"content": " ",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": true,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"50277": {
|
| 174 |
+
"content": " ",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": true,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"50278": {
|
| 182 |
+
"content": " ",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": true,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"50279": {
|
| 190 |
+
"content": " ",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": true,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"50280": {
|
| 198 |
+
"content": " ",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": true,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"50281": {
|
| 206 |
+
"content": " ",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": true,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
},
|
| 213 |
+
"50282": {
|
| 214 |
+
"content": " ",
|
| 215 |
+
"lstrip": false,
|
| 216 |
+
"normalized": true,
|
| 217 |
+
"rstrip": false,
|
| 218 |
+
"single_word": false,
|
| 219 |
+
"special": false
|
| 220 |
+
},
|
| 221 |
+
"50283": {
|
| 222 |
+
"content": " ",
|
| 223 |
+
"lstrip": false,
|
| 224 |
+
"normalized": true,
|
| 225 |
+
"rstrip": false,
|
| 226 |
+
"single_word": false,
|
| 227 |
+
"special": false
|
| 228 |
+
},
|
| 229 |
+
"50284": {
|
| 230 |
+
"content": " ",
|
| 231 |
+
"lstrip": false,
|
| 232 |
+
"normalized": true,
|
| 233 |
+
"rstrip": false,
|
| 234 |
+
"single_word": false,
|
| 235 |
+
"special": false
|
| 236 |
+
},
|
| 237 |
+
"50285": {
|
| 238 |
+
"content": " ",
|
| 239 |
+
"lstrip": false,
|
| 240 |
+
"normalized": true,
|
| 241 |
+
"rstrip": false,
|
| 242 |
+
"single_word": false,
|
| 243 |
+
"special": false
|
| 244 |
+
},
|
| 245 |
+
"50286": {
|
| 246 |
+
"content": " ",
|
| 247 |
+
"lstrip": false,
|
| 248 |
+
"normalized": true,
|
| 249 |
+
"rstrip": false,
|
| 250 |
+
"single_word": false,
|
| 251 |
+
"special": false
|
| 252 |
+
},
|
| 253 |
+
"50287": {
|
| 254 |
+
"content": "\t\t\t\t\t\t\t\t\t",
|
| 255 |
+
"lstrip": false,
|
| 256 |
+
"normalized": true,
|
| 257 |
+
"rstrip": false,
|
| 258 |
+
"single_word": false,
|
| 259 |
+
"special": false
|
| 260 |
+
},
|
| 261 |
+
"50288": {
|
| 262 |
+
"content": "\t\t\t\t\t\t\t\t",
|
| 263 |
+
"lstrip": false,
|
| 264 |
+
"normalized": true,
|
| 265 |
+
"rstrip": false,
|
| 266 |
+
"single_word": false,
|
| 267 |
+
"special": false
|
| 268 |
+
},
|
| 269 |
+
"50289": {
|
| 270 |
+
"content": "\t\t\t\t\t\t\t",
|
| 271 |
+
"lstrip": false,
|
| 272 |
+
"normalized": true,
|
| 273 |
+
"rstrip": false,
|
| 274 |
+
"single_word": false,
|
| 275 |
+
"special": false
|
| 276 |
+
},
|
| 277 |
+
"50290": {
|
| 278 |
+
"content": "\t\t\t\t\t\t",
|
| 279 |
+
"lstrip": false,
|
| 280 |
+
"normalized": true,
|
| 281 |
+
"rstrip": false,
|
| 282 |
+
"single_word": false,
|
| 283 |
+
"special": false
|
| 284 |
+
},
|
| 285 |
+
"50291": {
|
| 286 |
+
"content": "\t\t\t\t\t",
|
| 287 |
+
"lstrip": false,
|
| 288 |
+
"normalized": true,
|
| 289 |
+
"rstrip": false,
|
| 290 |
+
"single_word": false,
|
| 291 |
+
"special": false
|
| 292 |
+
},
|
| 293 |
+
"50292": {
|
| 294 |
+
"content": "\t\t\t\t",
|
| 295 |
+
"lstrip": false,
|
| 296 |
+
"normalized": true,
|
| 297 |
+
"rstrip": false,
|
| 298 |
+
"single_word": false,
|
| 299 |
+
"special": false
|
| 300 |
+
},
|
| 301 |
+
"50293": {
|
| 302 |
+
"content": "\t\t\t",
|
| 303 |
+
"lstrip": false,
|
| 304 |
+
"normalized": true,
|
| 305 |
+
"rstrip": false,
|
| 306 |
+
"single_word": false,
|
| 307 |
+
"special": false
|
| 308 |
+
},
|
| 309 |
+
"50294": {
|
| 310 |
+
"content": "\t\t",
|
| 311 |
+
"lstrip": false,
|
| 312 |
+
"normalized": true,
|
| 313 |
+
"rstrip": false,
|
| 314 |
+
"single_word": false,
|
| 315 |
+
"special": false
|
| 316 |
+
}
|
| 317 |
+
},
|
| 318 |
+
"bos_token": "<|endoftext|>",
|
| 319 |
+
"clean_up_tokenization_spaces": true,
|
| 320 |
+
"eos_token": "<|endoftext|>",
|
| 321 |
+
"errors": "replace",
|
| 322 |
+
"model_max_length": 3072,
|
| 323 |
+
"pad_token": "<|endoftext|>",
|
| 324 |
+
"padding_side": "right",
|
| 325 |
+
"tokenizer_class": "CodeGenTokenizer",
|
| 326 |
+
"unk_token": "<|endoftext|>"
|
| 327 |
+
}
|
trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
vision_tower/config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"attention_dropout": 0.0,
|
| 3 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 4 |
+
"hidden_size": 1152,
|
| 5 |
+
"image_size": 384,
|
| 6 |
+
"intermediate_size": 4304,
|
| 7 |
+
"layer_norm_eps": 1e-06,
|
| 8 |
+
"model_name_or_path": "google/siglip-so400m-patch14-384",
|
| 9 |
+
"model_name_or_path2": "",
|
| 10 |
+
"model_type": "siglip_vision_model",
|
| 11 |
+
"num_attention_heads": 16,
|
| 12 |
+
"num_channels": 3,
|
| 13 |
+
"num_hidden_layers": 27,
|
| 14 |
+
"patch_size": 14,
|
| 15 |
+
"transformers_version": "4.39.3"
|
| 16 |
+
}
|
vision_tower/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6c03cdf872045ec4e0d757bc8cd45adb18f6b4d30384c9f793d11793371c836f
|
| 3 |
+
size 856599050
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|