Commit
•
733803d
1
Parent(s):
2c7ed66
Upload folder using huggingface_hub (#1)
Browse files- 54287703f52190a0a2010eff94d817b32753f396069bacfcc11f318c459d4817 (ca7f0a4d079d4b1f9efd7742a1a230b522fb4c83)
- 7f3a3aded6a8308f0334c9a4ea8ee842b7e36d59aba2ff4335bac0949e11ec3a (4ce3aab3b436608f69754b415b4a5089a866fef8)
- 2620533162a810bf8f3219944f35aa3a4cb7193698b1b1c332ff961434d3868f (9b0bada0ea34f77dcc33861eae1875add5a86244)
- 9663f0160d87068173b9a3f70c8086e388092bd64b380fcd76ef7757e92e3b86 (2abc957c93d63212efb9aed06caa722dee72ba25)
- 9f0b18b43675654752792a0ceb8da369ee2246a1ec56a677dd536b06fd33fc60 (1dc76f67ff7a5e6cd293fdd5ad7974629328c7b7)
- d66f531ce5089c818ff186ebaec791496f367d95f1042c95d6f2552a51d200a9 (56537d9ec3bc154b41d3e1a653cdfe70ab1eebe6)
- 3421bda1140c7dcc367c2b5c3faa752bd782580248437fa75cfac4be9be9c7a6 (668ab34465311c9eae0d67417422ac84fb01afa5)
- 9015d1f19eaa0e687adabef257ac33340b98f1c390fe49a05e5cbc1e8b25ff36 (51db65e6e842f9f66e28e3ede25f777fe4c7f00d)
- 17372f4bb9e3192d02c353c8673af7a5a03e1caa05dd29864c759d129a4d11d5 (419c6a8d0746bc514cb8b99fd25caa030f1224e3)
- ac1a40ec45a7dd4587ec54cb04a3de161080f27f481fbb1cab0556a2f7fcf7be (c5ee5d2d4d8e4a877cbec769c2431681af8a0c70)
- 975b31fde88cfb5fc5173b05ddfe1ab044ec32f1be072ad831d55f2da9d71d6e (4f2928c3b7dc99cd48afbd9bc4fc61a7f018731d)
This view is limited to 50 files because it contains too many changes.
See raw diff
- sft_full/hyperrouter/added_tokens.json +13 -0
- sft_full/hyperrouter/config.json +170 -0
- sft_full/hyperrouter/generation_config.json +12 -0
- sft_full/hyperrouter/model-00001-of-00003.safetensors +3 -0
- sft_full/hyperrouter/model-00002-of-00003.safetensors +3 -0
- sft_full/hyperrouter/model-00003-of-00003.safetensors +3 -0
- sft_full/hyperrouter/model.safetensors.index.json +0 -0
- sft_full/hyperrouter/special_tokens_map.json +24 -0
- sft_full/hyperrouter/tokenizer.model +3 -0
- sft_full/hyperrouter/tokenizer_config.json +132 -0
- sft_full/hyperrouter/trainer_state.json +0 -0
- sft_full/hyperrouter/training_args.bin +3 -0
- sft_full/smoe/added_tokens.json +13 -0
- sft_full/smoe/config.json +168 -0
- sft_full/smoe/generation_config.json +12 -0
- sft_full/smoe/model-00001-of-00003.safetensors +3 -0
- sft_full/smoe/model-00002-of-00003.safetensors +3 -0
- sft_full/smoe/model-00003-of-00003.safetensors +3 -0
- sft_full/smoe/model.safetensors.index.json +0 -0
- sft_full/smoe/special_tokens_map.json +24 -0
- sft_full/smoe/tokenizer.model +3 -0
- sft_full/smoe/tokenizer_config.json +132 -0
- sft_full/smoe/trainer_state.json +0 -0
- sft_full/smoe/training_args.bin +3 -0
- sft_full/smoe_cosinegating/added_tokens.json +13 -0
- sft_full/smoe_cosinegating/config.json +168 -0
- sft_full/smoe_cosinegating/generation_config.json +12 -0
- sft_full/smoe_cosinegating/model-00001-of-00003.safetensors +3 -0
- sft_full/smoe_cosinegating/model-00002-of-00003.safetensors +3 -0
- sft_full/smoe_cosinegating/model-00003-of-00003.safetensors +3 -0
- sft_full/smoe_cosinegating/model.safetensors.index.json +0 -0
- sft_full/smoe_cosinegating/special_tokens_map.json +24 -0
- sft_full/smoe_cosinegating/tokenizer.model +3 -0
- sft_full/smoe_cosinegating/tokenizer_config.json +132 -0
- sft_full/smoe_cosinegating/trainer_state.json +0 -0
- sft_full/smoe_cosinegating/training_args.bin +3 -0
- sft_full/smoe_perturbed/added_tokens.json +13 -0
- sft_full/smoe_perturbed/config.json +168 -0
- sft_full/smoe_perturbed/generation_config.json +12 -0
- sft_full/smoe_perturbed/model-00001-of-00003.safetensors +3 -0
- sft_full/smoe_perturbed/model-00002-of-00003.safetensors +3 -0
- sft_full/smoe_perturbed/model-00003-of-00003.safetensors +3 -0
- sft_full/smoe_perturbed/model.safetensors.index.json +0 -0
- sft_full/smoe_perturbed/special_tokens_map.json +24 -0
- sft_full/smoe_perturbed/tokenizer.model +3 -0
- sft_full/smoe_perturbed/tokenizer_config.json +132 -0
- sft_full/smoe_perturbed/trainer_state.json +0 -0
- sft_full/smoe_perturbed/training_args.bin +3 -0
- sft_full/smoe_sigmoidgating/added_tokens.json +13 -0
- sft_full/smoe_sigmoidgating/config.json +168 -0
sft_full/hyperrouter/added_tokens.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|assistant|>": 32001,
|
| 3 |
+
"<|endoftext|>": 32000,
|
| 4 |
+
"<|end|>": 32007,
|
| 5 |
+
"<|placeholder1|>": 32002,
|
| 6 |
+
"<|placeholder2|>": 32003,
|
| 7 |
+
"<|placeholder3|>": 32004,
|
| 8 |
+
"<|placeholder4|>": 32005,
|
| 9 |
+
"<|placeholder5|>": 32008,
|
| 10 |
+
"<|placeholder6|>": 32009,
|
| 11 |
+
"<|system|>": 32006,
|
| 12 |
+
"<|user|>": 32010
|
| 13 |
+
}
|
sft_full/hyperrouter/config.json
ADDED
|
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/cm/archive/namnv78/checkpoints/phi35-siglip224/pft",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlavaPhiForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"auto_map": {
|
| 9 |
+
"AutoConfig": "configuration_phi3.Phi3Config",
|
| 10 |
+
"AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
|
| 11 |
+
},
|
| 12 |
+
"balance_loss_coef": 0.1,
|
| 13 |
+
"bos_token_id": 1,
|
| 14 |
+
"clip_smoe": true,
|
| 15 |
+
"dropout": false,
|
| 16 |
+
"embd_pdrop": 0.0,
|
| 17 |
+
"eos_token_id": 32000,
|
| 18 |
+
"freeze_mm_mlp_adapter": false,
|
| 19 |
+
"hidden_act": "silu",
|
| 20 |
+
"hidden_size": 3072,
|
| 21 |
+
"image_aspect_ratio": "pad",
|
| 22 |
+
"initializer_range": 0.02,
|
| 23 |
+
"intermediate_size": 8192,
|
| 24 |
+
"local_rank": 0,
|
| 25 |
+
"max_position_embeddings": 131072,
|
| 26 |
+
"mlp_smoe": true,
|
| 27 |
+
"mm_hidden_size": 1152,
|
| 28 |
+
"mm_patch_merge_type": "flat",
|
| 29 |
+
"mm_projector_lr": null,
|
| 30 |
+
"mm_projector_type": "moe",
|
| 31 |
+
"mm_use_im_patch_token": false,
|
| 32 |
+
"mm_use_im_start_end": false,
|
| 33 |
+
"mm_vision_select_feature": "patch",
|
| 34 |
+
"mm_vision_select_layer": -2,
|
| 35 |
+
"mm_vision_tower": "google/siglip-so400m-patch14-224",
|
| 36 |
+
"model_type": "llava_phi",
|
| 37 |
+
"moe_name": "hyperrouter",
|
| 38 |
+
"num_attention_heads": 32,
|
| 39 |
+
"num_experts": 4,
|
| 40 |
+
"num_hidden_layers": 32,
|
| 41 |
+
"num_key_value_heads": 32,
|
| 42 |
+
"num_layers": 3,
|
| 43 |
+
"num_selected": 2,
|
| 44 |
+
"original_max_position_embeddings": 4096,
|
| 45 |
+
"pad_token_id": 32000,
|
| 46 |
+
"resid_pdrop": 0.0,
|
| 47 |
+
"rms_norm_eps": 1e-05,
|
| 48 |
+
"rope_scaling": {
|
| 49 |
+
"long_factor": [
|
| 50 |
+
1.0800000429153442,
|
| 51 |
+
1.1100000143051147,
|
| 52 |
+
1.1399999856948853,
|
| 53 |
+
1.340000033378601,
|
| 54 |
+
1.5899999141693115,
|
| 55 |
+
1.600000023841858,
|
| 56 |
+
1.6200000047683716,
|
| 57 |
+
2.620000123977661,
|
| 58 |
+
3.2300000190734863,
|
| 59 |
+
3.2300000190734863,
|
| 60 |
+
4.789999961853027,
|
| 61 |
+
7.400000095367432,
|
| 62 |
+
7.700000286102295,
|
| 63 |
+
9.09000015258789,
|
| 64 |
+
12.199999809265137,
|
| 65 |
+
17.670000076293945,
|
| 66 |
+
24.46000099182129,
|
| 67 |
+
28.57000160217285,
|
| 68 |
+
30.420001983642578,
|
| 69 |
+
30.840002059936523,
|
| 70 |
+
32.590003967285156,
|
| 71 |
+
32.93000411987305,
|
| 72 |
+
42.320003509521484,
|
| 73 |
+
44.96000289916992,
|
| 74 |
+
50.340003967285156,
|
| 75 |
+
50.45000457763672,
|
| 76 |
+
57.55000305175781,
|
| 77 |
+
57.93000411987305,
|
| 78 |
+
58.21000289916992,
|
| 79 |
+
60.1400032043457,
|
| 80 |
+
62.61000442504883,
|
| 81 |
+
62.62000274658203,
|
| 82 |
+
62.71000289916992,
|
| 83 |
+
63.1400032043457,
|
| 84 |
+
63.1400032043457,
|
| 85 |
+
63.77000427246094,
|
| 86 |
+
63.93000411987305,
|
| 87 |
+
63.96000289916992,
|
| 88 |
+
63.970001220703125,
|
| 89 |
+
64.02999877929688,
|
| 90 |
+
64.06999969482422,
|
| 91 |
+
64.08000183105469,
|
| 92 |
+
64.12000274658203,
|
| 93 |
+
64.41000366210938,
|
| 94 |
+
64.4800033569336,
|
| 95 |
+
64.51000213623047,
|
| 96 |
+
64.52999877929688,
|
| 97 |
+
64.83999633789062
|
| 98 |
+
],
|
| 99 |
+
"short_factor": [
|
| 100 |
+
1.0,
|
| 101 |
+
1.0199999809265137,
|
| 102 |
+
1.0299999713897705,
|
| 103 |
+
1.0299999713897705,
|
| 104 |
+
1.0499999523162842,
|
| 105 |
+
1.0499999523162842,
|
| 106 |
+
1.0499999523162842,
|
| 107 |
+
1.0499999523162842,
|
| 108 |
+
1.0499999523162842,
|
| 109 |
+
1.0699999332427979,
|
| 110 |
+
1.0999999046325684,
|
| 111 |
+
1.1099998950958252,
|
| 112 |
+
1.1599998474121094,
|
| 113 |
+
1.1599998474121094,
|
| 114 |
+
1.1699998378753662,
|
| 115 |
+
1.2899998426437378,
|
| 116 |
+
1.339999794960022,
|
| 117 |
+
1.679999828338623,
|
| 118 |
+
1.7899998426437378,
|
| 119 |
+
1.8199998140335083,
|
| 120 |
+
1.8499997854232788,
|
| 121 |
+
1.8799997568130493,
|
| 122 |
+
1.9099997282028198,
|
| 123 |
+
1.9399996995925903,
|
| 124 |
+
1.9899996519088745,
|
| 125 |
+
2.0199997425079346,
|
| 126 |
+
2.0199997425079346,
|
| 127 |
+
2.0199997425079346,
|
| 128 |
+
2.0199997425079346,
|
| 129 |
+
2.0199997425079346,
|
| 130 |
+
2.0199997425079346,
|
| 131 |
+
2.0299997329711914,
|
| 132 |
+
2.0299997329711914,
|
| 133 |
+
2.0299997329711914,
|
| 134 |
+
2.0299997329711914,
|
| 135 |
+
2.0299997329711914,
|
| 136 |
+
2.0299997329711914,
|
| 137 |
+
2.0299997329711914,
|
| 138 |
+
2.0299997329711914,
|
| 139 |
+
2.0299997329711914,
|
| 140 |
+
2.0799996852874756,
|
| 141 |
+
2.0899996757507324,
|
| 142 |
+
2.189999580383301,
|
| 143 |
+
2.2199995517730713,
|
| 144 |
+
2.5899994373321533,
|
| 145 |
+
2.729999542236328,
|
| 146 |
+
2.749999523162842,
|
| 147 |
+
2.8399994373321533
|
| 148 |
+
],
|
| 149 |
+
"type": "longrope"
|
| 150 |
+
},
|
| 151 |
+
"rope_theta": 10000.0,
|
| 152 |
+
"router_z_loss_coef": 0.01,
|
| 153 |
+
"scales": [
|
| 154 |
+
1,
|
| 155 |
+
3
|
| 156 |
+
],
|
| 157 |
+
"sliding_window": 262144,
|
| 158 |
+
"tie_word_embeddings": false,
|
| 159 |
+
"tokenizer_model_max_length": 2048,
|
| 160 |
+
"tokenizer_padding_side": "right",
|
| 161 |
+
"topk_max": 2,
|
| 162 |
+
"topk_min": 1,
|
| 163 |
+
"torch_dtype": "bfloat16",
|
| 164 |
+
"training": true,
|
| 165 |
+
"transformers_version": "4.43.0",
|
| 166 |
+
"tune_mm_mlp_adapter": false,
|
| 167 |
+
"use_cache": true,
|
| 168 |
+
"use_mm_proj": true,
|
| 169 |
+
"vocab_size": 32064
|
| 170 |
+
}
|
sft_full/hyperrouter/generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": [
|
| 6 |
+
32007,
|
| 7 |
+
32001,
|
| 8 |
+
32000
|
| 9 |
+
],
|
| 10 |
+
"pad_token_id": 32000,
|
| 11 |
+
"transformers_version": "4.43.0"
|
| 12 |
+
}
|
sft_full/hyperrouter/model-00001-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:77070ba911bb125ab3cd8424cd59c16fe002d181caf04bf90cfe15a51301c6b4
|
| 3 |
+
size 4972489328
|
sft_full/hyperrouter/model-00002-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c92aba44ae28d81e099be78e65ce61b5095566a4646d0882415ff4cc63270f08
|
| 3 |
+
size 4995022432
|
sft_full/hyperrouter/model-00003-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fdcfe6f0f1bf56818412c4eec4443cbe87476db39f0f4782d0f29247dc905d28
|
| 3 |
+
size 342468696
|
sft_full/hyperrouter/model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
sft_full/hyperrouter/special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<unk>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
sft_full/hyperrouter/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
sft_full/hyperrouter/tokenizer_config.json
ADDED
|
@@ -0,0 +1,132 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": true,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": true,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": false
|
| 29 |
+
},
|
| 30 |
+
"32000": {
|
| 31 |
+
"content": "<|endoftext|>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
"32001": {
|
| 39 |
+
"content": "<|assistant|>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": true,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": true
|
| 45 |
+
},
|
| 46 |
+
"32002": {
|
| 47 |
+
"content": "<|placeholder1|>",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": false,
|
| 50 |
+
"rstrip": true,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": true
|
| 53 |
+
},
|
| 54 |
+
"32003": {
|
| 55 |
+
"content": "<|placeholder2|>",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": false,
|
| 58 |
+
"rstrip": true,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": true
|
| 61 |
+
},
|
| 62 |
+
"32004": {
|
| 63 |
+
"content": "<|placeholder3|>",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": false,
|
| 66 |
+
"rstrip": true,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": true
|
| 69 |
+
},
|
| 70 |
+
"32005": {
|
| 71 |
+
"content": "<|placeholder4|>",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": false,
|
| 74 |
+
"rstrip": true,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": true
|
| 77 |
+
},
|
| 78 |
+
"32006": {
|
| 79 |
+
"content": "<|system|>",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": false,
|
| 82 |
+
"rstrip": true,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": true
|
| 85 |
+
},
|
| 86 |
+
"32007": {
|
| 87 |
+
"content": "<|end|>",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": false,
|
| 90 |
+
"rstrip": true,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": true
|
| 93 |
+
},
|
| 94 |
+
"32008": {
|
| 95 |
+
"content": "<|placeholder5|>",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": false,
|
| 98 |
+
"rstrip": true,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": true
|
| 101 |
+
},
|
| 102 |
+
"32009": {
|
| 103 |
+
"content": "<|placeholder6|>",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": false,
|
| 106 |
+
"rstrip": true,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": true
|
| 109 |
+
},
|
| 110 |
+
"32010": {
|
| 111 |
+
"content": "<|user|>",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": false,
|
| 114 |
+
"rstrip": true,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": true
|
| 117 |
+
}
|
| 118 |
+
},
|
| 119 |
+
"bos_token": "<s>",
|
| 120 |
+
"chat_template": "{% for message in messages %}{% if message['role'] == 'system' and message['content'] %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
|
| 121 |
+
"clean_up_tokenization_spaces": false,
|
| 122 |
+
"eos_token": "<|endoftext|>",
|
| 123 |
+
"legacy": false,
|
| 124 |
+
"model_max_length": 2048,
|
| 125 |
+
"pad_token": "<unk>",
|
| 126 |
+
"padding_side": "right",
|
| 127 |
+
"sp_model_kwargs": {},
|
| 128 |
+
"spaces_between_special_tokens": false,
|
| 129 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 130 |
+
"unk_token": "<unk>",
|
| 131 |
+
"use_default_system_prompt": false
|
| 132 |
+
}
|
sft_full/hyperrouter/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
sft_full/hyperrouter/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce64b5e180ddbd78a6d2dbb50c07989eae0c5fc9f607e2a2025709f4528ef98d
|
| 3 |
+
size 8184
|
sft_full/smoe/added_tokens.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|assistant|>": 32001,
|
| 3 |
+
"<|endoftext|>": 32000,
|
| 4 |
+
"<|end|>": 32007,
|
| 5 |
+
"<|placeholder1|>": 32002,
|
| 6 |
+
"<|placeholder2|>": 32003,
|
| 7 |
+
"<|placeholder3|>": 32004,
|
| 8 |
+
"<|placeholder4|>": 32005,
|
| 9 |
+
"<|placeholder5|>": 32008,
|
| 10 |
+
"<|placeholder6|>": 32009,
|
| 11 |
+
"<|system|>": 32006,
|
| 12 |
+
"<|user|>": 32010
|
| 13 |
+
}
|
sft_full/smoe/config.json
ADDED
|
@@ -0,0 +1,168 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/cm/archive/namnv78/checkpoints/phi35-siglip224/pft",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlavaPhiForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"auto_map": {
|
| 9 |
+
"AutoConfig": "configuration_phi3.Phi3Config",
|
| 10 |
+
"AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
|
| 11 |
+
},
|
| 12 |
+
"balance_loss_coef": 0.1,
|
| 13 |
+
"bos_token_id": 1,
|
| 14 |
+
"clip_smoe": true,
|
| 15 |
+
"dropout": false,
|
| 16 |
+
"embd_pdrop": 0.0,
|
| 17 |
+
"eos_token_id": 32000,
|
| 18 |
+
"freeze_mm_mlp_adapter": false,
|
| 19 |
+
"hidden_act": "silu",
|
| 20 |
+
"hidden_size": 3072,
|
| 21 |
+
"image_aspect_ratio": "pad",
|
| 22 |
+
"initializer_range": 0.02,
|
| 23 |
+
"intermediate_size": 8192,
|
| 24 |
+
"local_rank": 0,
|
| 25 |
+
"max_position_embeddings": 131072,
|
| 26 |
+
"mlp_smoe": true,
|
| 27 |
+
"mm_hidden_size": 1152,
|
| 28 |
+
"mm_patch_merge_type": "flat",
|
| 29 |
+
"mm_projector_lr": null,
|
| 30 |
+
"mm_projector_type": "moe",
|
| 31 |
+
"mm_use_im_patch_token": false,
|
| 32 |
+
"mm_use_im_start_end": false,
|
| 33 |
+
"mm_vision_select_feature": "patch",
|
| 34 |
+
"mm_vision_select_layer": -2,
|
| 35 |
+
"mm_vision_tower": "google/siglip-so400m-patch14-224",
|
| 36 |
+
"model_type": "llava_phi",
|
| 37 |
+
"moe_name": "smoe",
|
| 38 |
+
"num_attention_heads": 32,
|
| 39 |
+
"num_experts": 4,
|
| 40 |
+
"num_hidden_layers": 32,
|
| 41 |
+
"num_key_value_heads": 32,
|
| 42 |
+
"num_layers": 3,
|
| 43 |
+
"num_selected": 2,
|
| 44 |
+
"original_max_position_embeddings": 4096,
|
| 45 |
+
"pad_token_id": 32000,
|
| 46 |
+
"resid_pdrop": 0.0,
|
| 47 |
+
"rms_norm_eps": 1e-05,
|
| 48 |
+
"rope_scaling": {
|
| 49 |
+
"long_factor": [
|
| 50 |
+
1.0800000429153442,
|
| 51 |
+
1.1100000143051147,
|
| 52 |
+
1.1399999856948853,
|
| 53 |
+
1.340000033378601,
|
| 54 |
+
1.5899999141693115,
|
| 55 |
+
1.600000023841858,
|
| 56 |
+
1.6200000047683716,
|
| 57 |
+
2.620000123977661,
|
| 58 |
+
3.2300000190734863,
|
| 59 |
+
3.2300000190734863,
|
| 60 |
+
4.789999961853027,
|
| 61 |
+
7.400000095367432,
|
| 62 |
+
7.700000286102295,
|
| 63 |
+
9.09000015258789,
|
| 64 |
+
12.199999809265137,
|
| 65 |
+
17.670000076293945,
|
| 66 |
+
24.46000099182129,
|
| 67 |
+
28.57000160217285,
|
| 68 |
+
30.420001983642578,
|
| 69 |
+
30.840002059936523,
|
| 70 |
+
32.590003967285156,
|
| 71 |
+
32.93000411987305,
|
| 72 |
+
42.320003509521484,
|
| 73 |
+
44.96000289916992,
|
| 74 |
+
50.340003967285156,
|
| 75 |
+
50.45000457763672,
|
| 76 |
+
57.55000305175781,
|
| 77 |
+
57.93000411987305,
|
| 78 |
+
58.21000289916992,
|
| 79 |
+
60.1400032043457,
|
| 80 |
+
62.61000442504883,
|
| 81 |
+
62.62000274658203,
|
| 82 |
+
62.71000289916992,
|
| 83 |
+
63.1400032043457,
|
| 84 |
+
63.1400032043457,
|
| 85 |
+
63.77000427246094,
|
| 86 |
+
63.93000411987305,
|
| 87 |
+
63.96000289916992,
|
| 88 |
+
63.970001220703125,
|
| 89 |
+
64.02999877929688,
|
| 90 |
+
64.06999969482422,
|
| 91 |
+
64.08000183105469,
|
| 92 |
+
64.12000274658203,
|
| 93 |
+
64.41000366210938,
|
| 94 |
+
64.4800033569336,
|
| 95 |
+
64.51000213623047,
|
| 96 |
+
64.52999877929688,
|
| 97 |
+
64.83999633789062
|
| 98 |
+
],
|
| 99 |
+
"short_factor": [
|
| 100 |
+
1.0,
|
| 101 |
+
1.0199999809265137,
|
| 102 |
+
1.0299999713897705,
|
| 103 |
+
1.0299999713897705,
|
| 104 |
+
1.0499999523162842,
|
| 105 |
+
1.0499999523162842,
|
| 106 |
+
1.0499999523162842,
|
| 107 |
+
1.0499999523162842,
|
| 108 |
+
1.0499999523162842,
|
| 109 |
+
1.0699999332427979,
|
| 110 |
+
1.0999999046325684,
|
| 111 |
+
1.1099998950958252,
|
| 112 |
+
1.1599998474121094,
|
| 113 |
+
1.1599998474121094,
|
| 114 |
+
1.1699998378753662,
|
| 115 |
+
1.2899998426437378,
|
| 116 |
+
1.339999794960022,
|
| 117 |
+
1.679999828338623,
|
| 118 |
+
1.7899998426437378,
|
| 119 |
+
1.8199998140335083,
|
| 120 |
+
1.8499997854232788,
|
| 121 |
+
1.8799997568130493,
|
| 122 |
+
1.9099997282028198,
|
| 123 |
+
1.9399996995925903,
|
| 124 |
+
1.9899996519088745,
|
| 125 |
+
2.0199997425079346,
|
| 126 |
+
2.0199997425079346,
|
| 127 |
+
2.0199997425079346,
|
| 128 |
+
2.0199997425079346,
|
| 129 |
+
2.0199997425079346,
|
| 130 |
+
2.0199997425079346,
|
| 131 |
+
2.0299997329711914,
|
| 132 |
+
2.0299997329711914,
|
| 133 |
+
2.0299997329711914,
|
| 134 |
+
2.0299997329711914,
|
| 135 |
+
2.0299997329711914,
|
| 136 |
+
2.0299997329711914,
|
| 137 |
+
2.0299997329711914,
|
| 138 |
+
2.0299997329711914,
|
| 139 |
+
2.0299997329711914,
|
| 140 |
+
2.0799996852874756,
|
| 141 |
+
2.0899996757507324,
|
| 142 |
+
2.189999580383301,
|
| 143 |
+
2.2199995517730713,
|
| 144 |
+
2.5899994373321533,
|
| 145 |
+
2.729999542236328,
|
| 146 |
+
2.749999523162842,
|
| 147 |
+
2.8399994373321533
|
| 148 |
+
],
|
| 149 |
+
"type": "longrope"
|
| 150 |
+
},
|
| 151 |
+
"rope_theta": 10000.0,
|
| 152 |
+
"router_z_loss_coef": 0.01,
|
| 153 |
+
"scales": [
|
| 154 |
+
1,
|
| 155 |
+
3
|
| 156 |
+
],
|
| 157 |
+
"sliding_window": 262144,
|
| 158 |
+
"tie_word_embeddings": false,
|
| 159 |
+
"tokenizer_model_max_length": 2048,
|
| 160 |
+
"tokenizer_padding_side": "right",
|
| 161 |
+
"torch_dtype": "bfloat16",
|
| 162 |
+
"training": true,
|
| 163 |
+
"transformers_version": "4.43.0",
|
| 164 |
+
"tune_mm_mlp_adapter": false,
|
| 165 |
+
"use_cache": true,
|
| 166 |
+
"use_mm_proj": true,
|
| 167 |
+
"vocab_size": 32064
|
| 168 |
+
}
|
sft_full/smoe/generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": [
|
| 6 |
+
32007,
|
| 7 |
+
32001,
|
| 8 |
+
32000
|
| 9 |
+
],
|
| 10 |
+
"pad_token_id": 32000,
|
| 11 |
+
"transformers_version": "4.43.0"
|
| 12 |
+
}
|
sft_full/smoe/model-00001-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3060186020e81e85f75d680f7a6446b1397f8e60fcf713fae963647075b186f6
|
| 3 |
+
size 4972489328
|
sft_full/smoe/model-00002-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8cb877ce803d3f1c50c57760d319415451c7d7a4e2221b564707681bffa8c6fb
|
| 3 |
+
size 4985529648
|
sft_full/smoe/model-00003-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e0e2b038bcb482466796bb79ce90e466efe95f6772a7318cd0cc19be3e9a828
|
| 3 |
+
size 248943552
|
sft_full/smoe/model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
sft_full/smoe/special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<unk>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
sft_full/smoe/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
sft_full/smoe/tokenizer_config.json
ADDED
|
@@ -0,0 +1,132 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": true,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": true,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": false
|
| 29 |
+
},
|
| 30 |
+
"32000": {
|
| 31 |
+
"content": "<|endoftext|>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
"32001": {
|
| 39 |
+
"content": "<|assistant|>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": true,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": true
|
| 45 |
+
},
|
| 46 |
+
"32002": {
|
| 47 |
+
"content": "<|placeholder1|>",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": false,
|
| 50 |
+
"rstrip": true,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": true
|
| 53 |
+
},
|
| 54 |
+
"32003": {
|
| 55 |
+
"content": "<|placeholder2|>",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": false,
|
| 58 |
+
"rstrip": true,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": true
|
| 61 |
+
},
|
| 62 |
+
"32004": {
|
| 63 |
+
"content": "<|placeholder3|>",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": false,
|
| 66 |
+
"rstrip": true,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": true
|
| 69 |
+
},
|
| 70 |
+
"32005": {
|
| 71 |
+
"content": "<|placeholder4|>",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": false,
|
| 74 |
+
"rstrip": true,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": true
|
| 77 |
+
},
|
| 78 |
+
"32006": {
|
| 79 |
+
"content": "<|system|>",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": false,
|
| 82 |
+
"rstrip": true,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": true
|
| 85 |
+
},
|
| 86 |
+
"32007": {
|
| 87 |
+
"content": "<|end|>",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": false,
|
| 90 |
+
"rstrip": true,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": true
|
| 93 |
+
},
|
| 94 |
+
"32008": {
|
| 95 |
+
"content": "<|placeholder5|>",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": false,
|
| 98 |
+
"rstrip": true,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": true
|
| 101 |
+
},
|
| 102 |
+
"32009": {
|
| 103 |
+
"content": "<|placeholder6|>",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": false,
|
| 106 |
+
"rstrip": true,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": true
|
| 109 |
+
},
|
| 110 |
+
"32010": {
|
| 111 |
+
"content": "<|user|>",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": false,
|
| 114 |
+
"rstrip": true,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": true
|
| 117 |
+
}
|
| 118 |
+
},
|
| 119 |
+
"bos_token": "<s>",
|
| 120 |
+
"chat_template": "{% for message in messages %}{% if message['role'] == 'system' and message['content'] %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
|
| 121 |
+
"clean_up_tokenization_spaces": false,
|
| 122 |
+
"eos_token": "<|endoftext|>",
|
| 123 |
+
"legacy": false,
|
| 124 |
+
"model_max_length": 2048,
|
| 125 |
+
"pad_token": "<unk>",
|
| 126 |
+
"padding_side": "right",
|
| 127 |
+
"sp_model_kwargs": {},
|
| 128 |
+
"spaces_between_special_tokens": false,
|
| 129 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 130 |
+
"unk_token": "<unk>",
|
| 131 |
+
"use_default_system_prompt": false
|
| 132 |
+
}
|
sft_full/smoe/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
sft_full/smoe/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:894656220e9537a9337b5f57a61a0ede5e77ae8c5e2dd56e2d353113ca978d56
|
| 3 |
+
size 8120
|
sft_full/smoe_cosinegating/added_tokens.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|assistant|>": 32001,
|
| 3 |
+
"<|endoftext|>": 32000,
|
| 4 |
+
"<|end|>": 32007,
|
| 5 |
+
"<|placeholder1|>": 32002,
|
| 6 |
+
"<|placeholder2|>": 32003,
|
| 7 |
+
"<|placeholder3|>": 32004,
|
| 8 |
+
"<|placeholder4|>": 32005,
|
| 9 |
+
"<|placeholder5|>": 32008,
|
| 10 |
+
"<|placeholder6|>": 32009,
|
| 11 |
+
"<|system|>": 32006,
|
| 12 |
+
"<|user|>": 32010
|
| 13 |
+
}
|
sft_full/smoe_cosinegating/config.json
ADDED
|
@@ -0,0 +1,168 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/cm/archive/namnv78/checkpoints/phi35-siglip224/pft",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlavaPhiForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"auto_map": {
|
| 9 |
+
"AutoConfig": "configuration_phi3.Phi3Config",
|
| 10 |
+
"AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
|
| 11 |
+
},
|
| 12 |
+
"balance_loss_coef": 0.1,
|
| 13 |
+
"bos_token_id": 1,
|
| 14 |
+
"clip_smoe": true,
|
| 15 |
+
"dropout": false,
|
| 16 |
+
"embd_pdrop": 0.0,
|
| 17 |
+
"eos_token_id": 32000,
|
| 18 |
+
"freeze_mm_mlp_adapter": false,
|
| 19 |
+
"hidden_act": "silu",
|
| 20 |
+
"hidden_size": 3072,
|
| 21 |
+
"image_aspect_ratio": "pad",
|
| 22 |
+
"initializer_range": 0.02,
|
| 23 |
+
"intermediate_size": 8192,
|
| 24 |
+
"local_rank": 0,
|
| 25 |
+
"max_position_embeddings": 131072,
|
| 26 |
+
"mlp_smoe": true,
|
| 27 |
+
"mm_hidden_size": 1152,
|
| 28 |
+
"mm_patch_merge_type": "flat",
|
| 29 |
+
"mm_projector_lr": null,
|
| 30 |
+
"mm_projector_type": "moe",
|
| 31 |
+
"mm_use_im_patch_token": false,
|
| 32 |
+
"mm_use_im_start_end": false,
|
| 33 |
+
"mm_vision_select_feature": "patch",
|
| 34 |
+
"mm_vision_select_layer": -2,
|
| 35 |
+
"mm_vision_tower": "google/siglip-so400m-patch14-224",
|
| 36 |
+
"model_type": "llava_phi",
|
| 37 |
+
"moe_name": "smoe_cosinegating",
|
| 38 |
+
"num_attention_heads": 32,
|
| 39 |
+
"num_experts": 4,
|
| 40 |
+
"num_hidden_layers": 32,
|
| 41 |
+
"num_key_value_heads": 32,
|
| 42 |
+
"num_layers": 3,
|
| 43 |
+
"num_selected": 2,
|
| 44 |
+
"original_max_position_embeddings": 4096,
|
| 45 |
+
"pad_token_id": 32000,
|
| 46 |
+
"resid_pdrop": 0.0,
|
| 47 |
+
"rms_norm_eps": 1e-05,
|
| 48 |
+
"rope_scaling": {
|
| 49 |
+
"long_factor": [
|
| 50 |
+
1.0800000429153442,
|
| 51 |
+
1.1100000143051147,
|
| 52 |
+
1.1399999856948853,
|
| 53 |
+
1.340000033378601,
|
| 54 |
+
1.5899999141693115,
|
| 55 |
+
1.600000023841858,
|
| 56 |
+
1.6200000047683716,
|
| 57 |
+
2.620000123977661,
|
| 58 |
+
3.2300000190734863,
|
| 59 |
+
3.2300000190734863,
|
| 60 |
+
4.789999961853027,
|
| 61 |
+
7.400000095367432,
|
| 62 |
+
7.700000286102295,
|
| 63 |
+
9.09000015258789,
|
| 64 |
+
12.199999809265137,
|
| 65 |
+
17.670000076293945,
|
| 66 |
+
24.46000099182129,
|
| 67 |
+
28.57000160217285,
|
| 68 |
+
30.420001983642578,
|
| 69 |
+
30.840002059936523,
|
| 70 |
+
32.590003967285156,
|
| 71 |
+
32.93000411987305,
|
| 72 |
+
42.320003509521484,
|
| 73 |
+
44.96000289916992,
|
| 74 |
+
50.340003967285156,
|
| 75 |
+
50.45000457763672,
|
| 76 |
+
57.55000305175781,
|
| 77 |
+
57.93000411987305,
|
| 78 |
+
58.21000289916992,
|
| 79 |
+
60.1400032043457,
|
| 80 |
+
62.61000442504883,
|
| 81 |
+
62.62000274658203,
|
| 82 |
+
62.71000289916992,
|
| 83 |
+
63.1400032043457,
|
| 84 |
+
63.1400032043457,
|
| 85 |
+
63.77000427246094,
|
| 86 |
+
63.93000411987305,
|
| 87 |
+
63.96000289916992,
|
| 88 |
+
63.970001220703125,
|
| 89 |
+
64.02999877929688,
|
| 90 |
+
64.06999969482422,
|
| 91 |
+
64.08000183105469,
|
| 92 |
+
64.12000274658203,
|
| 93 |
+
64.41000366210938,
|
| 94 |
+
64.4800033569336,
|
| 95 |
+
64.51000213623047,
|
| 96 |
+
64.52999877929688,
|
| 97 |
+
64.83999633789062
|
| 98 |
+
],
|
| 99 |
+
"short_factor": [
|
| 100 |
+
1.0,
|
| 101 |
+
1.0199999809265137,
|
| 102 |
+
1.0299999713897705,
|
| 103 |
+
1.0299999713897705,
|
| 104 |
+
1.0499999523162842,
|
| 105 |
+
1.0499999523162842,
|
| 106 |
+
1.0499999523162842,
|
| 107 |
+
1.0499999523162842,
|
| 108 |
+
1.0499999523162842,
|
| 109 |
+
1.0699999332427979,
|
| 110 |
+
1.0999999046325684,
|
| 111 |
+
1.1099998950958252,
|
| 112 |
+
1.1599998474121094,
|
| 113 |
+
1.1599998474121094,
|
| 114 |
+
1.1699998378753662,
|
| 115 |
+
1.2899998426437378,
|
| 116 |
+
1.339999794960022,
|
| 117 |
+
1.679999828338623,
|
| 118 |
+
1.7899998426437378,
|
| 119 |
+
1.8199998140335083,
|
| 120 |
+
1.8499997854232788,
|
| 121 |
+
1.8799997568130493,
|
| 122 |
+
1.9099997282028198,
|
| 123 |
+
1.9399996995925903,
|
| 124 |
+
1.9899996519088745,
|
| 125 |
+
2.0199997425079346,
|
| 126 |
+
2.0199997425079346,
|
| 127 |
+
2.0199997425079346,
|
| 128 |
+
2.0199997425079346,
|
| 129 |
+
2.0199997425079346,
|
| 130 |
+
2.0199997425079346,
|
| 131 |
+
2.0299997329711914,
|
| 132 |
+
2.0299997329711914,
|
| 133 |
+
2.0299997329711914,
|
| 134 |
+
2.0299997329711914,
|
| 135 |
+
2.0299997329711914,
|
| 136 |
+
2.0299997329711914,
|
| 137 |
+
2.0299997329711914,
|
| 138 |
+
2.0299997329711914,
|
| 139 |
+
2.0299997329711914,
|
| 140 |
+
2.0799996852874756,
|
| 141 |
+
2.0899996757507324,
|
| 142 |
+
2.189999580383301,
|
| 143 |
+
2.2199995517730713,
|
| 144 |
+
2.5899994373321533,
|
| 145 |
+
2.729999542236328,
|
| 146 |
+
2.749999523162842,
|
| 147 |
+
2.8399994373321533
|
| 148 |
+
],
|
| 149 |
+
"type": "longrope"
|
| 150 |
+
},
|
| 151 |
+
"rope_theta": 10000.0,
|
| 152 |
+
"router_z_loss_coef": 0.01,
|
| 153 |
+
"scales": [
|
| 154 |
+
1,
|
| 155 |
+
3
|
| 156 |
+
],
|
| 157 |
+
"sliding_window": 262144,
|
| 158 |
+
"tie_word_embeddings": false,
|
| 159 |
+
"tokenizer_model_max_length": 2048,
|
| 160 |
+
"tokenizer_padding_side": "right",
|
| 161 |
+
"torch_dtype": "bfloat16",
|
| 162 |
+
"training": true,
|
| 163 |
+
"transformers_version": "4.43.0",
|
| 164 |
+
"tune_mm_mlp_adapter": false,
|
| 165 |
+
"use_cache": true,
|
| 166 |
+
"use_mm_proj": true,
|
| 167 |
+
"vocab_size": 32064
|
| 168 |
+
}
|
sft_full/smoe_cosinegating/generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": [
|
| 6 |
+
32007,
|
| 7 |
+
32001,
|
| 8 |
+
32000
|
| 9 |
+
],
|
| 10 |
+
"pad_token_id": 32000,
|
| 11 |
+
"transformers_version": "4.43.0"
|
| 12 |
+
}
|
sft_full/smoe_cosinegating/model-00001-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e70af001e069480c661b44bda40ec265f8151b204f2ce7e1bd4a18adc30f49d
|
| 3 |
+
size 4972489328
|
sft_full/smoe_cosinegating/model-00002-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d9697408bce9e61d9db9e6a0303f7884a18627150cd410e22f1db4e78fb7d1c
|
| 3 |
+
size 4985533608
|
sft_full/smoe_cosinegating/model-00003-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d8b17f0f381e5754ad51c721f0eddfd4aae81785deb6a72a998a93423e0f769f
|
| 3 |
+
size 248943664
|
sft_full/smoe_cosinegating/model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
sft_full/smoe_cosinegating/special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<unk>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
sft_full/smoe_cosinegating/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
sft_full/smoe_cosinegating/tokenizer_config.json
ADDED
|
@@ -0,0 +1,132 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": true,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": true,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": false
|
| 29 |
+
},
|
| 30 |
+
"32000": {
|
| 31 |
+
"content": "<|endoftext|>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
"32001": {
|
| 39 |
+
"content": "<|assistant|>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": true,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": true
|
| 45 |
+
},
|
| 46 |
+
"32002": {
|
| 47 |
+
"content": "<|placeholder1|>",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": false,
|
| 50 |
+
"rstrip": true,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": true
|
| 53 |
+
},
|
| 54 |
+
"32003": {
|
| 55 |
+
"content": "<|placeholder2|>",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": false,
|
| 58 |
+
"rstrip": true,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": true
|
| 61 |
+
},
|
| 62 |
+
"32004": {
|
| 63 |
+
"content": "<|placeholder3|>",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": false,
|
| 66 |
+
"rstrip": true,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": true
|
| 69 |
+
},
|
| 70 |
+
"32005": {
|
| 71 |
+
"content": "<|placeholder4|>",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": false,
|
| 74 |
+
"rstrip": true,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": true
|
| 77 |
+
},
|
| 78 |
+
"32006": {
|
| 79 |
+
"content": "<|system|>",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": false,
|
| 82 |
+
"rstrip": true,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": true
|
| 85 |
+
},
|
| 86 |
+
"32007": {
|
| 87 |
+
"content": "<|end|>",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": false,
|
| 90 |
+
"rstrip": true,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": true
|
| 93 |
+
},
|
| 94 |
+
"32008": {
|
| 95 |
+
"content": "<|placeholder5|>",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": false,
|
| 98 |
+
"rstrip": true,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": true
|
| 101 |
+
},
|
| 102 |
+
"32009": {
|
| 103 |
+
"content": "<|placeholder6|>",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": false,
|
| 106 |
+
"rstrip": true,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": true
|
| 109 |
+
},
|
| 110 |
+
"32010": {
|
| 111 |
+
"content": "<|user|>",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": false,
|
| 114 |
+
"rstrip": true,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": true
|
| 117 |
+
}
|
| 118 |
+
},
|
| 119 |
+
"bos_token": "<s>",
|
| 120 |
+
"chat_template": "{% for message in messages %}{% if message['role'] == 'system' and message['content'] %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
|
| 121 |
+
"clean_up_tokenization_spaces": false,
|
| 122 |
+
"eos_token": "<|endoftext|>",
|
| 123 |
+
"legacy": false,
|
| 124 |
+
"model_max_length": 2048,
|
| 125 |
+
"pad_token": "<unk>",
|
| 126 |
+
"padding_side": "right",
|
| 127 |
+
"sp_model_kwargs": {},
|
| 128 |
+
"spaces_between_special_tokens": false,
|
| 129 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 130 |
+
"unk_token": "<unk>",
|
| 131 |
+
"use_default_system_prompt": false
|
| 132 |
+
}
|
sft_full/smoe_cosinegating/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
sft_full/smoe_cosinegating/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:74abf7f3a5b16db530b49de04d931d31874d9902af82c92d683f25980e00ed19
|
| 3 |
+
size 8184
|
sft_full/smoe_perturbed/added_tokens.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|assistant|>": 32001,
|
| 3 |
+
"<|endoftext|>": 32000,
|
| 4 |
+
"<|end|>": 32007,
|
| 5 |
+
"<|placeholder1|>": 32002,
|
| 6 |
+
"<|placeholder2|>": 32003,
|
| 7 |
+
"<|placeholder3|>": 32004,
|
| 8 |
+
"<|placeholder4|>": 32005,
|
| 9 |
+
"<|placeholder5|>": 32008,
|
| 10 |
+
"<|placeholder6|>": 32009,
|
| 11 |
+
"<|system|>": 32006,
|
| 12 |
+
"<|user|>": 32010
|
| 13 |
+
}
|
sft_full/smoe_perturbed/config.json
ADDED
|
@@ -0,0 +1,168 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/cm/archive/namnv78/checkpoints/phi35-siglip224/pft",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlavaPhiForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"auto_map": {
|
| 9 |
+
"AutoConfig": "configuration_phi3.Phi3Config",
|
| 10 |
+
"AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
|
| 11 |
+
},
|
| 12 |
+
"balance_loss_coef": 0.1,
|
| 13 |
+
"bos_token_id": 1,
|
| 14 |
+
"clip_smoe": true,
|
| 15 |
+
"dropout": false,
|
| 16 |
+
"embd_pdrop": 0.0,
|
| 17 |
+
"eos_token_id": 32000,
|
| 18 |
+
"freeze_mm_mlp_adapter": false,
|
| 19 |
+
"hidden_act": "silu",
|
| 20 |
+
"hidden_size": 3072,
|
| 21 |
+
"image_aspect_ratio": "pad",
|
| 22 |
+
"initializer_range": 0.02,
|
| 23 |
+
"intermediate_size": 8192,
|
| 24 |
+
"local_rank": 0,
|
| 25 |
+
"max_position_embeddings": 131072,
|
| 26 |
+
"mlp_smoe": true,
|
| 27 |
+
"mm_hidden_size": 1152,
|
| 28 |
+
"mm_patch_merge_type": "flat",
|
| 29 |
+
"mm_projector_lr": null,
|
| 30 |
+
"mm_projector_type": "moe",
|
| 31 |
+
"mm_use_im_patch_token": false,
|
| 32 |
+
"mm_use_im_start_end": false,
|
| 33 |
+
"mm_vision_select_feature": "patch",
|
| 34 |
+
"mm_vision_select_layer": -2,
|
| 35 |
+
"mm_vision_tower": "google/siglip-so400m-patch14-224",
|
| 36 |
+
"model_type": "llava_phi",
|
| 37 |
+
"moe_name": "smoe_perturbed",
|
| 38 |
+
"num_attention_heads": 32,
|
| 39 |
+
"num_experts": 4,
|
| 40 |
+
"num_hidden_layers": 32,
|
| 41 |
+
"num_key_value_heads": 32,
|
| 42 |
+
"num_layers": 3,
|
| 43 |
+
"num_selected": 2,
|
| 44 |
+
"original_max_position_embeddings": 4096,
|
| 45 |
+
"pad_token_id": 32000,
|
| 46 |
+
"resid_pdrop": 0.0,
|
| 47 |
+
"rms_norm_eps": 1e-05,
|
| 48 |
+
"rope_scaling": {
|
| 49 |
+
"long_factor": [
|
| 50 |
+
1.0800000429153442,
|
| 51 |
+
1.1100000143051147,
|
| 52 |
+
1.1399999856948853,
|
| 53 |
+
1.340000033378601,
|
| 54 |
+
1.5899999141693115,
|
| 55 |
+
1.600000023841858,
|
| 56 |
+
1.6200000047683716,
|
| 57 |
+
2.620000123977661,
|
| 58 |
+
3.2300000190734863,
|
| 59 |
+
3.2300000190734863,
|
| 60 |
+
4.789999961853027,
|
| 61 |
+
7.400000095367432,
|
| 62 |
+
7.700000286102295,
|
| 63 |
+
9.09000015258789,
|
| 64 |
+
12.199999809265137,
|
| 65 |
+
17.670000076293945,
|
| 66 |
+
24.46000099182129,
|
| 67 |
+
28.57000160217285,
|
| 68 |
+
30.420001983642578,
|
| 69 |
+
30.840002059936523,
|
| 70 |
+
32.590003967285156,
|
| 71 |
+
32.93000411987305,
|
| 72 |
+
42.320003509521484,
|
| 73 |
+
44.96000289916992,
|
| 74 |
+
50.340003967285156,
|
| 75 |
+
50.45000457763672,
|
| 76 |
+
57.55000305175781,
|
| 77 |
+
57.93000411987305,
|
| 78 |
+
58.21000289916992,
|
| 79 |
+
60.1400032043457,
|
| 80 |
+
62.61000442504883,
|
| 81 |
+
62.62000274658203,
|
| 82 |
+
62.71000289916992,
|
| 83 |
+
63.1400032043457,
|
| 84 |
+
63.1400032043457,
|
| 85 |
+
63.77000427246094,
|
| 86 |
+
63.93000411987305,
|
| 87 |
+
63.96000289916992,
|
| 88 |
+
63.970001220703125,
|
| 89 |
+
64.02999877929688,
|
| 90 |
+
64.06999969482422,
|
| 91 |
+
64.08000183105469,
|
| 92 |
+
64.12000274658203,
|
| 93 |
+
64.41000366210938,
|
| 94 |
+
64.4800033569336,
|
| 95 |
+
64.51000213623047,
|
| 96 |
+
64.52999877929688,
|
| 97 |
+
64.83999633789062
|
| 98 |
+
],
|
| 99 |
+
"short_factor": [
|
| 100 |
+
1.0,
|
| 101 |
+
1.0199999809265137,
|
| 102 |
+
1.0299999713897705,
|
| 103 |
+
1.0299999713897705,
|
| 104 |
+
1.0499999523162842,
|
| 105 |
+
1.0499999523162842,
|
| 106 |
+
1.0499999523162842,
|
| 107 |
+
1.0499999523162842,
|
| 108 |
+
1.0499999523162842,
|
| 109 |
+
1.0699999332427979,
|
| 110 |
+
1.0999999046325684,
|
| 111 |
+
1.1099998950958252,
|
| 112 |
+
1.1599998474121094,
|
| 113 |
+
1.1599998474121094,
|
| 114 |
+
1.1699998378753662,
|
| 115 |
+
1.2899998426437378,
|
| 116 |
+
1.339999794960022,
|
| 117 |
+
1.679999828338623,
|
| 118 |
+
1.7899998426437378,
|
| 119 |
+
1.8199998140335083,
|
| 120 |
+
1.8499997854232788,
|
| 121 |
+
1.8799997568130493,
|
| 122 |
+
1.9099997282028198,
|
| 123 |
+
1.9399996995925903,
|
| 124 |
+
1.9899996519088745,
|
| 125 |
+
2.0199997425079346,
|
| 126 |
+
2.0199997425079346,
|
| 127 |
+
2.0199997425079346,
|
| 128 |
+
2.0199997425079346,
|
| 129 |
+
2.0199997425079346,
|
| 130 |
+
2.0199997425079346,
|
| 131 |
+
2.0299997329711914,
|
| 132 |
+
2.0299997329711914,
|
| 133 |
+
2.0299997329711914,
|
| 134 |
+
2.0299997329711914,
|
| 135 |
+
2.0299997329711914,
|
| 136 |
+
2.0299997329711914,
|
| 137 |
+
2.0299997329711914,
|
| 138 |
+
2.0299997329711914,
|
| 139 |
+
2.0299997329711914,
|
| 140 |
+
2.0799996852874756,
|
| 141 |
+
2.0899996757507324,
|
| 142 |
+
2.189999580383301,
|
| 143 |
+
2.2199995517730713,
|
| 144 |
+
2.5899994373321533,
|
| 145 |
+
2.729999542236328,
|
| 146 |
+
2.749999523162842,
|
| 147 |
+
2.8399994373321533
|
| 148 |
+
],
|
| 149 |
+
"type": "longrope"
|
| 150 |
+
},
|
| 151 |
+
"rope_theta": 10000.0,
|
| 152 |
+
"router_z_loss_coef": 0.01,
|
| 153 |
+
"scales": [
|
| 154 |
+
1,
|
| 155 |
+
3
|
| 156 |
+
],
|
| 157 |
+
"sliding_window": 262144,
|
| 158 |
+
"tie_word_embeddings": false,
|
| 159 |
+
"tokenizer_model_max_length": 2048,
|
| 160 |
+
"tokenizer_padding_side": "right",
|
| 161 |
+
"torch_dtype": "bfloat16",
|
| 162 |
+
"training": true,
|
| 163 |
+
"transformers_version": "4.43.0",
|
| 164 |
+
"tune_mm_mlp_adapter": false,
|
| 165 |
+
"use_cache": true,
|
| 166 |
+
"use_mm_proj": true,
|
| 167 |
+
"vocab_size": 32064
|
| 168 |
+
}
|
sft_full/smoe_perturbed/generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": [
|
| 6 |
+
32007,
|
| 7 |
+
32001,
|
| 8 |
+
32000
|
| 9 |
+
],
|
| 10 |
+
"pad_token_id": 32000,
|
| 11 |
+
"transformers_version": "4.43.0"
|
| 12 |
+
}
|
sft_full/smoe_perturbed/model-00001-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:87fd7ac6ec78d179eaf9a74c6bcf515318e337ab9f99c8c6d5659630e3f884a9
|
| 3 |
+
size 4972489328
|
sft_full/smoe_perturbed/model-00002-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea4992fcf804b3dd4e133110725b2bfeb819559139bddaeb852e6931cf4faa74
|
| 3 |
+
size 4985533608
|
sft_full/smoe_perturbed/model-00003-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:369ab1a2c9903478d233348bcdee93fab707680031305c19354783c04fbf4004
|
| 3 |
+
size 248943664
|
sft_full/smoe_perturbed/model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
sft_full/smoe_perturbed/special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<unk>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
sft_full/smoe_perturbed/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
sft_full/smoe_perturbed/tokenizer_config.json
ADDED
|
@@ -0,0 +1,132 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": true,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": true,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": false
|
| 29 |
+
},
|
| 30 |
+
"32000": {
|
| 31 |
+
"content": "<|endoftext|>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
"32001": {
|
| 39 |
+
"content": "<|assistant|>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": true,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": true
|
| 45 |
+
},
|
| 46 |
+
"32002": {
|
| 47 |
+
"content": "<|placeholder1|>",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": false,
|
| 50 |
+
"rstrip": true,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": true
|
| 53 |
+
},
|
| 54 |
+
"32003": {
|
| 55 |
+
"content": "<|placeholder2|>",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": false,
|
| 58 |
+
"rstrip": true,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": true
|
| 61 |
+
},
|
| 62 |
+
"32004": {
|
| 63 |
+
"content": "<|placeholder3|>",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": false,
|
| 66 |
+
"rstrip": true,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": true
|
| 69 |
+
},
|
| 70 |
+
"32005": {
|
| 71 |
+
"content": "<|placeholder4|>",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": false,
|
| 74 |
+
"rstrip": true,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": true
|
| 77 |
+
},
|
| 78 |
+
"32006": {
|
| 79 |
+
"content": "<|system|>",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": false,
|
| 82 |
+
"rstrip": true,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": true
|
| 85 |
+
},
|
| 86 |
+
"32007": {
|
| 87 |
+
"content": "<|end|>",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": false,
|
| 90 |
+
"rstrip": true,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": true
|
| 93 |
+
},
|
| 94 |
+
"32008": {
|
| 95 |
+
"content": "<|placeholder5|>",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": false,
|
| 98 |
+
"rstrip": true,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": true
|
| 101 |
+
},
|
| 102 |
+
"32009": {
|
| 103 |
+
"content": "<|placeholder6|>",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": false,
|
| 106 |
+
"rstrip": true,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": true
|
| 109 |
+
},
|
| 110 |
+
"32010": {
|
| 111 |
+
"content": "<|user|>",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": false,
|
| 114 |
+
"rstrip": true,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": true
|
| 117 |
+
}
|
| 118 |
+
},
|
| 119 |
+
"bos_token": "<s>",
|
| 120 |
+
"chat_template": "{% for message in messages %}{% if message['role'] == 'system' and message['content'] %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
|
| 121 |
+
"clean_up_tokenization_spaces": false,
|
| 122 |
+
"eos_token": "<|endoftext|>",
|
| 123 |
+
"legacy": false,
|
| 124 |
+
"model_max_length": 2048,
|
| 125 |
+
"pad_token": "<unk>",
|
| 126 |
+
"padding_side": "right",
|
| 127 |
+
"sp_model_kwargs": {},
|
| 128 |
+
"spaces_between_special_tokens": false,
|
| 129 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 130 |
+
"unk_token": "<unk>",
|
| 131 |
+
"use_default_system_prompt": false
|
| 132 |
+
}
|
sft_full/smoe_perturbed/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
sft_full/smoe_perturbed/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:08aaf4412961001d21ae464e0d5be33c4cc8cb307123de1b06ef7f4872692493
|
| 3 |
+
size 8184
|
sft_full/smoe_sigmoidgating/added_tokens.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|assistant|>": 32001,
|
| 3 |
+
"<|endoftext|>": 32000,
|
| 4 |
+
"<|end|>": 32007,
|
| 5 |
+
"<|placeholder1|>": 32002,
|
| 6 |
+
"<|placeholder2|>": 32003,
|
| 7 |
+
"<|placeholder3|>": 32004,
|
| 8 |
+
"<|placeholder4|>": 32005,
|
| 9 |
+
"<|placeholder5|>": 32008,
|
| 10 |
+
"<|placeholder6|>": 32009,
|
| 11 |
+
"<|system|>": 32006,
|
| 12 |
+
"<|user|>": 32010
|
| 13 |
+
}
|
sft_full/smoe_sigmoidgating/config.json
ADDED
|
@@ -0,0 +1,168 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/cm/archive/namnv78/checkpoints/phi35-siglip224/pft",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlavaPhiForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"auto_map": {
|
| 9 |
+
"AutoConfig": "configuration_phi3.Phi3Config",
|
| 10 |
+
"AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
|
| 11 |
+
},
|
| 12 |
+
"balance_loss_coef": 0.1,
|
| 13 |
+
"bos_token_id": 1,
|
| 14 |
+
"clip_smoe": true,
|
| 15 |
+
"dropout": false,
|
| 16 |
+
"embd_pdrop": 0.0,
|
| 17 |
+
"eos_token_id": 32000,
|
| 18 |
+
"freeze_mm_mlp_adapter": false,
|
| 19 |
+
"hidden_act": "silu",
|
| 20 |
+
"hidden_size": 3072,
|
| 21 |
+
"image_aspect_ratio": "pad",
|
| 22 |
+
"initializer_range": 0.02,
|
| 23 |
+
"intermediate_size": 8192,
|
| 24 |
+
"local_rank": 0,
|
| 25 |
+
"max_position_embeddings": 131072,
|
| 26 |
+
"mlp_smoe": true,
|
| 27 |
+
"mm_hidden_size": 1152,
|
| 28 |
+
"mm_patch_merge_type": "flat",
|
| 29 |
+
"mm_projector_lr": null,
|
| 30 |
+
"mm_projector_type": "moe",
|
| 31 |
+
"mm_use_im_patch_token": false,
|
| 32 |
+
"mm_use_im_start_end": false,
|
| 33 |
+
"mm_vision_select_feature": "patch",
|
| 34 |
+
"mm_vision_select_layer": -2,
|
| 35 |
+
"mm_vision_tower": "google/siglip-so400m-patch14-224",
|
| 36 |
+
"model_type": "llava_phi",
|
| 37 |
+
"moe_name": "smoe_sigmoidgating",
|
| 38 |
+
"num_attention_heads": 32,
|
| 39 |
+
"num_experts": 4,
|
| 40 |
+
"num_hidden_layers": 32,
|
| 41 |
+
"num_key_value_heads": 32,
|
| 42 |
+
"num_layers": 3,
|
| 43 |
+
"num_selected": 2,
|
| 44 |
+
"original_max_position_embeddings": 4096,
|
| 45 |
+
"pad_token_id": 32000,
|
| 46 |
+
"resid_pdrop": 0.0,
|
| 47 |
+
"rms_norm_eps": 1e-05,
|
| 48 |
+
"rope_scaling": {
|
| 49 |
+
"long_factor": [
|
| 50 |
+
1.0800000429153442,
|
| 51 |
+
1.1100000143051147,
|
| 52 |
+
1.1399999856948853,
|
| 53 |
+
1.340000033378601,
|
| 54 |
+
1.5899999141693115,
|
| 55 |
+
1.600000023841858,
|
| 56 |
+
1.6200000047683716,
|
| 57 |
+
2.620000123977661,
|
| 58 |
+
3.2300000190734863,
|
| 59 |
+
3.2300000190734863,
|
| 60 |
+
4.789999961853027,
|
| 61 |
+
7.400000095367432,
|
| 62 |
+
7.700000286102295,
|
| 63 |
+
9.09000015258789,
|
| 64 |
+
12.199999809265137,
|
| 65 |
+
17.670000076293945,
|
| 66 |
+
24.46000099182129,
|
| 67 |
+
28.57000160217285,
|
| 68 |
+
30.420001983642578,
|
| 69 |
+
30.840002059936523,
|
| 70 |
+
32.590003967285156,
|
| 71 |
+
32.93000411987305,
|
| 72 |
+
42.320003509521484,
|
| 73 |
+
44.96000289916992,
|
| 74 |
+
50.340003967285156,
|
| 75 |
+
50.45000457763672,
|
| 76 |
+
57.55000305175781,
|
| 77 |
+
57.93000411987305,
|
| 78 |
+
58.21000289916992,
|
| 79 |
+
60.1400032043457,
|
| 80 |
+
62.61000442504883,
|
| 81 |
+
62.62000274658203,
|
| 82 |
+
62.71000289916992,
|
| 83 |
+
63.1400032043457,
|
| 84 |
+
63.1400032043457,
|
| 85 |
+
63.77000427246094,
|
| 86 |
+
63.93000411987305,
|
| 87 |
+
63.96000289916992,
|
| 88 |
+
63.970001220703125,
|
| 89 |
+
64.02999877929688,
|
| 90 |
+
64.06999969482422,
|
| 91 |
+
64.08000183105469,
|
| 92 |
+
64.12000274658203,
|
| 93 |
+
64.41000366210938,
|
| 94 |
+
64.4800033569336,
|
| 95 |
+
64.51000213623047,
|
| 96 |
+
64.52999877929688,
|
| 97 |
+
64.83999633789062
|
| 98 |
+
],
|
| 99 |
+
"short_factor": [
|
| 100 |
+
1.0,
|
| 101 |
+
1.0199999809265137,
|
| 102 |
+
1.0299999713897705,
|
| 103 |
+
1.0299999713897705,
|
| 104 |
+
1.0499999523162842,
|
| 105 |
+
1.0499999523162842,
|
| 106 |
+
1.0499999523162842,
|
| 107 |
+
1.0499999523162842,
|
| 108 |
+
1.0499999523162842,
|
| 109 |
+
1.0699999332427979,
|
| 110 |
+
1.0999999046325684,
|
| 111 |
+
1.1099998950958252,
|
| 112 |
+
1.1599998474121094,
|
| 113 |
+
1.1599998474121094,
|
| 114 |
+
1.1699998378753662,
|
| 115 |
+
1.2899998426437378,
|
| 116 |
+
1.339999794960022,
|
| 117 |
+
1.679999828338623,
|
| 118 |
+
1.7899998426437378,
|
| 119 |
+
1.8199998140335083,
|
| 120 |
+
1.8499997854232788,
|
| 121 |
+
1.8799997568130493,
|
| 122 |
+
1.9099997282028198,
|
| 123 |
+
1.9399996995925903,
|
| 124 |
+
1.9899996519088745,
|
| 125 |
+
2.0199997425079346,
|
| 126 |
+
2.0199997425079346,
|
| 127 |
+
2.0199997425079346,
|
| 128 |
+
2.0199997425079346,
|
| 129 |
+
2.0199997425079346,
|
| 130 |
+
2.0199997425079346,
|
| 131 |
+
2.0299997329711914,
|
| 132 |
+
2.0299997329711914,
|
| 133 |
+
2.0299997329711914,
|
| 134 |
+
2.0299997329711914,
|
| 135 |
+
2.0299997329711914,
|
| 136 |
+
2.0299997329711914,
|
| 137 |
+
2.0299997329711914,
|
| 138 |
+
2.0299997329711914,
|
| 139 |
+
2.0299997329711914,
|
| 140 |
+
2.0799996852874756,
|
| 141 |
+
2.0899996757507324,
|
| 142 |
+
2.189999580383301,
|
| 143 |
+
2.2199995517730713,
|
| 144 |
+
2.5899994373321533,
|
| 145 |
+
2.729999542236328,
|
| 146 |
+
2.749999523162842,
|
| 147 |
+
2.8399994373321533
|
| 148 |
+
],
|
| 149 |
+
"type": "longrope"
|
| 150 |
+
},
|
| 151 |
+
"rope_theta": 10000.0,
|
| 152 |
+
"router_z_loss_coef": 0.01,
|
| 153 |
+
"scales": [
|
| 154 |
+
1,
|
| 155 |
+
3
|
| 156 |
+
],
|
| 157 |
+
"sliding_window": 262144,
|
| 158 |
+
"tie_word_embeddings": false,
|
| 159 |
+
"tokenizer_model_max_length": 2048,
|
| 160 |
+
"tokenizer_padding_side": "right",
|
| 161 |
+
"torch_dtype": "bfloat16",
|
| 162 |
+
"training": true,
|
| 163 |
+
"transformers_version": "4.43.0",
|
| 164 |
+
"tune_mm_mlp_adapter": false,
|
| 165 |
+
"use_cache": true,
|
| 166 |
+
"use_mm_proj": true,
|
| 167 |
+
"vocab_size": 32064
|
| 168 |
+
}
|